Tianfu Wu

Bin Tan, Nan Xue, Tianfu Wu et al.

This paper studies the challenging two-view 3D reconstruction in a rigorous sparse-view configuration, which is suffering from insufficient correspondences in the input image pairs for camera pose estimation. We present a novel Neural One-PlanE RANSAC framework (termed NOPE-SAC in short) that exerts excellent capability to learn one-plane pose hypotheses from 3D plane correspondences. Building on the top of a siamese plane detection network, our NOPE-SAC first generates putative plane correspondences with a coarse initial pose. It then feeds the learned 3D plane parameters of correspondences into shared MLPs to estimate the one-plane camera pose hypotheses, which are subsequently reweighed in a RANSAC manner to obtain the final camera pose. Because the neural one-plane pose minimizes the number of plane correspondences for adaptive pose hypotheses generation, it enables stable pose voting and reliable pose refinement in a few plane correspondences for the sparse-view inputs. In the experiments, we demonstrate that our NOPE-SAC significantly improves the camera pose estimation for the two-view inputs with severe viewpoint changes, setting several new state-of-the-art performances on two challenging benchmarks, i.e., MatterPort3D and ScanNet, for sparse-view 3D reconstruction. The source code is released at https://github.com/IceTTTb/NopeSAC for reproducible research.

Nan Xue, Tianfu Wu, Song Bai et al.

This article presents Holistically-Attracted Wireframe Parsing (HAWP), a method for geometric analysis of 2D images containing wireframes formed by line segments and junctions. HAWP utilizes a parsimonious Holistic Attraction (HAT) field representation that encodes line segments using a closed-form 4D geometric vector field. The proposed HAWP consists of three sequential components empowered by end-to-end and HAT-driven designs: (1) generating a dense set of line segments from HAT fields and endpoint proposals from heatmaps, (2) binding the dense line segments to sparse endpoint proposals to produce initial wireframes, and (3) filtering false positive proposals through a novel endpoint-decoupled line-of-interest aligning (EPD LOIAlign) module that captures the co-occurrence between endpoint proposals and HAT fields for better verification. Thanks to our novel designs, HAWPv2 shows strong performance in fully supervised learning, while HAWPv3 excels in self-supervised learning, achieving superior repeatability scores and efficient training (24 GPU hours on a single GPU). Furthermore, HAWPv3 exhibits a promising potential for wireframe parsing in out-of-distribution images without providing ground truth labels of wireframes.

Yuxi Xiao, Nan Xue, Tianfu Wu et al.

This paper presents a neural incremental Structure-from-Motion (SfM) approach, Level-S$^2$fM, which estimates the camera poses and scene geometry from a set of uncalibrated images by learning coordinate MLPs for the implicit surfaces and the radiance fields from the established keypoint correspondences. Our novel formulation poses some new challenges due to inevitable two-view and few-view configurations in the incremental SfM pipeline, which complicates the optimization of coordinate MLPs for volumetric neural rendering with unknown camera poses. Nevertheless, we demonstrate that the strong inductive basis conveying in the 2D correspondences is promising to tackle those challenges by exploiting the relationship between the ray sampling schemes. Based on this, we revisit the pipeline of incremental SfM and renew the key components, including two-view geometry initialization, the camera poses registration, the 3D points triangulation, and Bundle Adjustment, with a fresh perspective based on neural implicit surfaces. By unifying the scene geometry in small MLP networks through coordinate MLPs, our Level-S$^2$fM treats the zero-level set of the implicit surface as an informative top-down regularization to manage the reconstructed 3D points, reject the outliers in correspondences via querying SDF, and refine the estimated geometries by NBA (Neural BA). Not only does our Level-S$^2$fM lead to promising results on camera pose estimation and scene geometry reconstruction, but it also shows a promising way for neural implicit rendering without knowing camera extrinsic beforehand.

Wenchao Ma, Bin Tan, Nan Xue et al.

This paper studies the problem of holistic 3D wireframe perception (HoW-3D), a new task of perceiving both the visible 3D wireframes and the invisible ones from single-view 2D images. As the non-front surfaces of an object cannot be directly observed in a single view, estimating the non-line-of-sight (NLOS) geometries in HoW-3D is a fundamentally challenging problem and remains open in computer vision. We study the problem of HoW-3D by proposing an ABC-HoW benchmark, which is created on top of CAD models sourced from the ABC-dataset with 12k single-view images and the corresponding holistic 3D wireframe models. With our large-scale ABC-HoW benchmark available, we present a novel Deep Spatial Gestalt (DSG) model to learn the visible junctions and line segments as the basis and then infer the NLOS 3D structures from the visible cues by following the Gestalt principles of human vision systems. In our experiments, we demonstrate that our DSG model performs very well in inferring the holistic 3D wireframes from single-view images. Compared with the strong baseline methods, our DSG model outperforms the previous wireframe detectors in detecting the invisible line geometry in single-view images and is even very competitive with prior arts that take high-fidelity PointCloud as inputs on reconstructing 3D wireframes.

Nan Xue, Bin Tan, Yuxi Xiao et al.

This paper studies the problem of structured 3D reconstruction using wireframes that consist of line segments and junctions, focusing on the computation of structured boundary geometries of scenes. Instead of leveraging matching-based solutions from 2D wireframes (or line segments) for 3D wireframe reconstruction as done in prior arts, we present NEAT, a rendering-distilling formulation using neural fields to represent 3D line segments with 2D observations, and bipartite matching for perceiving and distilling of a sparse set of 3D global junctions. The proposed {NEAT} enjoys the joint optimization of the neural fields and the global junctions from scratch, using view-dependent 2D observations without precomputed cross-view feature matching. Comprehensive experiments on the DTU and BlendedMVS datasets demonstrate our NEAT's superiority over state-of-the-art alternatives for 3D wireframe reconstruction. Moreover, the distilled 3D global junctions by NEAT, are a better initialization than SfM points, for the recently-emerged 3D Gaussian Splatting for high-fidelity novel view synthesis using about 20 times fewer initial 3D points. Project page: \url{https://xuenan.net/neat}.

Xianpeng Liu, Ce Zheng, Kelvin Cheng et al.

The main challenge of monocular 3D object detection is the accurate localization of 3D center. Motivated by a new and strong observation that this challenge can be remedied by a 3D-space local-grid search scheme in an ideal case, we propose a stage-wise approach, which combines the information flow from 2D-to-3D (3D bounding box proposal generation with a single 2D image) and 3D-to-2D (proposal verification by denoising with 3D-to-2D contexts) in a top-down manner. Specifically, we first obtain initial proposals from off-the-shelf backbone monocular 3D detectors. Then, we generate a 3D anchor space by local-grid sampling from the initial proposals. Finally, we perform 3D bounding box denoising at the 3D-to-2D proposal verification stage. To effectively learn discriminative features for denoising highly overlapped proposals, this paper presents a method of using the Perceiver I/O model to fuse the 3D-to-2D geometric information and the 2D appearance information. With the encoded latent representation of a proposal, the verification head is implemented with a self-attention module. Our method, named as MonoXiver, is generic and can be easily adapted to any backbone monocular 3D detectors. Experimental results on the well-established KITTI dataset and the challenging large-scale Waymo dataset show that MonoXiver consistently achieves improvement with limited computation overhead.

Bo Jiang, Hamid Krim, Tianfu Wu et al.

The power and flexibility of Optimal Transport (OT) have pervaded a wide spectrum of problems, including recent Machine Learning challenges such as unsupervised domain adaptation. Its essence of quantitatively relating two probability distributions by some optimal metric, has been creatively exploited and shown to hold promise for many real-world data challenges. In a related theme in the present work, we posit that domain adaptation robustness is rooted in the intrinsic (latent) representations of the respective data, which are inherently lying in a non-linear submanifold embedded in a higher dimensional Euclidean space. We account for the geometric properties by refining the $l^2$ Euclidean metric to better reflect the geodesic distance between two distinct representations. We integrate a metric correction term as well as a prior cluster structure in the source data of the OT-driven adaptation. We show that this is tantamount to an implicit Bayesian framework, which we demonstrate to be viable for a more robust and better-performing approach to domain adaptation. Substantiating experiments are also included for validation purposes.

Chinmay Savadikar, Michelle Dai, Tianfu Wu

This paper studies task-incremental continual learning (TCL) using Vision Transformers (ViTs). Our goal is to improve the overall streaming-task performance without catastrophic forgetting by learning task synergies (e.g., a new task learns to automatically reuse/adapt modules from previous similar tasks, or to introduce new modules when needed, or to skip some modules when it appears to be an easier task). One grand challenge is how to tame ViTs at streaming diverse tasks in terms of balancing their plasticity and stability in a task-aware way while overcoming the catastrophic forgetting. To address the challenge, we propose a simple yet effective approach that identifies a lightweight yet expressive ``sweet spot'' in the ViT block as the task-synergy memory in TCL. We present a Hierarchical task-synergy Exploration-Exploitation (HEE) sampling based neural architecture search (NAS) method for effectively learning task synergies by structurally updating the identified memory component with respect to four basic operations (reuse, adapt, new and skip) at streaming tasks. The proposed method is thus dubbed as CHEEM (Continual Hierarchical-Exploration-Exploitation Memory). In experiments, we test the proposed CHEEM on the challenging Visual Domain Decathlon (VDD) benchmark and the 5-Dataset benchmark. It obtains consistently better performance than the prior art with sensible CHEEM learned continually.

Zeran Ke, Bin Tan, Xianwei Zheng et al.

This paper studies the problem of Line Segment Detection (LSD) for the characterization of line geometry in images, with the aim of learning a domain-agnostic robust LSD model that works well for any natural images. With the focus of scalable self-supervised learning of LSD, we revisit and streamline the fundamental designs of (deep and non-deep) LSD approaches to have a high-performing and efficient LSD learner, dubbed as ScaleLSD, for the curation of line geometry at scale from over 10M unlabeled real-world images. Our ScaleLSD works very well to detect much more number of line segments from any natural images even than the pioneered non-deep LSD approach, having a more complete and accurate geometric characterization of images using line segments. Experimentally, our proposed ScaleLSD is comprehensively testified under zero-shot protocols in detection performance, single-view 3D geometry estimation, two-view line segment matching, and multiview 3D line mapping, all with excellent performance obtained. Based on the thorough evaluation, our ScaleLSD is observed to be the first deep approach that outperforms the pioneered non-deep LSD in all aspects we have tested, significantly expanding and reinforcing the versatility of the line geometry of images. Code and Models are available at https://github.com/ant-research/scalelsd

Wei Sun, Tianfu Wu

Despite remarkable recent progress on both unconditional and conditional image synthesis, it remains a long-standing problem to learn generative models that are capable of synthesizing realistic and sharp images from reconfigurable spatial layout (i.e., bounding boxes + class labels in an image lattice) and style (i.e., structural and appearance variations encoded by latent vectors), especially at high resolution. By reconfigurable, it means that a model can preserve the intrinsic one-to-many mapping from a given layout to multiple plausible images with different styles, and is adaptive with respect to perturbations of a layout and style latent code. In this paper, we present a layout- and style-based architecture for generative adversarial networks (termed LostGANs) that can be trained end-to-end to generate images from reconfigurable layout and style. Inspired by the vanilla StyleGAN, the proposed LostGAN consists of two new components: (i) learning fine-grained mask maps in a weakly-supervised manner to bridge the gap between layouts and images, and (ii) learning object instance-specific layout-aware feature normalization (ISLA-Norm) in the generator to realize multi-object style generation. In experiments, the proposed method is tested on the COCO-Stuff dataset and the Visual Genome dataset with state-of-the-art performance obtained. The code and pretrained models are available at \url{https://github.com/iVMCL/LostGANs}.

Xilai Li, Wei Sun, Tianfu Wu

In state-of-the-art deep neural networks, both feature normalization and feature attention have become ubiquitous. % with significant performance improvement shown in a vast amount of tasks. They are usually studied as separate modules, however. In this paper, we propose a light-weight integration between the two schema and present Attentive Normalization (AN). Instead of learning a single affine transformation, AN learns a mixture of affine transformations and utilizes their weighted-sum as the final affine transformation applied to re-calibrate features in an instance-specific way. The weights are learned by leveraging channel-wise feature attention. In experiments, we test the proposed AN using four representative neural architectures in the ImageNet-1000 classification benchmark and the MS-COCO 2017 object detection and instance segmentation benchmark. AN obtains consistent performance improvement for different neural architectures in both benchmarks with absolute increase of top-1 accuracy in ImageNet-1000 between 0.5\% and 2.7\%, and absolute increase up to 1.8\% and 2.2\% for bounding box and mask AP in MS-COCO respectively. We observe that the proposed AN provides a strong alternative to the widely used Squeeze-and-Excitation (SE) module. The source codes are publicly available at https://github.com/iVMCL/AOGNet-v2 (the ImageNet Classification Repo) and https://github.com/iVMCL/AttentiveNorm\_Detection (the MS-COCO Detection and Segmentation Repo).

Xianpeng Liu, Ce Zheng, Ming Qian et al.

We present Multi-View Attentive Contextualization (MvACon), a simple yet effective method for improving 2D-to-3D feature lifting in query-based multi-view 3D (MV3D) object detection. Despite remarkable progress witnessed in the field of query-based MV3D object detection, prior art often suffers from either the lack of exploiting high-resolution 2D features in dense attention-based lifting, due to high computational costs, or from insufficiently dense grounding of 3D queries to multi-scale 2D features in sparse attention-based lifting. Our proposed MvACon hits the two birds with one stone using a representationally dense yet computationally sparse attentive feature contextualization scheme that is agnostic to specific 2D-to-3D feature lifting approaches. In experiments, the proposed MvACon is thoroughly tested on the nuScenes benchmark, using both the BEVFormer and its recent 3D deformable attention (DFA3D) variant, as well as the PETR, showing consistent detection performance improvement, especially in enhancing performance in location, orientation, and velocity prediction. It is also tested on the Waymo-mini benchmark using BEVFormer with similar improvement. We qualitatively and quantitatively show that global cluster-based contexts effectively encode dense scene-level contexts for MV3D object detection. The promising results of our proposed MvACon reinforces the adage in computer vision -- ``(contextualized) feature matters".

Rui Xue, Shichao Zhu, Liang Qin et al.

Graph Neural Networks (GNNs) have emerged as powerful tools for modeling graph-structured data and have been widely used in recommender systems, such as for capturing complex user-item and item-item relations. However, most industrial deployments adopt a two-stage pipeline: GNNs are first pre-trained offline to generate node embeddings, which are then used as static features for downstream recommender systems. This decoupled paradigm leads to two key limitations: (1) high computational overhead, since large-scale GNN inference must be repeatedly executed to refresh embeddings; and (2) lack of joint optimization, as the gradient from the recommender system cannot directly influence the GNN learning process, causing the GNN to be suboptimally informative for the recommendation task. In this paper, we propose E2E-GRec, a novel end-to-end training framework that unifies GNN training with the recommender system. Our framework is characterized by three key components: (i) efficient subgraph sampling from a large-scale cross-domain heterogeneous graph to ensure training scalability and efficiency; (ii) a Graph Feature Auto-Encoder (GFAE) serving as an auxiliary self-supervised task to guide the GNN to learn structurally meaningful embeddings; and (iii) a two-level feature fusion mechanism combined with Gradnorm-based dynamic loss balancing, which stabilizes graph-aware multi-task end-to-end training. Extensive offline evaluations, online A/B tests (e.g., a +0.133% relative improvement in stay duration, a 0.3171% reduction in the average number of videos a user skips) on large-scale production data, together with theoretical analysis, demonstrate that E2E-GRec consistently surpasses traditional approaches, yielding significant gains across multiple recommendation metrics.

Rui Xue, Tianfu Wu

Graph Neural Networks (GNNs) struggle to balance heterophily and homophily in representation learning, a challenge further amplified in self-supervised settings. We propose H$^3$GNNs, an end-to-end self-supervised learning framework that harmonizes both structural properties through two key innovations: (i) Joint Structural Node Encoding. We embed nodes into a unified space combining linear and non-linear feature projections with K-hop structural representations via a Weighted Graph Convolution Network(WGCN). A cross-attention mechanism enhances awareness and adaptability to heterophily and homophily. (ii) Self-Supervised Learning Using Teacher-Student Predictive Architectures with Node-Difficulty Driven Dynamic Masking Strategies. We use a teacher-student model, the student sees the masked input graph and predicts node features inferred by the teacher that sees the full input graph in the joint encoding space. To enhance learning difficulty, we introduce two novel node-predictive-difficulty-based masking strategies. Experiments on seven benchmarks (four heterophily datasets and three homophily datasets) confirm the effectiveness and efficiency of H$^3$GNNs across diverse graph types. Our H$^3$GNNs achieves overall state-of-the-art performance on the four heterophily datasets, while retaining on-par performance to previous state-of-the-art methods on the three homophily datasets.

Thomas Paniagua, Ryan Grainger, Tianfu Wu

The adversarial vulnerability of Deep Neural Networks (DNNs) has been well-known and widely concerned, often under the context of learning top-$1$ attacks (e.g., fooling a DNN to classify a cat image as dog). This paper shows that the concern is much more serious by learning significantly more aggressive ordered top-$K$ clear-box~\footnote{ This is often referred to as white/black-box attacks in the literature. We choose to adopt neutral terminology, clear/opaque-box attacks in this paper, and omit the prefix clear-box for simplicity.} targeted attacks proposed in Adversarial Distillation. We propose a novel and rigorous quadratic programming (QP) method of learning ordered top-$K$ attacks with low computing cost, dubbed as \textbf{QuadAttac$K$}. Our QuadAttac$K$ directly solves the QP to satisfy the attack constraint in the feature embedding space (i.e., the input space to the final linear classifier), which thus exploits the semantics of the feature embedding space (i.e., the principle of class coherence). With the optimized feature embedding vector perturbation, it then computes the adversarial perturbation in the data space via the vanilla one-step back-propagation. In experiments, the proposed QuadAttac$K$ is tested in the ImageNet-1k classification using ResNet-50, DenseNet-121, and Vision Transformers (ViT-B and DEiT-S). It successfully pushes the boundary of successful ordered top-$K$ attacks from $K=10$ up to $K=20$ at a cheap budget ($1\times 60$) and further improves attack success rates for $K=5$ for all tested models, while retaining the performance for $K=1$.

Bo Jiang, Hamid Krim, Tianfu Wu et al.

We introduce in this paper a new statistical perspective, exploiting the Jaccard similarity metric, as a measure-based metric to effectively invoke non-linear features in the loss of self-supervised contrastive learning. Specifically, our proposed metric may be interpreted as a dependence measure between two adapted projections learned from the so-called latent representations. This is in contrast to the cosine similarity measure in the conventional contrastive learning model, which accounts for correlation information. To the best of our knowledge, this effectively non-linearly fused information embedded in the Jaccard similarity, is novel to self-supervision learning with promising results. The proposed approach is compared to two state-of-the-art self-supervised contrastive learning methods on three image datasets. We not only demonstrate its amenable applicability in current ML problems, but also its improved performance and training efficiency.

Jianghao Shen, Tianfu Wu

Learning light-weight yet expressive deep networks in both image synthesis and image recognition remains a challenging problem. Inspired by a more recent observation that it is the data-specificity that makes the multi-head self-attention (MHSA) in the Transformer model so powerful, this paper proposes to extend the widely adopted light-weight Squeeze-Excitation (SE) module to be spatially-adaptive to reinforce its data specificity, as a convolutional alternative of the MHSA, while retaining the efficiency of SE and the inductive basis of convolution. It presents two designs of spatially-adaptive squeeze-excitation (SASE) modules for image synthesis and image recognition respectively. For image synthesis tasks, the proposed SASE is tested in both low-shot and one-shot learning tasks. It shows better performance than prior arts. For image recognition tasks, the proposed SASE is used as a drop-in replacement for convolution layers in ResNets and achieves much better accuracy than the vanilla ResNets, and slightly better than the MHSA counterparts such as the Swin-Transformer and Pyramid-Transformer in the ImageNet-1000 dataset, with significantly smaller models.

Xianpeng Liu, Nan Xue, Tianfu Wu

Monocular 3D object detection aims to localize 3D bounding boxes in an input single 2D image. It is a highly challenging problem and remains open, especially when no extra information (e.g., depth, lidar and/or multi-frames) can be leveraged in training and/or inference. This paper proposes a simple yet effective formulation for monocular 3D object detection without exploiting any extra information. It presents the MonoCon method which learns Monocular Contexts, as auxiliary tasks in training, to help monocular 3D object detection. The key idea is that with the annotated 3D bounding boxes of objects in an image, there is a rich set of well-posed projected 2D supervision signals available in training, such as the projected corner keypoints and their associated offset vectors with respect to the center of 2D bounding box, which should be exploited as auxiliary tasks in training. The proposed MonoCon is motivated by the Cramer-Wold theorem in measure theory at a high level. In implementation, it utilizes a very simple end-to-end design to justify the effectiveness of learning auxiliary monocular contexts, which consists of three components: a Deep Neural Network (DNN) based feature backbone, a number of regression head branches for learning the essential parameters used in the 3D bounding box prediction, and a number of regression head branches for learning auxiliary contexts. After training, the auxiliary context regression branches are discarded for better inference efficiency. In experiments, the proposed MonoCon is tested in the KITTI benchmark (car, pedestrain and cyclist). It outperforms all prior arts in the leaderboard on car category and obtains comparable performance on pedestrian and cyclist in terms of accuracy. Thanks to the simple design, the proposed MonoCon method obtains the fastest inference speed with 38.7 fps in comparisons

Nan Xue, Tianfu Wu, Gui-Song Xia et al.

This paper studies the problem of multi-person pose estimation in a bottom-up fashion. With a new and strong observation that the localization issue of the center-offset formulation can be remedied in a local-window search scheme in an ideal situation, we propose a multi-person pose estimation approach, dubbed as LOGO-CAP, by learning the LOcal-GlObal Contextual Adaptation for human Pose. Specifically, our approach learns the keypoint attraction maps (KAMs) from the local keypoints expansion maps (KEMs) in small local windows in the first step, which are subsequently treated as dynamic convolutional kernels on the keypoints-focused global heatmaps for contextual adaptation, achieving accurate multi-person pose estimation. Our method is end-to-end trainable with near real-time inference speed in a single forward pass, obtaining state-of-the-art performance on the COCO keypoint benchmark for bottom-up human pose estimation. With the COCO trained model, our method also outperforms prior arts by a large margin on the challenging OCHuman dataset.

Kelvin Cheng, Christopher Healey, Tianfu Wu

Stereo matching has recently witnessed remarkable progress using Deep Neural Networks (DNNs). But, how robust are they? Although it has been well-known that DNNs often suffer from adversarial vulnerability with a catastrophic drop in performance, the situation is even worse in stereo matching. This paper first shows that a type of weak white-box attacks can overwhelm state-of-the-art methods. The attack is learned by a proposed stereo-constrained projected gradient descent (PGD) method in stereo matching. This observation raises serious concerns for the deployment of DNN-based stereo matching. Parallel to the adversarial vulnerability, DNN-based stereo matching is typically trained under the so-called simulation to reality pipeline, and thus domain generalizability is an important problem. This paper proposes to rethink the learnable DNN-based feature backbone towards adversarially-robust and domain generalizable stereo matching by completely removing it for matching. In experiments, the proposed method is tested in the SceneFlow dataset and the KITTI2015 benchmark, with promising results. We compute the matching cost volume using the classic multi-scale census transform (i.e., local binary pattern) of the raw input stereo images, followed by a stacked Hourglass head sub-network solving the matching problem. It significantly improves the adversarial robustness, while retaining accuracy performance comparable to state-of-the-art methods. It also shows better generalizability from simulation (SceneFlow) to real (KITTI) datasets when no fine-tuning is used.

Bin Tan, Nan Xue, Song Bai et al.

This paper presents a neural network built upon Transformers, namely PlaneTR, to simultaneously detect and reconstruct planes from a single image. Different from previous methods, PlaneTR jointly leverages the context information and the geometric structures in a sequence-to-sequence way to holistically detect plane instances in one forward pass. Specifically, we represent the geometric structures as line segments and conduct the network with three main components: (i) context and line segments encoders, (ii) a structure-guided plane decoder, (iii) a pixel-wise plane embedding decoder. Given an image and its detected line segments, PlaneTR generates the context and line segment sequences via two specially designed encoders and then feeds them into a Transformers-based decoder to directly predict a sequence of plane instances by simultaneously considering the context and global structure cues. Finally, the pixel-wise embeddings are computed to assign each pixel to one predicted plane instance which is nearest to it in embedding space. Comprehensive experiments demonstrate that PlaneTR achieves a state-of-the-art performance on the ScanNet and NYUv2 datasets.

Wei Sun, Tianfu Wu

Both generative learning and discriminative learning have recently witnessed remarkable progress using Deep Neural Networks (DNNs). For structured input synthesis and structured output prediction problems (e.g., layout-to-image synthesis and image semantic segmentation respectively), they often are studied separately. This paper proposes deep consensus learning (DCL) for joint layout-to-image synthesis and weakly-supervised image semantic segmentation. The former is realized by a recently proposed LostGAN approach, and the latter by introducing an inference network as the third player joining the two-player game of LostGAN. Two deep consensus mappings are exploited to facilitate training the three networks end-to-end: Given an input layout (a list of object bounding boxes), the generator generates a mask (label map) and then use it to help synthesize an image. The inference network infers the mask for the synthesized image. Then, the latent consensus is measured between the mask generated by the generator and the one inferred by the inference network. For the real image corresponding to the input layout, its mask also is computed by the inference network, and then used by the generator to reconstruct the real image. Then, the data consensus is measured between the real image and its reconstructed image. The discriminator still plays the role of an adversary by computing the realness scores for a real image, its reconstructed image and a synthesized image. In experiments, our DCL is tested in the COCO-Stuff dataset. It obtains compelling layout-to-image synthesis results and weakly-supervised image semantic segmentation results.

Zexi Chen, Benjamin Dutton, Bharathkumar Ramachandra et al.

The Mean Teacher (MT) model of Tarvainen and Valpola has shown favorable performance on several semi-supervised benchmark datasets. MT maintains a teacher model's weights as the exponential moving average of a student model's weights and minimizes the divergence between their probability predictions under diverse perturbations of the inputs. However, MT is known to suffer from confirmation bias, that is, reinforcing incorrect teacher model predictions. In this work, we propose a simple yet effective method called Local Clustering (LC) to mitigate the effect of confirmation bias. In MT, each data point is considered independent of other points during training; however, data points are likely to be close to each other in feature space if they share similar features. Motivated by this, we cluster data points locally by minimizing the pairwise distance between neighboring data points in feature space. Combined with a standard classification cross-entropy objective on labeled data points, the misclassified unlabeled data points are pulled towards high-density regions of their correct class with the help of their neighbors, thus improving model performance. We demonstrate on semi-supervised benchmark datasets SVHN and CIFAR-10 that adding our LC loss to MT yields significant improvements compared to MT and performance comparable to the state of the art in semi-supervised learning.

Wei Sun, Tianfu Wu

With the remarkable recent progress on learning deep generative models, it becomes increasingly interesting to develop models for controllable image synthesis from reconfigurable inputs. This paper focuses on a recent emerged task, layout-to-image, to learn generative models that are capable of synthesizing photo-realistic images from spatial layout (i.e., object bounding boxes configured in an image lattice) and style (i.e., structural and appearance variations encoded by latent vectors). This paper first proposes an intuitive paradigm for the task, layout-to-mask-to-image, to learn to unfold object masks of given bounding boxes in an input layout to bridge the gap between the input layout and synthesized images. Then, this paper presents a method built on Generative Adversarial Networks for the proposed layout-to-mask-to-image with style control at both image and mask levels. Object masks are learned from the input layout and iteratively refined along stages in the generator network. Style control at the image level is the same as in vanilla GANs, while style control at the object mask level is realized by a proposed novel feature normalization scheme, Instance-Sensitive and Layout-Aware Normalization. In experiments, the proposed method is tested in the COCO-Stuff dataset and the Visual Genome dataset with state-of-the-art performance obtained.

Nan Xue, Tianfu Wu, Song Bai et al.

This paper presents a fast and parsimonious parsing method to accurately and robustly detect a vectorized wireframe in an input image with a single forward pass. The proposed method is end-to-end trainable, consisting of three components: (i) line segment and junction proposal generation, (ii) line segment and junction matching, and (iii) line segment and junction verification. For computing line segment proposals, a novel exact dual representation is proposed which exploits a parsimonious geometric reparameterization for line segments and forms a holistic 4-dimensional attraction field map for an input image. Junctions can be treated as the "basins" in the attraction field. The proposed method is thus called Holistically-Attracted Wireframe Parser (HAWP). In experiments, the proposed method is tested on two benchmarks, the Wireframe dataset, and the YorkUrban dataset. On both benchmarks, it obtains state-of-the-art performance in terms of accuracy and efficiency. For example, on the Wireframe dataset, compared to the previous state-of-the-art method L-CNN, it improves the challenging mean structural average precision (msAP) by a large margin ($2.8\%$ absolute improvements) and achieves 29.5 FPS on single GPU ($89\%$ relative improvement). A systematic ablation study is performed to further justify the proposed method.

Richeng Jin, Yufan Huang, Xiaofan He et al.

Federated learning (FL) has emerged as a prominent distributed learning paradigm. FL entails some pressing needs for developing novel parameter estimation approaches with theoretical guarantees of convergence, which are also communication efficient, differentially private and Byzantine resilient in the heterogeneous data distribution settings. Quantization-based SGD solvers have been widely adopted in FL and the recently proposed SIGNSGD with majority vote shows a promising direction. However, no existing methods enjoy all the aforementioned properties. In this paper, we propose an intuitively-simple yet theoretically-sound method based on SIGNSGD to bridge the gap. We present Stochastic-Sign SGD which utilizes novel stochastic-sign based gradient compressors enabling the aforementioned properties in a unified framework. We also present an error-feedback variant of the proposed Stochastic-Sign SGD which further improves the learning performance in FL. We test the proposed method with extensive experiments using deep neural networks on the MNIST dataset and the CIFAR-10 dataset. The experimental results corroborate the effectiveness of the proposed method.

Nan Xue, Song Bai, Fu-Dong Wang et al.

This paper presents regional attraction of line segment maps, and hereby poses the problem of line segment detection (LSD) as a problem of region coloring. Given a line segment map, the proposed regional attraction first establishes the relationship between line segments and regions in the image lattice. Based on this, the line segment map is equivalently transformed to an attraction field map (AFM), which can be remapped to a set of line segments without loss of information. Accordingly, we develop an end-to-end framework to learn attraction field maps for raw input images, followed by a squeeze module to detect line segments. Apart from existing works, the proposed detector properly handles the local ambiguity and does not rely on the accurate identification of edge pixels. Comprehensive experiments on the Wireframe dataset and the YorkUrban dataset demonstrate the superiority of our method. In particular, we achieve an F-measure of 0.831 on the Wireframe dataset, advancing the state-of-the-art performance by 10.3 percent.

Xianglei Xing, Tianfu Wu, Song-Chun Zhu et al.

This paper proposes to learn hierarchical compositional AND-OR model for interpretable image synthesis by sparsifying the generator network. The proposed method adopts the scene-objects-parts-subparts-primitives hierarchy in image representation. A scene has different types (i.e., OR) each of which consists of a number of objects (i.e., AND). This can be recursively formulated across the scene-objects-parts-subparts hierarchy and is terminated at the primitive level (e.g., wavelets-like basis). To realize this AND-OR hierarchy in image synthesis, we learn a generator network that consists of the following two components: (i) Each layer of the hierarchy is represented by an over-complete set of convolutional basis functions. Off-the-shelf convolutional neural architectures are exploited to implement the hierarchy. (ii) Sparsity-inducing constraints are introduced in end-to-end training, which induces a sparsely activated and sparsely connected AND-OR model from the initially densely connected generator network. A straightforward sparsity-inducing constraint is utilized, that is to only allow the top-$k$ basis functions to be activated at each layer (where $k$ is a hyper-parameter). The learned basis functions are also capable of image reconstruction to explain the input images. In experiments, the proposed method is tested on four benchmark datasets. The results show that meaningful and interpretable hierarchical representations are learned with better qualities of image synthesis and reconstruction obtained than baselines.

Wei Sun, Jawadul H. Bappy, Shanglin Yang et al.

Generating a photorealistic image with intended human pose is a promising yet challenging research topic for many applications such as smart photo editing, movie making, virtual try-on, and fashion display. In this paper, we present a novel deep generative model to transfer an image of a person from a given pose to a new pose while keeping fashion item consistent. In order to formulate the framework, we employ one generator and two discriminators for image synthesis. The generator includes an image encoder, a pose encoder and a decoder. The two encoders provide good representation of visual and geometrical context which will be utilized by the decoder in order to generate a photorealistic image. Unlike existing pose-guided image generation models, we exploit two discriminators to guide the synthesis process where one discriminator differentiates between generated image and real images (training samples), and another discriminator verifies the consistency of appearance between a target pose and a generated image. We perform end-to-end training of the network to learn the parameters through back-propagation given ground-truth images. The proposed generative model is capable of synthesizing a photorealistic image of a person given a target pose. We have demonstrated our results by conducting rigorous experiments on two data sets, both quantitatively and qualitatively.

Zekun Zhang, Tianfu Wu

Deep Neural Networks (DNNs) are vulnerable to adversarial attacks, especially white-box targeted attacks. One scheme of learning attacks is to design a proper adversarial objective function that leads to the imperceptible perturbation for any test image (e.g., the Carlini-Wagner (C&W) method). Most methods address targeted attacks in the Top-1 manner. In this paper, we propose to learn ordered Top-k attacks (k>= 1) for image classification tasks, that is to enforce the Top-k predicted labels of an adversarial example to be the k (randomly) selected and ordered labels (the ground-truth label is exclusive). To this end, we present an adversarial distillation framework: First, we compute an adversarial probability distribution for any given ordered Top-k targeted labels with respect to the ground-truth of a test image. Then, we learn adversarial examples by minimizing the Kullback-Leibler (KL) divergence together with the perturbation energy penalty, similar in spirit to the network distillation method. We explore how to leverage label semantic similarities in computing the targeted distributions, leading to knowledge-oriented attacks. In experiments, we thoroughly test Top-1 and Top-5 attacks in the ImageNet-1000 validation dataset using two popular DNNs trained with clean ImageNet-1000 train dataset, ResNet-50 and DenseNet-121. For both models, our proposed adversarial distillation approach outperforms the C&W method in the Top-1 setting, as well as other baseline methods. Our approach shows significant improvement in the Top-5 setting against a strong modified C&W method.

Xilai Li, Yingbo Zhou, Tianfu Wu et al.

Addressing catastrophic forgetting is one of the key challenges in continual learning where machine learning systems are trained with sequential or streaming tasks. Despite recent remarkable progress in state-of-the-art deep learning, deep neural networks (DNNs) are still plagued with the catastrophic forgetting problem. This paper presents a conceptually simple yet general and effective framework for handling catastrophic forgetting in continual learning with DNNs. The proposed method consists of two components: a neural structure optimization component and a parameter learning and/or fine-tuning component. By separating the explicit neural structure learning and the parameter estimation, not only is the proposed method capable of evolving neural structures in an intuitively meaningful way, but also shows strong capabilities of alleviating catastrophic forgetting in experiments. Furthermore, the proposed method outperforms all other baselines on the permuted MNIST dataset, the split CIFAR100 dataset and the Visual Domain Decathlon dataset in continual learning setting.

Khashayar Asadi, Pengyu Chen, Kevin Han et al.

Camera-equipped unmanned vehicles (UVs) have received a lot of attention in data collection for construction monitoring applications. To develop an autonomous platform, the UV should be able to process multiple modules (e.g., context-awareness, control, localization, and mapping) on an embedded platform. Pixel-wise semantic segmentation provides a UV with the ability to be contextually aware of its surrounding environment. However, in the case of mobile robotic systems with limited computing resources, the large size of the segmentation model and high memory usage requires high computing resources, which a major challenge for mobile UVs (e.g., a small-scale vehicle with limited payload and space). To overcome this challenge, this paper presents a light and efficient deep neural network architecture to run on an embedded platform in real-time. The proposed model segments navigable space on an image sequence (i.e., a video stream), which is essential for an autonomous vehicle that is based on machine vision. The results demonstrate the performance efficiency of the proposed architecture compared to the existing models and suggest possible improvements that could make the model even more efficient, which is necessary for the future development of the autonomous robotics systems.

Wei Sun, Tianfu Wu

Image synthesis and image-to-image translation are two important generative learning tasks. Remarkable progress has been made by learning Generative Adversarial Networks (GANs)~\cite{goodfellow2014generative} and cycle-consistent GANs (CycleGANs)~\cite{zhu2017unpaired} respectively. This paper presents a method of learning Spatial Pyramid Attentive Pooling (SPAP) which is a novel architectural unit and can be easily integrated into both generators and discriminators in GANs and CycleGANs. The proposed SPAP integrates Atrous spatial pyramid~\cite{chen2018deeplab}, a proposed cascade attention mechanism and residual connections~\cite{he2016deep}. It leverages the advantages of the three components to facilitate effective end-to-end generative learning: (i) the capability of fusing multi-scale information by ASPP; (ii) the capability of capturing relative importance between both spatial locations (especially multi-scale context) or feature channels by attention; (iii) the capability of preserving information and enhancing optimization feasibility by residual connections. Coarse-to-fine and fine-to-coarse SPAP are studied and intriguing attention maps are observed in both tasks. In experiments, the proposed SPAP is tested in GANs on the Celeba-HQ-128 dataset~\cite{karras2017progressive}, and tested in CycleGANs on the Image-to-Image translation datasets including the Cityscape dataset~\cite{cordts2016cityscapes}, Facade and Aerial Maps dataset~\cite{zhu2017unpaired}, both obtaining better performance.

Bo Li, Caiming Xiong, Tianfu Wu et al.

Chinese traditional painting is one of the most historical artworks in the world. It is very popular in Eastern and Southeast Asia due to being aesthetically appealing. Compared with western artistic painting, it is usually more visually abstract and textureless. Recently, neural network based style transfer methods have shown promising and appealing results which are mainly focused on western painting. It remains a challenging problem to preserve abstraction in neural style transfer. In this paper, we present a Neural Abstract Style Transfer method for Chinese traditional painting. It learns to preserve abstraction and other style jointly end-to-end via a novel MXDoG-guided filter (Modified version of the eXtended Difference-of-Gaussians) and three fully differentiable loss terms. To the best of our knowledge, there is little work study on neural style transfer of Chinese traditional painting. To promote research on this direction, we collect a new dataset with diverse photo-realistic images and Chinese traditional paintings. In experiments, the proposed method shows more appealing stylized results in transferring the style of Chinese traditional painting than state-of-the-art neural style transfer methods.

Nan Xue, Song Bai, Fudong Wang et al.

This paper presents a region-partition based attraction field dual representation for line segment maps, and thus poses the problem of line segment detection (LSD) as the region coloring problem. The latter is then addressed by learning deep convolutional neural networks (ConvNets) for accuracy, robustness and efficiency. For a 2D line segment map, our dual representation consists of three components: (i) A region-partition map in which every pixel is assigned to one and only one line segment; (ii) An attraction field map in which every pixel in a partition region is encoded by its 2D projection vector w.r.t. the associated line segment; and (iii) A squeeze module which squashes the attraction field to a line segment map that almost perfectly recovers the input one. By leveraging the duality, we learn ConvNets to compute the attraction field maps for raw in-put images, followed by the squeeze module for LSD, in an end-to-end manner. Our method rigorously addresses several challenges in LSD such as local ambiguity and class imbalance. Our method also harnesses the best practices developed in ConvNets based semantic segmentation methods such as the encoder-decoder architecture and the a-trous convolution. In experiments, our method is tested on the WireFrame dataset and the YorkUrban dataset with state-of-the-art performance obtained. Especially, we advance the performance by 4.5 percents on the WireFrame dataset. Our method is also fast with 6.6~10.4 FPS, outperforming most of existing line segment detectors.

Zexi Chen, Bharathkumar Ramachandra, Tianfu Wu et al.

Spatial and temporal relationships, both short-range and long-range, between objects in videos, are key cues for recognizing actions. It is a challenging problem to model them jointly. In this paper, we first present a new variant of Long Short-Term Memory, namely Relational LSTM, to address the challenge of relation reasoning across space and time between objects. In our Relational LSTM module, we utilize a non-local operation similar in spirit to the recently proposed non-local network to substitute the fully connected operation in the vanilla LSTM. By doing this, our Relational LSTM is capable of capturing long and short-range spatio-temporal relations between objects in videos in a principled way. Then, we propose a two-branch neural architecture consisting of the Relational LSTM module as the non-local branch and a spatio-temporal pooling based local branch. The local branch is utilized for capturing local spatial appearance and/or short-term motion features. The two branches are concatenated to learn video-level features from snippet-level ones which are then used for classification. Experimental results on UCF-101 and HMDB-51 datasets show that our model achieves state-of-the-art results among LSTM-based methods, while obtaining comparable performance with other state-of-the-art methods (which use not directly comparable schema). Further, on the more complex large-scale Charades dataset, we obtain a large 3.2% gain over state-of-the-art methods, verifying the effectiveness of our method in complex understanding.

Sameera Lanka, Tianfu Wu

Experience replay is an important technique for addressing sample-inefficiency in deep reinforcement learning (RL), but faces difficulty in learning from binary and sparse rewards due to disproportionately few successful experiences in the replay buffer. Hindsight experience replay (HER) was recently proposed to tackle this difficulty by manipulating unsuccessful transitions, but in doing so, HER introduces a significant bias in the replay buffer experiences and therefore achieves a suboptimal improvement in sample-efficiency. In this paper, we present an analysis on the source of bias in HER, and propose a simple and effective method to counter the bias, to most effectively harness the sample-efficiency provided by HER. Our method, motivated by counter-factual reasoning and called ARCHER, extends HER with a trade-off to make rewards calculated for hindsight experiences numerically greater than real rewards. We validate our algorithm on two continuous control environments from DeepMind Control Suite - Reacher and Finger, which simulate manipulation tasks with a robotic arm - in combination with various reward functions, task complexities and goal sampling strategies. Our experiments consistently demonstrate that countering bias using more aggressive hindsight rewards increases sample efficiency, thus establishing the greater benefit of ARCHER in RL applications with limited computing budget.

Bo Li, Tianfu Wu, Lun Zhang et al.

Region-based convolutional neural networks (R-CNN)~\cite{fast_rcnn,faster_rcnn,mask_rcnn} have largely dominated object detection. Operators defined on RoIs (Region of Interests) play an important role in R-CNNs such as RoIPooling~\cite{fast_rcnn} and RoIAlign~\cite{mask_rcnn}. They all only utilize information inside RoIs for RoI prediction, even with their recent deformable extensions~\cite{deformable_cnn}. Although surrounding context is well-known for its importance in object detection, it has yet been integrated in R-CNNs in a flexible and effective way. Inspired by the auto-context work~\cite{auto_context} and the multi-class object layout work~\cite{nms_context}, this paper presents a generic context-mining RoI operator (i.e., \textit{RoICtxMining}) seamlessly integrated in R-CNNs, and the resulting object detection system is termed \textbf{Auto-Context R-CNN} which is trained end-to-end. The proposed RoICtxMining operator is a simple yet effective two-layer extension of the RoIPooling or RoIAlign operator. Centered at an object-RoI, it creates a $3\times 3$ layout to mine contextual information adaptively in the $8$ surrounding context regions on-the-fly. Within each of the $8$ context regions, a context-RoI is mined in term of discriminative power and its RoIPooling / RoIAlign features are concatenated with the object-RoI for final prediction. \textit{The proposed Auto-Context R-CNN is robust to occlusion and small objects, and shows promising vulnerability for adversarial attacks without being adversarially-trained.} In experiments, it is evaluated using RoIPooling as the backbone and shows competitive results on Pascal VOC, Microsoft COCO, and KITTI datasets (including $6.9\%$ mAP improvements over the R-FCN~\cite{rfcn} method on COCO \textit{test-dev} dataset and the first place on both KITTI pedestrian and cyclist detection as of this submission).

Khashayar Asadi, Hariharan Ramshankar, Harish Pullagurla et al.

One of the major challenges of a real-time autonomous robotic system for construction monitoring is to simultaneously localize, map, and navigate over the lifetime of the robot, with little or no human intervention. Past research on Simultaneous Localization and Mapping (SLAM) and context-awareness are two active research areas in the computer vision and robotics communities. The studies that integrate both in real-time into a single modular framework for construction monitoring still need further investigation. A monocular vision system and real-time scene understanding are computationally heavy and the major state-of-the-art algorithms are tested on high-end desktops and/or servers with a high CPU- and/or GPU- computing capabilities, which affect their mobility and deployment for real-world applications. To address these challenges and achieve automation, this paper proposes an integrated robotic computer vision system, which generates a real-world spatial map of the obstacles and traversable space present in the environment in near real-time. This is done by integrating contextual Awareness and visual SLAM into a ground robotics agent. This paper presents the hardware utilization and performance of the aforementioned system for three different outdoor environments, which represent the applicability of this pipeline to diverse outdoor scenes in near real-time. The entire system is also self-contained and does not require user input, which demonstrates the potential of this computer vision system for autonomous navigation.

Zeyuan Chen, Shaoliang Nie, Tianfu Wu et al.

We present a deep learning approach for high resolution face completion with multiple controllable attributes (e.g., male and smiling) under arbitrary masks. Face completion entails understanding both structural meaningfulness and appearance consistency locally and globally to fill in "holes" whose content do not appear elsewhere in an input image. It is a challenging task with the difficulty level increasing significantly with respect to high resolution, the complexity of "holes" and the controllable attributes of filled-in fragments. Our system addresses the challenges by learning a fully end-to-end framework that trains generative adversarial networks (GANs) progressively from low resolution to high resolution with conditional vectors encoding controllable attributes. We design novel network architectures to exploit information across multiple scales effectively and efficiently. We introduce new loss functions encouraging sharp completion. We show that our system can complete faces with large structural and appearance variations using a single feed-forward pass of computation with mean inference time of 0.007 seconds for images at 1024 x 1024 resolution. We also perform a pilot human study that shows our approach outperforms state-of-the-art face completion methods in terms of rank analysis. The code will be released upon publication.

Xilai Li, Xi Song, Tianfu Wu

Neural architectures are the foundation for improving performance of deep neural networks (DNNs). This paper presents deep compositional grammatical architectures which harness the best of two worlds: grammar models and DNNs. The proposed architectures integrate compositionality and reconfigurability of the former and the capability of learning rich features of the latter in a principled way. We utilize AND-OR Grammar (AOG) as network generator in this paper and call the resulting networks AOGNets. An AOGNet consists of a number of stages each of which is composed of a number of AOG building blocks. An AOG building block splits its input feature map into N groups along feature channels and then treat it as a sentence of N words. It then jointly realizes a phrase structure grammar and a dependency grammar in bottom-up parsing the "sentence" for better feature exploration and reuse. It provides a unified framework for the best practices developed in state-of-the-art DNNs. In experiments, AOGNet is tested in the CIFAR-10, CIFAR-100 and ImageNet-1K classification benchmark and the MS-COCO object detection and segmentation benchmark. In CIFAR-10, CIFAR-100 and ImageNet-1K, AOGNet obtains better performance than ResNet and most of its variants, ResNeXt and its attention based variants such as SENet, DenseNet and DualPathNet. AOGNet also obtains the best model interpretability score using network dissection. AOGNet further shows better potential in adversarial defense. In MS-COCO, AOGNet obtains better performance than the ResNet and ResNeXt backbones in Mask R-CNN.

Tianfu Wu, Wei Sun, Xilai Li et al.

This paper first proposes a method of formulating model interpretability in visual understanding tasks based on the idea of unfolding latent structures. It then presents a case study in object detection using popular two-stage region-based convolutional network (i.e., R-CNN) detection systems. We focus on weakly-supervised extractive rationale generation, that is learning to unfold latent discriminative part configurations of object instances automatically and simultaneously in detection without using any supervision for part configurations. We utilize a top-down hierarchical and compositional grammar model embedded in a directed acyclic AND-OR Graph (AOG) to explore and unfold the space of latent part configurations of regions of interest (RoIs). We propose an AOGParsing operator to substitute the RoIPooling operator widely used in R-CNN. In detection, a bounding box is interpreted by the best parse tree derived from the AOG on-the-fly, which is treated as the qualitatively extractive rationale generated for interpreting detection. We propose a folding-unfolding method to train the AOG and convolutional networks end-to-end. In experiments, we build on R-FCN and test our method on the PASCAL VOC 2007 and 2012 datasets. We show that the method can unfold promising latent structures without hurting the performance.

Hang Qi, Yuanlu Xu, Tao Yuan et al.

Cross-view video understanding is an important yet under-explored area in computer vision. In this paper, we introduce a joint parsing framework that integrates view-centric proposals into scene-centric parse graphs that represent a coherent scene-centric understanding of cross-view scenes. Our key observations are that overlapping fields of views embed rich appearance and geometry correlations and that knowledge fragments corresponding to individual vision tasks are governed by consistency constraints available in commonsense knowledge. The proposed joint parsing framework represents such correlations and constraints explicitly and generates semantic scene-centric parse graphs. Quantitative experiments show that scene-centric predictions in the parse graph outperform view-centric predictions.

Diqi Chen, Yizhou Wang, Tianfu Wu et al.

In this paper, we present a novel method of no-reference image quality assessment (NR-IQA), which is to predict the perceptual quality score of a given image without using any reference image. The proposed method harnesses three functions (i) the visual attention mechanism, which affects many aspects of visual perception including image quality assessment, however, is overlooked in the NR-IQA literature. The method assumes that the fixation areas on an image contain key information to the process of IQA. (ii) the robust averaging strategy, which is a means \--- supported by psychology studies \--- to integrating multiple/step-wise evidence to make a final perceptual judgment. (iii) the multi-task learning, which is believed to be an effectual means to shape representation learning and could result in a more generalized model. To exploit the synergy of the three, we consider the NR-IQA as a dynamic perception process, in which the model samples a sequence of "informative" areas and aggregates the information to learn a representation for the tasks of jointly predicting the image quality score and the distortion type. The model learning is implemented by a reinforcement strategy, in which the rewards of both tasks guide the learning of the optimal sampling policy to acquire the "task-informative" image regions so that the predictions can be made accurately and efficiently (in terms of the sampling steps). The reinforcement learning is realized by a deep network with the policy gradient method and trained through back-propagation. In experiments, the model is tested on the TID2008 dataset and it outperforms several state-of-the-art methods. Furthermore, the model is very efficient in the sense that a small number of fixations are used in NR-IQA.

Bo Zhao, Botong Wu, Tianfu Wu et al.

This paper presents a method of zero-shot learning (ZSL) which poses ZSL as the missing data problem, rather than the missing label problem. Specifically, most existing ZSL methods focus on learning mapping functions from the image feature space to the label embedding space. Whereas, the proposed method explores a simple yet effective transductive framework in the reverse way \--- our method estimates data distribution of unseen classes in the image feature space by transferring knowledge from the label embedding space. In experiments, our method outperforms the state-of-the-art on two popular datasets.

Bo Li, Tianfu Wu, Shuai Shao et al.

Jointly integrating aspect ratio and context has been extensively studied and shown performance improvement in traditional object detection systems such as the DPMs. It, however, has been largely ignored in deep neural network based detection systems. This paper presents a method of integrating a mixture of object models and region-based convolutional networks for accurate object detection. Each mixture component accounts for both object aspect ratio and multi-scale contextual information explicitly: (i) it exploits a mixture of tiling configurations in the RoI pooling to remedy the warping artifacts caused by a single type RoI pooling (e.g., with equally-sized 7 x 7 cells), and to respect the underlying object shapes more; (ii) it "looks from both the inside and the outside of a RoI" by incorporating contextual information at two scales: global context pooled from the whole image and local context pooled from the surrounding of a RoI. To facilitate accurate detection, this paper proposes a multi-stage detection scheme for integrating the mixture of object models, which utilizes the detection results of the model at the previous stage as the proposals for the current in both training and testing. The proposed method is called the aspect ratio and context aware region-based convolutional network (ARC-R-CNN). In experiments, ARC-R-CNN shows very competitive results with Faster R-CNN [41] and R-FCN [10] on two datasets: the PASCAL VOC and the Microsoft COCO. It obtains significantly better mAP performance using high IoU thresholds on both datasets.

Yunzhu Li, Benyuan Sun, Tianfu Wu et al.

This paper presents a method for face detection in the wild, which integrates a ConvNet and a 3D mean face model in an end-to-end multi-task discriminative learning framework. The 3D mean face model is predefined and fixed (e.g., we used the one provided in the AFLW dataset). The ConvNet consists of two components: (i) The face pro- posal component computes face bounding box proposals via estimating facial key-points and the 3D transformation (rotation and translation) parameters for each predicted key-point w.r.t. the 3D mean face model. (ii) The face verification component computes detection results by prun- ing and refining proposals based on facial key-points based configuration pooling. The proposed method addresses two issues in adapting state- of-the-art generic object detection ConvNets (e.g., faster R-CNN) for face detection: (i) One is to eliminate the heuristic design of prede- fined anchor boxes in the region proposals network (RPN) by exploit- ing a 3D mean face model. (ii) The other is to replace the generic RoI (Region-of-Interest) pooling layer with a configuration pooling layer to respect underlying object structures. The multi-task loss consists of three terms: the classification Softmax loss and the location smooth l1 -losses [14] of both the facial key-points and the face bounding boxes. In ex- periments, our ConvNet is trained on the AFLW dataset only and tested on the FDDB benchmark with fine-tuning and on the AFW benchmark without fine-tuning. The proposed method obtains very competitive state-of-the-art performance in the two benchmarks.

Bo Li, Tianfu Wu, Caiming Xiong et al.

Physical fluents, a term originally used by Newton [40], refers to time-varying object states in dynamic scenes. In this paper, we are interested in inferring the fluents of vehicles from video. For example, a door (hood, trunk) is open or closed through various actions, light is blinking to turn. Recognizing these fluents has broad applications, yet have received scant attention in the computer vision literature. Car fluent recognition entails a unified framework for car detection, car part localization and part status recognition, which is made difficult by large structural and appearance variations, low resolutions and occlusions. This paper learns a spatial-temporal And-Or hierarchical model to represent car fluents. The learning of this model is formulated under the latent structural SVM framework. Since there are no publicly related dataset, we collect and annotate a car fluent dataset consisting of car videos with diverse fluents. In experiments, the proposed method outperforms several highly related baseline methods in terms of car fluent recognition and car part localization.

Hang Qi, Tianfu Wu, Mun-Wai Lee et al.

This paper presents a restricted visual Turing test (VTT) for story-line based deep understanding in long-term and multi-camera captured videos. Given a set of videos of a scene (such as a multi-room office, a garden, and a parking lot.) and a sequence of story-line based queries, the task is to provide answers either simply in binary form "true/false" (to a polar query) or in an accurate natural language description (to a non-polar query). Queries, polar or non-polar, consist of view-based queries which can be answered from a particular camera view and scene-centered queries which involves joint inference across different cameras. The story lines are collected to cover spatial, temporal and causal understanding of input videos. The data and queries distinguish our VTT from recently proposed visual question answering in images and video captioning. A vision system is proposed to perform joint video and query parsing which integrates different vision modules, a knowledge base and a query engine. The system provides unified interfaces for different modules so that individual modules can be reconfigured to test a new method. We provide a benchmark dataset and a toolkit for ontology guided story-line query generation which consists of about 93.5 hours videos captured in four different locations and 3,426 queries split into 127 story lines. We also provide a baseline implementation and result analyses.

Tianfu Wu, Yang Lu, Song-Chun Zhu

This paper presents a method, called AOGTracker, for simultaneously tracking, learning and parsing (TLP) of unknown objects in video sequences with a hierarchical and compositional And-Or graph (AOG) representation. %The AOG captures both structural and appearance variations of a target object in a principled way. The TLP method is formulated in the Bayesian framework with a spatial and a temporal dynamic programming (DP) algorithms inferring object bounding boxes on-the-fly. During online learning, the AOG is discriminatively learned using latent SVM to account for appearance (e.g., lighting and partial occlusion) and structural (e.g., different poses and viewpoints) variations of a tracked object, as well as distractors (e.g., similar objects) in background. Three key issues in online inference and learning are addressed: (i) maintaining purity of positive and negative examples collected online, (ii) controling model complexity in latent structure learning, and (iii) identifying critical moments to re-learn the structure of AOG based on its intrackability. The intrackability measures uncertainty of an AOG based on its score maps in a frame. In experiments, our AOGTracker is tested on two popular tracking benchmarks with the same parameter setting: the TB-100/50/CVPR2013 benchmarks, and the VOT benchmarks --- VOT 2013, 2014, 2015 and TIR2015 (thermal imagery tracking). In the former, our AOGTracker outperforms state-of-the-art tracking algorithms including two trackers based on deep convolutional network. In the latter, our AOGTracker outperforms all other trackers in VOT2013 and is comparable to the state-of-the-art methods in VOT2014, 2015 and TIR2015.