Chunhong Pan

Kun Ding, Ying Wang, Pengzhang Liu et al.

Vision-language models have recently shown great potential on many tasks in computer vision. Meanwhile, prior work demonstrates prompt tuning designed for vision-language models could acquire superior performance on few-shot image recognition compared to linear probe, a strong baseline. In practice, many few-shot tasks are inherently correlated, particularly within specialized domains. However, such information is overlooked previously. Inspired by the fact that modeling task relationship by multi-task learning can usually boost performance, we propose a novel method SoftCPT (Soft Context Sharing for Prompt Tuning) to tune pre-trained vision-language models on multiple target few-shot tasks jointly. Specifically, we design a task-shared meta network to generate prompt context for each task using task name together with a learnable task context as input. The parameters of this meta network as well as the task context are tuned on the joint training set of all tasks. As such, the prompt context of all tasks will be shared in a soft manner. Extensive experiments across four multi-task few-shot datasets covering 44 tasks and 1593 categories demonstrate that SoftCPT significantly outperforms single-task prompt tuning methods, highlighting the effectiveness of multi-task learning for vision-language prompt tuning. Code is available at https://github.com/kding1225/softcpt.

Tao Zhang, Yuyang Hong, Yang Xia et al.

Recent advances in multimodal large language models (MLLMs) have led to impressive progress across various benchmarks. However, their capability in understanding infrared images remains unexplored. To address this gap, we introduce IF-Bench, the first high-quality benchmark designed for evaluating multimodal understanding of infrared images. IF-Bench consists of 499 images sourced from 23 infrared datasets and 680 carefully curated visual question-answer pairs, covering 10 essential dimensions of image understanding. Based on this benchmark, we systematically evaluate over 40 open-source and closed-source MLLMs, employing cyclic evaluation, bilingual assessment, and hybrid judgment strategies to enhance the reliability of the results. Our analysis reveals how model scale, architecture, and inference paradigms affect infrared image comprehension, providing valuable insights for this area. Furthermore, we propose a training-free generative visual prompting (GenViP) method, which leverages advanced image editing models to translate infrared images into semantically and spatially aligned RGB counterparts, thereby mitigating domain distribution shifts. Extensive experiments demonstrate that our method consistently yields significant performance improvements across a wide range of MLLMs. The benchmark and code are available at https://github.com/casiatao/IF-Bench.

Xing Nie, Bolin Ni, Jianlong Chang et al.

In computer vision, fine-tuning is the de-facto approach to leverage pre-trained vision models to perform downstream tasks. However, deploying it in practice is quite challenging, due to adopting parameter inefficient global update and heavily relying on high-quality downstream data. Recently, prompt-based learning, which adds a task-relevant prompt to adapt the downstream tasks to pre-trained models, has drastically boosted the performance of many natural language downstream tasks. In this work, we extend this notable transfer ability benefited from prompt into vision models as an alternative to fine-tuning. To this end, we propose parameter-efficient Prompt tuning (Pro-tuning) to adapt frozen vision models to various downstream vision tasks. The key to Pro-tuning is prompt-based tuning, i.e., learning task-specific vision prompts for downstream input images with the pre-trained model frozen. By only training a few additional parameters, it can work on diverse CNN-based and Transformer-based architectures. Extensive experiments evidence that Pro-tuning outperforms fine-tuning in a broad range of vision tasks and scenarios, including image classification (generic objects, class imbalance, image corruption, adversarial robustness, and out-of-distribution generalization), and dense prediction tasks such as object detection and semantic segmentation.

Tao Zhang, Cheng Da, Kun Ding et al.

Preference optimization for diffusion models aims to align them with human preferences for images. Previous methods typically use Vision-Language Models (VLMs) as pixel-level reward models to approximate human preferences. However, when used for step-level preference optimization, these models face challenges in handling noisy images of different timesteps and require complex transformations into pixel space. In this work, we show that pre-trained diffusion models are naturally suited for step-level reward modeling in the noisy latent space, as they are explicitly designed to process latent images at various noise levels. Accordingly, we propose the Latent Reward Model (LRM), which repurposes components of the diffusion model to predict preferences of latent images at arbitrary timesteps. Building on LRM, we introduce Latent Preference Optimization (LPO), a step-level preference optimization method conducted directly in the noisy latent space. Experimental results indicate that LPO significantly improves the model's alignment with general, aesthetic, and text-image alignment preferences, while achieving a 2.5-28x training speedup over existing preference optimization methods. Our code and models are available at https://github.com/Kwai-Kolors/LPO.

Tao Zhang, Kun Ding, Jinyong Wen et al.

Self-supervised learning (SSL) for RGB images has achieved significant success, yet there is still limited research on SSL for infrared images, primarily due to three prominent challenges: 1) the lack of a suitable large-scale infrared pre-training dataset, 2) the distinctiveness of non-iconic infrared images rendering common pre-training tasks like masked image modeling (MIM) less effective, and 3) the scarcity of fine-grained textures making it particularly challenging to learn general image features. To address these issues, we construct a Multi-Scene Infrared Pre-training (MSIP) dataset comprising 178,756 images, and introduce object-sensitive random RoI cropping, an image preprocessing method, to tackle the challenge posed by non-iconic images. To alleviate the impact of weak textures on feature learning, we propose a pre-training paradigm called Pre-training with ADapter (PAD), which uses adapters to learn domain-specific features while freezing parameters pre-trained on ImageNet to retain the general feature extraction capability. This new paradigm is applicable to any transformer-based SSL method. Furthermore, to achieve more flexible coordination between pre-trained and newly-learned features in different layers and patches, a patchwise-scale adapter with dynamically learnable scale factors is introduced. Extensive experiments on three downstream tasks show that PAD, with only 1.23M pre-trainable parameters, outperforms other baseline paradigms including continual full pre-training on MSIP. Our code and dataset are available at https://github.com/casiatao/PAD.

Tao Zhang, Jinyong Wen, Zhen Chen et al.

Pre-training techniques significantly enhance the performance of semantic segmentation tasks with limited training data. However, the efficacy under a large domain gap between pre-training (e.g. RGB) and fine-tuning (e.g. infrared) remains underexplored. In this study, we first benchmark the infrared semantic segmentation performance of various pre-training methods and reveal several phenomena distinct from the RGB domain. Next, our layerwise analysis of pre-trained attention maps uncovers that: (1) There are three typical attention patterns (local, hybrid, and global); (2) Pre-training tasks notably influence the pattern distribution across layers; (3) The hybrid pattern is crucial for semantic segmentation as it attends to both nearby and foreground elements; (4) The texture bias impedes model generalization in infrared tasks. Building on these insights, we propose UNIP, a UNified Infrared Pre-training framework, to enhance the pre-trained model performance. This framework uses the hybrid-attention distillation NMI-HAD as the pre-training target, a large-scale mixed dataset InfMix for pre-training, and a last-layer feature pyramid network LL-FPN for fine-tuning. Experimental results show that UNIP outperforms various pre-training methods by up to 13.5\% in average mIoU on three infrared segmentation tasks, evaluated using fine-tuning and linear probing metrics. UNIP-S achieves performance on par with MAE-L while requiring only 1/10 of the computational cost. Furthermore, UNIP significantly surpasses state-of-the-art (SOTA) infrared or RGB segmentation methods and demonstrates broad potential for application in other modalities, such as RGB and depth. Our code is available at https://github.com/casiatao/UNIP.

Zhengkai Jiang, Yu Liu, Ceyuan Yang et al.

Transferring existing image-based detectors to the video is non-trivial since the quality of frames is always deteriorated by part occlusion, rare pose, and motion blur. Previous approaches exploit to propagate and aggregate features across video frames by using optical flow-warping. However, directly applying image-level optical flow onto the high-level features might not establish accurate spatial correspondences. Therefore, a novel module called Learnable Spatio-Temporal Sampling (LSTS) has been proposed to learn semantic-level correspondences among adjacent frame features accurately. The sampled locations are first randomly initialized, then updated iteratively to find better spatial correspondences guided by detection supervision progressively. Besides, Sparsely Recursive Feature Updating (SRFU) module and Dense Feature Aggregation (DFA) module are also introduced to model temporal relations and enhance per-frame features, respectively. Without bells and whistles, the proposed method achieves state-of-the-art performance on the ImageNet VID dataset with less computational complexity and real-time speed. Code will be made available at https://github.com/jiangzhengkai/LSTS.

Kun Ding, Haojian Zhang, Qiang Yu et al.

We propose a generalized method for boosting the generalization ability of pre-trained vision-language models (VLMs) while fine-tuning on downstream few-shot tasks. The idea is realized by exploiting out-of-distribution (OOD) detection to predict whether a sample belongs to a base distribution or a novel distribution and then using the score generated by a dedicated competition based scoring function to fuse the zero-shot and few-shot classifier. The fused classifier is dynamic, which will bias towards the zero-shot classifier if a sample is more likely from the distribution pre-trained on, leading to improved base-to-novel generalization ability. Our method is performed only in test stage, which is applicable to boost existing methods without time-consuming re-training. Extensive experiments show that even weak distribution detectors can still improve VLMs' generalization ability. Specifically, with the help of OOD detectors, the harmonic mean of CoOp and ProGrad increase by 2.6 and 1.5 percentage points over 11 recognition datasets in the base-to-novel setting.

Chenghao Zhang, Gaofeng Meng, Bin Fan et al.

The remarkable performance of recent stereo depth estimation models benefits from the successful use of convolutional neural networks to regress dense disparity. Akin to most tasks, this needs gathering training data that covers a number of heterogeneous scenes at deployment time. However, training samples are typically acquired continuously in practical applications, making the capability to learn new scenes continually even more crucial. For this purpose, we propose to perform continual stereo matching where a model is tasked to 1) continually learn new scenes, 2) overcome forgetting previously learned scenes, and 3) continuously predict disparities at inference. We achieve this goal by introducing a Reusable Architecture Growth (RAG) framework. RAG leverages task-specific neural unit search and architecture growth to learn new scenes continually in both supervised and self-supervised manners. It can maintain high reusability during growth by reusing previous units while obtaining good performance. Additionally, we present a Scene Router module to adaptively select the scene-specific architecture path at inference. Comprehensive experiments on numerous datasets show that our framework performs impressively in various weather, road, and city circumstances and surpasses the state-of-the-art methods in more challenging cross-dataset settings. Further experiments also demonstrate the adaptability of our method to unseen scenes, which can facilitate end-to-end stereo architecture learning and practical deployment.

Ruixiang Wang, Yuyang Hong, Shiming Xiang et al.

Transformers have demonstrated success in graph learning, particularly for node-level tasks. However, existing methods encounter an information bottleneck when generating graph-level representations. The prevalent single token paradigm fails to fully leverage the inherent strength of self-attention in encoding token sequences, and degenerates into a weighted sum of node signals. To address this issue, we design a novel serialized token paradigm to encapsulate global signals more effectively. Specifically, a graph serialization method is proposed to aggregate node signals into serialized graph tokens, with positional encoding being automatically involved. Then, stacked self-attention layers are applied to encode this token sequence and capture its internal dependencies. Our method can yield more expressive graph representations by modeling complex interactions among multiple graph tokens. Experimental results show that our method achieves state-of-the-art results on several graph-level benchmarks. Ablation studies verify the effectiveness of the proposed modules.

Xing Nie, Yongcheng Liu, Shaohong Chen et al.

Exploiting convolutional neural networks for point cloud processing is quite challenging, due to the inherent irregular distribution and discrete shape representation of point clouds. To address these problems, many handcrafted convolution variants have sprung up in recent years. Though with elaborate design, these variants could be far from optimal in sufficiently capturing diverse shapes formed by discrete points. In this paper, we propose PointSeaConv, i.e., a novel differential convolution search paradigm on point clouds. It can work in a purely data-driven manner and thus is capable of auto-creating a group of suitable convolutions for geometric shape modeling. We also propose a joint optimization framework for simultaneous search of internal convolution and external architecture, and introduce epsilon-greedy algorithm to alleviate the effect of discretization error. As a result, PointSeaNet, a deep network that is sufficient to capture geometric shapes at both convolution level and architecture level, can be searched out for point cloud processing. Extensive experiments strongly evidence that our proposed PointSeaNet surpasses current handcrafted deep models on challenging benchmarks across multiple tasks with remarkable margins.

Jianbo Liu, Ying Wang, Shiming Xiang et al.

Previous methods for skeleton-based gesture recognition mostly arrange the skeleton sequence into a pseudo picture or spatial-temporal graph and apply deep Convolutional Neural Network (CNN) or Graph Convolutional Network (GCN) for feature extraction. Although achieving superior results, these methods have inherent limitations in dynamically capturing local features of interactive hand parts, and the computing efficiency still remains a serious issue. In this work, the self-attention mechanism is introduced to alleviate this problem. Considering the hierarchical structure of hand joints, we propose an efficient hierarchical self-attention network (HAN) for skeleton-based gesture recognition, which is based on pure self-attention without any CNN, RNN or GCN operators. Specifically, the joint self-attention module is used to capture spatial features of fingers, the finger self-attention module is designed to aggregate features of the whole hand. In terms of temporal features, the temporal self-attention module is utilized to capture the temporal dynamics of the fingers and the entire hand. Finally, these features are fused by the fusion self-attention module for gesture classification. Experiments show that our method achieves competitive results on three gesture recognition datasets with much lower computational complexity.

Nuo Xu, Chunlei Huo, Jiacheng Guo et al.

In recent years, deep learning methods bring incredible progress to the field of object detection. However, in the field of remote sensing image processing, existing methods neglect the relationship between imaging configuration and detection performance, and do not take into account the importance of detection performance feedback for improving image quality. Therefore, detection performance is limited by the passive nature of the conventional object detection framework. In order to solve the above limitations, this paper takes adaptive brightness adjustment and scale adjustment as examples, and proposes an active object detection method based on deep reinforcement learning. The goal of adaptive image attribute learning is to maximize the detection performance. With the help of active object detection and image attribute adjustment strategies, low-quality images can be converted into high-quality images, and the overall performance is improved without retraining the detector.

Chaoxu Guo, Bin Fan, Qian Zhang et al.

Current state-of-the-art detectors typically exploit feature pyramid to detect objects at different scales. Among them, FPN is one of the representative works that build a feature pyramid by multi-scale features summation. However, the design defects behind prevent the multi-scale features from being fully exploited. In this paper, we begin by first analyzing the design defects of feature pyramid in FPN, and then introduce a new feature pyramid architecture named AugFPN to address these problems. Specifically, AugFPN consists of three components: Consistent Supervision, Residual Feature Augmentation, and Soft RoI Selection. AugFPN narrows the semantic gaps between features of different scales before feature fusion through Consistent Supervision. In feature fusion, ratio-invariant context information is extracted by Residual Feature Augmentation to reduce the information loss of feature map at the highest pyramid level. Finally, Soft RoI Selection is employed to learn a better RoI feature adaptively after feature fusion. By replacing FPN with AugFPN in Faster R-CNN, our models achieve 2.3 and 1.6 points higher Average Precision (AP) when using ResNet50 and MobileNet-v2 as backbone respectively. Furthermore, AugFPN improves RetinaNet by 1.6 points AP and FCOS by 0.9 points AP when using ResNet50 as backbone. Codes will be made available.

Xiyan Liu, Gaofeng Meng, Shiming Xiang et al.

Chinese character synthesis involves two related aspects, i.e., style maintenance and content consistency. Although some methods have achieved remarkable success in synthesizing a character with specified style from standard font, how to map characters to a specified style domain without losing their identifiability remains very challenging. In this paper, we propose a novel model named FontGAN, which integrates the character stylization and de-stylization into a unified framework. In our model, we decouple character images into style representation and content representation, which facilitates more precise control of these two types of variables, thereby improving the quality of the generated results. We also introduce two modules, namely, font consistency module (FCM) and content prior module (CPM). FCM exploits a category guided Kullback-Leibler loss to embedding the style representation into different Gaussian distributions. It constrains the characters of the same font in the training set globally. On the other hand, it enables our model to obtain style variables through sampling in testing phase. CPM provides content prior for the model to guide the content encoding process and alleviates the problem of stroke deficiency during de-stylization. Extensive experimental results on character stylization and de-stylization have demonstrated the effectiveness of our method.

Yongcheng Liu, Bin Fan, Gaofeng Meng et al.

Point cloud processing is very challenging, as the diverse shapes formed by irregular points are often indistinguishable. A thorough grasp of the elusive shape requires sufficiently contextual semantic information, yet few works devote to this. Here we propose DensePoint, a general architecture to learn densely contextual representation for point cloud processing. Technically, it extends regular grid CNN to irregular point configuration by generalizing a convolution operator, which holds the permutation invariance of points, and achieves efficient inductive learning of local patterns. Architecturally, it finds inspiration from dense connection mode, to repeatedly aggregate multi-level and multi-scale semantics in a deep hierarchy. As a result, densely contextual information along with rich semantics, can be acquired by DensePoint in an organic manner, making it highly effective. Extensive experiments on challenging benchmarks across four tasks, as well as thorough model analysis, verify DensePoint achieves the state of the arts.

Jianlong Chang, Xinbang Zhang, Yiwen Guo et al.

For network architecture search (NAS), it is crucial but challenging to simultaneously guarantee both effectiveness and efficiency. Towards achieving this goal, we develop a differentiable NAS solution, where the search space includes arbitrary feed-forward network consisting of the predefined number of connections. Benefiting from a proposed ensemble Gumbel-Softmax estimator, our method optimizes both the architecture of a deep network and its parameters in the same round of backward propagation, yielding an end-to-end mechanism of searching network architectures. Extensive experiments on a variety of popular datasets strongly evidence that our method is capable of discovering high-performance architectures, while guaranteeing the requisite efficiency during searching.

Jianlong Chang, Yiwen Guo, Lingfeng Wang et al.

Traditional clustering methods often perform clustering with low-level indiscriminative representations and ignore relationships between patterns, resulting in slight achievements in the era of deep learning. To handle this problem, we develop Deep Discriminative Clustering (DDC) that models the clustering task by investigating relationships between patterns with a deep neural network. Technically, a global constraint is introduced to adaptively estimate the relationships, and a local constraint is developed to endow the network with the capability of learning high-level discriminative representations. By iteratively training the network and estimating the relationships in a mini-batch manner, DDC theoretically converges and the trained network enables to generate a group of discriminative representations that can be treated as clustering centers for straightway clustering. Extensive experiments strongly demonstrate that DDC outperforms current methods on eight image, text and audio datasets concurrently.

Yonghao He, Dezhong Xu, Lifang Wu et al.

Face detection, as a fundamental technology for various applications, is always deployed on edge devices which have limited memory storage and low computing power. This paper introduces a Light and Fast Face Detector (LFFD) for edge devices. The proposed method is anchor-free and belongs to the one-stage category. Specifically, we rethink the importance of receptive field (RF) and effective receptive field (ERF) in the background of face detection. Essentially, the RFs of neurons in a certain layer are distributed regularly in the input image and theses RFs are natural "anchors". Combining RF "anchors" and appropriate RF strides, the proposed method can detect a large range of continuous face scales with 100% coverage in theory. The insightful understanding of relations between ERF and face scales motivates an efficient backbone for one-stage detection. The backbone is characterized by eight detection branches and common layers, resulting in efficient computation. Comprehensive and extensive experiments on popular benchmarks: WIDER FACE and FDDB are conducted. A new evaluation schema is proposed for application-oriented scenarios. Under the new schema, the proposed method can achieve superior accuracy (WIDER FACE Val/Test -- Easy: 0.910/0.896, Medium: 0.881/0.865, Hard: 0.780/0.770; FDDB -- discontinuous: 0.973, continuous: 0.724). Multiple hardware platforms are introduced to evaluate the running efficiency. The proposed method can obtain fast inference speed (NVIDIA TITAN Xp: 131.45 FPS at 640x480; NVIDIA TX2: 136.99 PFS at 160x120; Raspberry Pi 3 Model B+: 8.44 FPS at 160x120) with model size of 9 MB.

Yongcheng Liu, Bin Fan, Shiming Xiang et al.

Point cloud analysis is very challenging, as the shape implied in irregular points is difficult to capture. In this paper, we propose RS-CNN, namely, Relation-Shape Convolutional Neural Network, which extends regular grid CNN to irregular configuration for point cloud analysis. The key to RS-CNN is learning from relation, i.e., the geometric topology constraint among points. Specifically, the convolutional weight for local point set is forced to learn a high-level relation expression from predefined geometric priors, between a sampled point from this point set and the others. In this way, an inductive local representation with explicit reasoning about the spatial layout of points can be obtained, which leads to much shape awareness and robustness. With this convolution as a basic operator, RS-CNN, a hierarchical architecture can be developed to achieve contextual shape-aware learning for point cloud analysis. Extensive experiments on challenging benchmarks across three tasks verify RS-CNN achieves the state of the arts.

Chaoxu Guo, Bin Fan, Jie Gu et al.

Transferring image-based object detectors to the domain of videos remains a challenging problem. Previous efforts mostly exploit optical flow to propagate features across frames, aiming to achieve a good trade-off between accuracy and efficiency. However, introducing an extra model to estimate optical flow can significantly increase the overall model size. The gap between optical flow and high-level features can also hinder it from establishing spatial correspondence accurately. Instead of relying on optical flow, this paper proposes a novel module called Progressive Sparse Local Attention (PSLA), which establishes the spatial correspondence between features across frames in a local region with progressively sparser stride and uses the correspondence to propagate features. Based on PSLA, Recursive Feature Updating (RFU) and Dense Feature Transforming (DenseFT) are proposed to model temporal appearance and enrich feature representation respectively in a novel video object detection framework. Experiments on ImageNet VID show that our method achieves the best accuracy compared to existing methods with smaller model size and acceptable runtime speed.

Yukang Chen, Gaofeng Meng, Qian Zhang et al.

Designing neural architectures is a fundamental step in deep learning applications. As a partner technique, model compression on neural networks has been widely investigated to gear the needs that the deep learning algorithms could be run with the limited computation resources on mobile devices. Currently, both the tasks of architecture design and model compression require expertise tricks and tedious trials. In this paper, we integrate these two tasks into one unified framework, which enables the joint architecture search with quantization (compression) policies for neural networks. This method is named JASQ. Here our goal is to automatically find a compact neural network model with high performance that is suitable for mobile devices. Technically, a multi-objective evolutionary search algorithm is introduced to search the models under the balance between model size and performance accuracy. In experiments, we find that our approach outperforms the methods that search only for architectures or only for quantization policies. 1) Specifically, given existing networks, our approach can provide them with learning-based quantization policies, and outperforms their 2 bits, 4 bits, 8 bits, and 16 bits counterparts. It can yield higher accuracies than the float models, for example, over 1.02% higher accuracy on MobileNet-v1. 2) What is more, under the balance between model size and performance accuracy, two models are obtained with joint search of architectures and quantization policies: a high-accuracy model and a small model, JASQNet and JASQNet-Small that achieves 2.97% error rate with 0.9 MB on CIFAR-10.

Yongcheng Liu, Lu Sheng, Jing Shao et al.

Multi-label image classification is a fundamental but challenging task towards general visual understanding. Existing methods found the region-level cues (e.g., features from RoIs) can facilitate multi-label classification. Nevertheless, such methods usually require laborious object-level annotations (i.e., object labels and bounding boxes) for effective learning of the object-level visual features. In this paper, we propose a novel and efficient deep framework to boost multi-label classification by distilling knowledge from weakly-supervised detection task without bounding box annotations. Specifically, given the image-level annotations, (1) we first develop a weakly-supervised detection (WSD) model, and then (2) construct an end-to-end multi-label image classification framework augmented by a knowledge distillation module that guides the classification model by the WSD model according to the class-level predictions for the whole image and the object-level visual features for object RoIs. The WSD model is the teacher model and the classification model is the student model. After this cross-task knowledge distillation, the performance of the classification model is significantly improved and the efficiency is maintained since the WSD model can be safely discarded in the test phase. Extensive experiments on two large-scale datasets (MS-COCO and NUS-WIDE) show that our framework achieves superior performances over the state-of-the-art methods on both performance and efficiency.

Yongcheng Liu, Bin Fan, Lingfeng Wang et al.

Semantic labeling for very high resolution (VHR) images in urban areas, is of significant importance in a wide range of remote sensing applications. However, many confusing manmade objects and intricate fine-structured objects make it very difficult to obtain both coherent and accurate labeling results. For this challenging task, we propose a novel deep model with convolutional neural networks (CNNs), i.e., an end-to-end self-cascaded network (ScasNet). Specifically, for confusing manmade objects, ScasNet improves the labeling coherence with sequential global-to-local contexts aggregation. Technically, multi-scale contexts are captured on the output of a CNN encoder, and then they are successively aggregated in a self-cascaded manner. Meanwhile, for fine-structured objects, ScasNet boosts the labeling accuracy with a coarse-to-fine refinement strategy. It progressively refines the target objects using the low-level features learned by CNN's shallow layers. In addition, to correct the latent fitting residual caused by multi-feature fusion inside ScasNet, a dedicated residual correction scheme is proposed. It greatly improves the effectiveness of ScasNet. Extensive experimental results on three public datasets, including two challenging benchmarks, show that ScasNet achieves the state-of-the-art performance.

Bin Fan, Qingqun Kong, Xinchao Wang et al.

This paper performs a comprehensive and comparative evaluation of the state of the art local features for the task of image based 3D reconstruction. The evaluated local features cover the recently developed ones by using powerful machine learning techniques and the elaborately designed handcrafted features. To obtain a comprehensive evaluation, we choose to include both float type features and binary ones. Meanwhile, two kinds of datasets have been used in this evaluation. One is a dataset of many different scene types with groundtruth 3D points, containing images of different scenes captured at fixed positions, for quantitative performance evaluation of different local features in the controlled image capturing situations. The other dataset contains Internet scale image sets of several landmarks with a lot of unrelated images, which is used for qualitative performance evaluation of different local features in the free image collection situations. Our experimental results show that binary features are competent to reconstruct scenes from controlled image sequences with only a fraction of processing time compared to use float type features. However, for the case of large scale image set with many distracting images, float type features show a clear advantage over binary ones.

Bin Fan, Qingqun Kong, Wei Sui et al.

Binary features have been incrementally popular in the past few years due to their low memory footprints and the efficient computation of Hamming distance between binary descriptors. They have been shown with promising results on some real time applications, e.g., SLAM, where the matching operations are relative few. However, in computer vision, there are many applications such as 3D reconstruction requiring lots of matching operations between local features. Therefore, a natural question is that is the binary feature still a promising solution to this kind of applications? To get the answer, this paper conducts a comparative study of binary features and their matching methods on the context of 3D reconstruction in a recently proposed large scale mutliview stereo dataset. Our evaluations reveal that not all binary features are capable of this task. Most of them are inferior to the classical SIFT based method in terms of reconstruction accuracy and completeness with a not significant better computational performance.

Guangliang Cheng, Feiyun Zhu, Shiming Xiang et al.

It is very useful and increasingly popular to extract accurate road centerlines from very-high-resolution (VHR) re- mote sensing imagery for various applications, such as road map generation and updating etc. There are three shortcomings of current methods: (a) Due to the noise and occlusions (owing to vehicles and trees), most road extraction methods bring in heterogeneous classification results; (b) Morphological thinning algorithm is widely used to extract road centerlines, while it pro- duces small spurs around the centerlines; (c) Many methods are ineffective to extract centerlines around the road intersections. To address the above three issues, we propose a novel method to ex- tract smooth and complete road centerlines via three techniques: the multiscale joint collaborative representation (MJCR) & graph cuts (GC), tensor voting (TV) & non-maximum suppression (NMS) and fitting based connection algorithm. Specifically, a MJCR-GC based road area segmentation method is proposed by incorporating mutiscale features and spatial information. In this way, a homogenous road segmentation result is achieved. Then, to obtain a smooth and correct road centerline network, a TV-NMS based centerline extraction method is introduced. This method not only extracts smooth road centerlines, but also connects the discontinuous road centerlines. Finally, to overcome the ineffectiveness of current methods in the road intersection, a fitting based road centerline connection algorithm is proposed. As a result, we can get a complete road centerline network. Extensive experiments on two datasets demonstrate that our method achieves higher quantitative results, as well as more satisfactory visual performances by comparing with state-of-the- art methods.

Cuicui Kang, Shengcai Liao, Yonghao He et al.

The cross-media retrieval problem has received much attention in recent years due to the rapid increasing of multimedia data on the Internet. A new approach to the problem has been raised which intends to match features of different modalities directly. In this research, there are two critical issues: how to get rid of the heterogeneity between different modalities and how to match the cross-modal features of different dimensions. Recently metric learning methods show a good capability in learning a distance metric to explore the relationship between data points. However, the traditional metric learning algorithms only focus on single-modal features, which suffer difficulties in addressing the cross-modal features of different dimensions. In this paper, we propose a cross-modal similarity learning algorithm for the cross-modal feature matching. The proposed method takes a bilinear formulation, and with the nuclear-norm penalization, it achieves low-rank representation. Accordingly, the accelerated proximal gradient algorithm is successfully imported to find the optimal solution with a fast convergence rate O(1/t^2). Experiments on three well known image-text cross-media retrieval databases show that the proposed method achieves the best performance compared to the state-of-the-art algorithms.

Feiyun Zhu, Bin Fan, Xinliang Zhu et al.

Subset selection from massive data with noised information is increasingly popular for various applications. This problem is still highly challenging as current methods are generally slow in speed and sensitive to outliers. To address the above two issues, we propose an accelerated robust subset selection (ARSS) method. Specifically in the subset selection area, this is the first attempt to employ the $\ell_{p}(0<p\leq1)$-norm based measure for the representation loss, preventing large errors from dominating our objective. As a result, the robustness against outlier elements is greatly enhanced. Actually, data size is generally much larger than feature length, i.e. $N\gg L$. Based on this observation, we propose a speedup solver (via ALM and equivalent derivations) to highly reduce the computational cost, theoretically from $O(N^{4})$ to $O(N{}^{2}L)$. Extensive experiments on ten benchmark datasets verify that our method not only outperforms state of the art methods, but also runs 10,000+ times faster than the most related method.

Feiyun Zhu, Ying Wang, Bin Fan et al.

Hyperspectral unmixing (HU) plays a fundamental role in a wide range of hyperspectral applications. It is still challenging due to the common presence of outlier channels and the large solution space. To address the above two issues, we propose a novel model by emphasizing both robust representation and learning-based sparsity. Specifically, we apply the $\ell_{2,1}$-norm to measure the representation error, preventing outlier channels from dominating our objective. In this way, the side effects of outlier channels are greatly relieved. Besides, we observe that the mixed level of each pixel varies over image grids. Based on this observation, we exploit a learning-based sparsity method to simultaneously learn the HU results and a sparse guidance map. Via this guidance map, the sparsity constraint in the $\ell_{p}\!\left(\!0\!<\! p\!\leq\!1\right)$-norm is adaptively imposed according to the learnt mixed level of each pixel. Compared with state-of-the-art methods, our model is better suited to the real situation, thus expected to achieve better HU results. The resulted objective is highly non-convex and non-smooth, and so it is hard to optimize. As a profound theoretical contribution, we propose an efficient algorithm to solve it. Meanwhile, the convergence proof and the computational complexity analysis are systematically provided. Extensive evaluations verify that our method is highly promising for the HU task---it achieves very accurate guidance maps and much better HU results compared with state-of-the-art methods.

Feiyun Zhu, Ying Wang, Shiming Xiang et al.

Hyperspectral Unmixing (HU) has received increasing attention in the past decades due to its ability of unveiling information latent in hyperspectral data. Unfortunately, most existing methods fail to take advantage of the spatial information in data. To overcome this limitation, we propose a Structured Sparse regularized Nonnegative Matrix Factorization (SS-NMF) method from the following two aspects. First, we incorporate a graph Laplacian to encode the manifold structures embedded in the hyperspectral data space. In this way, the highly similar neighboring pixels can be grouped together. Second, the lasso penalty is employed in SS-NMF for the fact that pixels in the same manifold structure are sparsely mixed by a common set of relevant bases. These two factors act as a new structured sparse constraint. With this constraint, our method can learn a compact space, where highly similar pixels are grouped to share correlated sparse representations. Experiments on real hyperspectral data sets with different noise levels demonstrate that our method outperforms the state-of-the-art methods significantly.

Feiyun Zhu, Ying Wang, Bin Fan et al.

Hyperspectral unmixing, the process of estimating a common set of spectral bases and their corresponding composite percentages at each pixel, is an important task for hyperspectral analysis, visualization and understanding. From an unsupervised learning perspective, this problem is very challenging---both the spectral bases and their composite percentages are unknown, making the solution space too large. To reduce the solution space, many approaches have been proposed by exploiting various priors. In practice, these priors would easily lead to some unsuitable solution. This is because they are achieved by applying an identical strength of constraints to all the factors, which does not hold in practice. To overcome this limitation, we propose a novel sparsity based method by learning a data-guided map to describe the individual mixed level of each pixel. Through this data-guided map, the $\ell_{p}(0<p<1)$ constraint is applied in an adaptive manner. Such implementation not only meets the practical situation, but also guides the spectral bases toward the pixels under highly sparse constraint. What's more, an elegant optimization scheme as well as its convergence proof have been provided in this paper. Extensive experiments on several datasets also demonstrate that the data-guided map is feasible, and high quality unmixing results could be obtained by our method.

Ying Wang, Chunhong Pan, Shiming Xiang et al.

Hyperspectral unmixing is one of the crucial steps for many hyperspectral applications. The problem of hyperspectral unmixing has proven to be a difficult task in unsupervised work settings where the endmembers and abundances are both unknown. What is more, this task becomes more challenging in the case that the spectral bands are degraded with noise. This paper presents a robust model for unsupervised hyperspectral unmixing. Specifically, our model is developed with the correntropy based metric where the non-negative constraints on both endmembers and abundances are imposed to keep physical significance. In addition, a sparsity prior is explicitly formulated to constrain the distribution of the abundances of each endmember. To solve our model, a half-quadratic optimization technique is developed to convert the original complex optimization problem into an iteratively re-weighted NMF with sparsity constraints. As a result, the optimization of our model can adaptively assign small weights to noisy bands and give more emphasis on noise-free bands. In addition, with sparsity constraints, our model can naturally generate sparse abundances. Experiments on synthetic and real data demonstrate the effectiveness of our model in comparison to the related state-of-the-art unmixing models.