Yong Liu

Jianlin Liu, Qiang Nie, Yong Liu et al.

We propose a novel visual re-localization method based on direct matching between the implicit 3D descriptors and the 2D image with transformer. A conditional neural radiance field(NeRF) is chosen as the 3D scene representation in our pipeline, which supports continuous 3D descriptors generation and neural rendering. By unifying the feature matching and the scene coordinate regression to the same framework, our model learns both generalizable knowledge and scene prior respectively during two training stages. Furthermore, to improve the localization robustness when domain gap exists between training and testing phases, we propose an appearance adaptation layer to explicitly align styles between the 3D model and the query image. Experiments show that our method achieves higher localization accuracy than other learning-based approaches on multiple benchmarks. Code is available at \url{https://github.com/JenningsL/nerf-loc}.

Dihe Huang, Ying Chen, Shang Xu et al.

The detector-free feature matching approaches are currently attracting great attention thanks to their excellent performance. However, these methods still struggle at large-scale and viewpoint variations, due to the geometric inconsistency resulting from the application of the mutual nearest neighbour criterion (\ie, one-to-one assignment) in patch-level matching.Accordingly, we introduce AdaMatcher, which first accomplishes the feature correlation and co-visible area estimation through an elaborate feature interaction module, then performs adaptive assignment on patch-level matching while estimating the scales between images, and finally refines the co-visible matches through scale alignment and sub-pixel regression module.Extensive experiments show that AdaMatcher outperforms solid baselines and achieves state-of-the-art results on many downstream tasks. Additionally, the adaptive assignment and sub-pixel refinement module can be used as a refinement network for other matching methods, such as SuperGlue, to boost their performance further. The code will be publicly available at https://github.com/AbyssGaze/AdaMatcher.

Yong Liu, Ran Yu, Jiahao Wang et al.

This paper studies semi-supervised video object segmentation through boosting intra-frame interaction. Recent memory network-based methods focus on exploiting inter-frame temporal reference while paying little attention to intra-frame spatial dependency. Specifically, these segmentation model tends to be susceptible to interference from unrelated nontarget objects in a certain frame. To this end, we propose Global Spectral Filter Memory network (GSFM), which improves intra-frame interaction through learning long-term spatial dependencies in the spectral domain. The key components of GSFM is 2D (inverse) discrete Fourier transform for spatial information mixing. Besides, we empirically find low frequency feature should be enhanced in encoder (backbone) while high frequency for decoder (segmentation head). We attribute this to semantic information extracting role for encoder and fine-grained details highlighting role for decoder. Thus, Low (High) Frequency Module is proposed to fit this circumstance. Extensive experiments on the popular DAVIS and YouTube-VOS benchmarks demonstrate that GSFM noticeably outperforms the baseline method and achieves state-of-the-art performance. Besides, extensive analysis shows that the proposed modules are reasonable and of great generalization ability. Our source code is available at https://github.com/workforai/GSFM.

Yong Liu, Ran Yu, Fei Yin et al.

Recently, several spatial-temporal memory-based methods have verified that storing intermediate frames and their masks as memory are helpful to segment target objects in videos. However, they mainly focus on better matching between the current frame and the memory frames without explicitly paying attention to the quality of the memory. Therefore, frames with poor segmentation masks are prone to be memorized, which leads to a segmentation mask error accumulation problem and further affect the segmentation performance. In addition, the linear increase of memory frames with the growth of frame number also limits the ability of the models to handle long videos. To this end, we propose a Quality-aware Dynamic Memory Network (QDMN) to evaluate the segmentation quality of each frame, allowing the memory bank to selectively store accurately segmented frames to prevent the error accumulation problem. Then, we combine the segmentation quality with temporal consistency to dynamically update the memory bank to improve the practicability of the models. Without any bells and whistles, our QDMN achieves new state-of-the-art performance on both DAVIS and YouTube-VOS benchmarks. Moreover, extensive experiments demonstrate that the proposed Quality Assessment Module (QAM) can be applied to memory-based methods as generic plugins and significantly improves performance. Our source code is available at https://github.com/workforai/QDMN.

Zizhang Li, Xiaoyang Lyu, Yuanyuan Ding et al.

Recently, neural implicit surfaces have become popular for multi-view reconstruction. To facilitate practical applications like scene editing and manipulation, some works extend the framework with semantic masks input for the object-compositional reconstruction rather than the holistic perspective. Though achieving plausible disentanglement, the performance drops significantly when processing the indoor scenes where objects are usually partially observed. We propose RICO to address this by regularizing the unobservable regions for indoor compositional reconstruction. Our key idea is to first regularize the smoothness of the occluded background, which then in turn guides the foreground object reconstruction in unobservable regions based on the object-background relationship. Particularly, we regularize the geometry smoothness of occluded background patches. With the improved background surface, the signed distance function and the reversedly rendered depth of objects can be optimized to bound them within the background range. Extensive experiments show our method outperforms other methods on synthetic and real-world indoor scenes and prove the effectiveness of proposed regularizations. The code is available at https://github.com/kyleleey/RICO.

Zizhang Li, Mengmeng Wang, Huaijin Pi et al.

Recently, the image-wise implicit neural representation of videos, NeRV, has gained popularity for its promising results and swift speed compared to regular pixel-wise implicit representations. However, the redundant parameters within the network structure can cause a large model size when scaling up for desirable performance. The key reason of this phenomenon is the coupled formulation of NeRV, which outputs the spatial and temporal information of video frames directly from the frame index input. In this paper, we propose E-NeRV, which dramatically expedites NeRV by decomposing the image-wise implicit neural representation into separate spatial and temporal context. Under the guidance of this new formulation, our model greatly reduces the redundant model parameters, while retaining the representation ability. We experimentally find that our method can improve the performance to a large extent with fewer parameters, resulting in a more than $8\times$ faster speed on convergence. Code is available at https://github.com/kyleleey/E-NeRV.

Yue Han, Jiangning Zhang, Yabiao Wang et al.

Few-Shot Instance Segmentation (FSIS) requires detecting and segmenting novel classes with limited support examples. Existing methods based on Region Proposal Networks (RPNs) face two issues: 1) Overfitting suppresses novel class objects; 2) Dual-branch models require complex spatial correlation strategies to prevent spatial information loss when generating class prototypes. We introduce a unified framework, Reference Twice (RefT), to exploit the relationship between support and query features for FSIS and related tasks. Our three main contributions are: 1) A novel transformer-based baseline that avoids overfitting, offering a new direction for FSIS; 2) Demonstrating that support object queries encode key factors after base training, allowing query features to be enhanced twice at both feature and query levels using simple cross-attention, thus avoiding complex spatial correlation interaction; 3) Introducing a class-enhanced base knowledge distillation loss to address the issue of DETR-like models struggling with incremental settings due to the input projection layer, enabling easy extension to incremental FSIS. Extensive experimental evaluations on the COCO dataset under three FSIS settings demonstrate that our method performs favorably against existing approaches across different shots, \eg, $+8.2/+9.4$ performance gain over state-of-the-art methods with 10/30-shots. Source code and models will be available at https://github.com/hanyue1648/RefT.

Yong Liu, Siqi Mai, Xiangning Chen et al.

Recently, Sharpness-Aware Minimization (SAM), which connects the geometry of the loss landscape and generalization, has demonstrated significant performance boosts on training large-scale models such as vision transformers. However, the update rule of SAM requires two sequential (non-parallelizable) gradient computations at each step, which can double the computational overhead. In this paper, we propose a novel algorithm LookSAM - that only periodically calculates the inner gradient ascent, to significantly reduce the additional training cost of SAM. The empirical results illustrate that LookSAM achieves similar accuracy gains to SAM while being tremendously faster - it enjoys comparable computational complexity with first-order optimizers such as SGD or Adam. To further evaluate the performance and scalability of LookSAM, we incorporate a layer-wise modification and perform experiments in the large-batch training scenario, which is more prone to converge to sharp local minima. We are the first to successfully scale up the batch size when training Vision Transformers (ViTs). With a 64k batch size, we are able to train ViTs from scratch in minutes while maintaining competitive performance.

Kunyang Han, Yong Liu, Jun Hao Liew et al.

Recent advancements in pre-trained vision-language models, such as CLIP, have enabled the segmentation of arbitrary concepts solely from textual inputs, a process commonly referred to as open-vocabulary semantic segmentation (OVS). However, existing OVS techniques confront a fundamental challenge: the trained classifier tends to overfit on the base classes observed during training, resulting in suboptimal generalization performance to unseen classes. To mitigate this issue, recent studies have proposed the use of an additional frozen pre-trained CLIP for classification. Nonetheless, this approach incurs heavy computational overheads as the CLIP vision encoder must be repeatedly forward-passed for each mask, rendering it impractical for real-world applications. To address this challenge, our objective is to develop a fast OVS model that can perform comparably or better without the extra computational burden of the CLIP image encoder during inference. To this end, we propose a core idea of preserving the generalizable representation when fine-tuning on known classes. Specifically, we introduce a text diversification strategy that generates a set of synonyms for each training category, which prevents the learned representation from collapsing onto specific known category names. Additionally, we employ a text-guided knowledge distillation method to preserve the generalizable knowledge of CLIP. Extensive experiments demonstrate that our proposed model achieves robust generalization performance across various datasets. Furthermore, we perform a preliminary exploration of open-vocabulary video segmentation and present a benchmark that can facilitate future open-vocabulary research in the video domain.

Jiazheng Xing, Mengmeng Wang, Yong Liu et al.

Spatial and temporal modeling is one of the most core aspects of few-shot action recognition. Most previous works mainly focus on long-term temporal relation modeling based on high-level spatial representations, without considering the crucial low-level spatial features and short-term temporal relations. Actually, the former feature could bring rich local semantic information, and the latter feature could represent motion characteristics of adjacent frames, respectively. In this paper, we propose SloshNet, a new framework that revisits the spatial and temporal modeling for few-shot action recognition in a finer manner. First, to exploit the low-level spatial features, we design a feature fusion architecture search module to automatically search for the best combination of the low-level and high-level spatial features. Next, inspired by the recent transformer, we introduce a long-term temporal modeling module to model the global temporal relations based on the extracted spatial appearance features. Meanwhile, we design another short-term temporal modeling module to encode the motion characteristics between adjacent frame representations. After that, the final predictions can be obtained by feeding the embedded rich spatial-temporal features to a common frame-level class prototype matcher. We extensively validate the proposed SloshNet on four few-shot action recognition datasets, including Something-Something V2, Kinetics, UCF101, and HMDB51. It achieves favorable results against state-of-the-art methods in all datasets.

Jiahao Wang, Songyang Zhang, Yong Liu et al.

This paper studies how to keep a vision backbone effective while removing token mixers in its basic building blocks. Token mixers, as self-attention for vision transformers (ViTs), are intended to perform information communication between different spatial tokens but suffer from considerable computational cost and latency. However, directly removing them will lead to an incomplete model structure prior, and thus brings a significant accuracy drop. To this end, we first develop an RepIdentityFormer base on the re-parameterizing idea, to study the token mixer free model architecture. And we then explore the improved learning paradigm to break the limitation of simple token mixer free backbone, and summarize the empirical practice into 5 guidelines. Equipped with the proposed optimization strategy, we are able to build an extremely simple vision backbone with encouraging performance, while enjoying the high efficiency during inference. Extensive experiments and ablative analysis also demonstrate that the inductive bias of network architecture, can be incorporated into simple network structure with appropriate optimization strategy. We hope this work can serve as a starting point for the exploration of optimization-driven efficient network design. Project page: https://techmonsterwang.github.io/RIFormer/.

Zhihao Chen, Yang Zhou, Anh Tran et al.

Medical phrase grounding (MPG) aims to locate the most relevant region in a medical image, given a phrase query describing certain medical findings, which is an important task for medical image analysis and radiological diagnosis. However, existing visual grounding methods rely on general visual features for identifying objects in natural images and are not capable of capturing the subtle and specialized features of medical findings, leading to sub-optimal performance in MPG. In this paper, we propose MedRPG, an end-to-end approach for MPG. MedRPG is built on a lightweight vision-language transformer encoder and directly predicts the box coordinates of mentioned medical findings, which can be trained with limited medical data, making it a valuable tool in medical image analysis. To enable MedRPG to locate nuanced medical findings with better region-phrase correspondences, we further propose Tri-attention Context contrastive alignment (TaCo). TaCo seeks context alignment to pull both the features and attention outputs of relevant region-phrase pairs close together while pushing those of irrelevant regions far away. This ensures that the final box prediction depends more on its finding-specific regions and phrases. Experimental results on three MPG datasets demonstrate that our MedRPG outperforms state-of-the-art visual grounding approaches by a large margin. Additionally, the proposed TaCo strategy is effective in enhancing finding localization ability and reducing spurious region-phrase correlations.

Jianbiao Mei, Yu Yang, Mengmeng Wang et al.

Semantic scene completion (SSC) jointly predicts the semantics and geometry of the entire 3D scene, which plays an essential role in 3D scene understanding for autonomous driving systems. SSC has achieved rapid progress with the help of semantic context in segmentation. However, how to effectively exploit the relationships between the semantic context in semantic segmentation and geometric structure in scene completion remains under exploration. In this paper, we propose to solve outdoor SSC from the perspective of representation separation and BEV fusion. Specifically, we present the network, named SSC-RS, which uses separate branches with deep supervision to explicitly disentangle the learning procedure of the semantic and geometric representations. And a BEV fusion network equipped with the proposed Adaptive Representation Fusion (ARF) module is presented to aggregate the multi-scale features effectively and efficiently. Due to the low computational burden and powerful representation ability, our model has good generality while running in real-time. Extensive experiments on SemanticKITTI demonstrate our SSC-RS achieves state-of-the-art performance.

Xuhai Chen, Jiangning Zhang, Chao Xu et al.

Most of the existing blind image Super-Resolution (SR) methods assume that the blur kernels are space-invariant. However, the blur involved in real applications are usually space-variant due to object motion, out-of-focus, etc., resulting in severe performance drop of the advanced SR methods. To address this problem, we firstly introduce two new datasets with out-of-focus blur, i.e., NYUv2-BSR and Cityscapes-BSR, to support further researches of blind SR with space-variant blur. Based on the datasets, we design a novel Cross-MOdal fuSion network (CMOS) that estimate both blur and semantics simultaneously, which leads to improved SR results. It involves a feature Grouping Interactive Attention (GIA) module to make the two modalities interact more effectively and avoid inconsistency. GIA can also be used for the interaction of other features because of the universality of its structure. Qualitative and quantitative experiments compared with state-of-the-art methods on above datasets and real-world images demonstrate the superiority of our method, e.g., obtaining PSNR/SSIM by +1.91/+0.0048 on NYUv2-BSR than MANet.

Yimin Ou, Rui Yang, Lufan Ma et al.

Existing instance segmentation methods have achieved impressive performance but still suffer from a common dilemma: redundant representations (e.g., multiple boxes, grids, and anchor points) are inferred for one instance, which leads to multiple duplicated predictions. Thus, mainstream methods usually rely on a hand-designed non-maximum suppression (NMS) post-processing step to select the optimal prediction result, which hinders end-to-end training. To address this issue, we propose a box-free and NMS-free end-to-end instance segmentation framework, termed UniInst, that yields only one unique representation for each instance. Specifically, we design an instance-aware one-to-one assignment scheme, namely Only Yield One Representation (OYOR), which dynamically assigns one unique representation to each instance according to the matching quality between predictions and ground truths. Then, a novel prediction re-ranking strategy is elegantly integrated into the framework to address the misalignment between the classification score and the mask quality, enabling the learned representation to be more discriminative. With these techniques, our UniInst, the first FCN-based box-free and NMS-free instance segmentation framework, achieves competitive performance, e.g., 39.0 mask AP using ResNet-50-FPN and 40.2 mask AP using ResNet-101-FPN, against mainstream methods on COCO test-dev 2017. Moreover, the proposed instance-aware method is robust to occlusion scenes, outperforming common baselines by remarkable mask AP on the heavily-occluded OCHuman benchmark. Code is available at https://github.com/b03505036/UniInst.

Tianwei Lin, Honglin Lin, Fu Li et al. · amazon-science

Photo-realistic style transfer aims at migrating the artistic style from an exemplar style image to a content image, producing a result image without spatial distortions or unrealistic artifacts. Impressive results have been achieved by recent deep models. However, deep neural network based methods are too expensive to run in real-time. Meanwhile, bilateral grid based methods are much faster but still contain artifacts like overexposure. In this work, we propose the \textbf{Adaptive ColorMLP (AdaCM)}, an effective and efficient framework for universal photo-realistic style transfer. First, we find the complex non-linear color mapping between input and target domain can be efficiently modeled by a small multi-layer perceptron (ColorMLP) model. Then, in \textbf{AdaCM}, we adopt a CNN encoder to adaptively predict all parameters for the ColorMLP conditioned on each input content and style image pair. Experimental results demonstrate that AdaCM can generate vivid and high-quality stylization results. Meanwhile, our AdaCM is ultrafast and can process a 4K resolution image in 6ms on one V100 GPU.

Li Zhang, Yong Liu, Shaoteng Liu et al.

Intellectual property protection of deep neural networks is receiving attention from more and more researchers, and the latest research applies model watermarking to generative models for image processing. However, the existing watermarking methods designed for generative models do not take into account the effects of different channels of sample images on watermarking. As a result, the watermarking performance is still limited. To tackle this problem, in this paper, we first analyze the effects of embedding watermark information on different channels. Then, based on the characteristics of human visual system (HVS), we introduce two HVS-based generative model watermarking methods, which are realized in RGB color space and YUV color space respectively. In RGB color space, the watermark is embedded into the R and B channels based on the fact that HVS is more sensitive to G channel. In YUV color space, the watermark is embedded into the DCT domain of U and V channels based on the fact that HVS is more sensitive to brightness changes. Experimental results demonstrate the effectiveness of the proposed work, which improves the fidelity of the model to be protected and has good universality compared with previous methods.

Chao Xu, Jiangning Zhang, Miao Hua et al.

This paper presents a novel Region-Aware Face Swapping (RAFSwap) network to achieve identity-consistent harmonious high-resolution face generation in a local-global manner: \textbf{1)} Local Facial Region-Aware (FRA) branch augments local identity-relevant features by introducing the Transformer to effectively model misaligned cross-scale semantic interaction. \textbf{2)} Global Source Feature-Adaptive (SFA) branch further complements global identity-relevant cues for generating identity-consistent swapped faces. Besides, we propose a \textit{Face Mask Predictor} (FMP) module incorporated with StyleGAN2 to predict identity-relevant soft facial masks in an unsupervised manner that is more practical for generating harmonious high-resolution faces. Abundant experiments qualitatively and quantitatively demonstrate the superiority of our method for generating more identity-consistent high-resolution swapped faces over SOTA methods, \eg, obtaining 96.70 ID retrieval that outperforms SOTA MegaFS by 5.87$\uparrow$.

Yunliang Jiang, Chenyang Gu, Zhenfeng Xue et al.

As a special case of common object removal, image person removal is playing an increasingly important role in social media and criminal investigation domains. Due to the integrity of person area and the complexity of human posture, person removal has its own dilemmas. In this paper, we propose a novel idea to tackle these problems from the perspective of data synthesis. Concerning the lack of dedicated dataset for image person removal, two dataset production methods are proposed to automatically generate images, masks and ground truths respectively. Then, a learning framework similar to local image degradation is proposed so that the masks can be used to guide the feature extraction process and more texture information can be gathered for final prediction. A coarse-to-fine training strategy is further applied to refine the details. The data synthesis and learning framework combine well with each other. Experimental results verify the effectiveness of our method quantitatively and qualitatively, and the trained network proves to have good generalization ability either on real or synthetic images.

Xinzhe Ni, Yong Liu, Hao Wen et al.

Current methods for few-shot action recognition mainly fall into the metric learning framework following ProtoNet, which demonstrates the importance of prototypes. Although they achieve relatively good performance, the effect of multimodal information is ignored, e.g. label texts. In this work, we propose a novel MultimOdal PRototype-ENhanced Network (MORN), which uses the semantic information of label texts as multimodal information to enhance prototypes. A CLIP visual encoder and a frozen CLIP text encoder are introduced to obtain features with good multimodal initialization. Then in the visual flow, visual prototypes are computed by a visual prototype-computed module. In the text flow, a semantic-enhanced (SE) module and an inflating operation are used to obtain text prototypes. The final multimodal prototypes are then computed by a multimodal prototype-enhanced (MPE) module. Besides, we define a PRototype SImilarity DiffErence (PRIDE) to evaluate the quality of prototypes, which is used to verify our improvement on the prototype level and effectiveness of MORN. We conduct extensive experiments on four popular few-shot action recognition datasets: HMDB51, UCF101, Kinetics and SSv2, and MORN achieves state-of-the-art results. When plugging PRIDE into the training stage, the performance can be further improved.

Jianlin Liu, Zhuofei Huang, Dihe Huang et al.

3D object detection from monocular image(s) is a challenging and long-standing problem of computer vision. To combine information from different perspectives without troublesome 2D instance tracking, recent methods tend to aggregate multiview feature by sampling regular 3D grid densely in space, which is inefficient. In this paper, we attempt to improve multi-view feature aggregation by proposing a learnable keypoints sampling method, which scatters pseudo surface points in 3D space, in order to keep data sparsity. The scattered points augmented by multi-view geometric constraints and visual features are then employed to infer objects location and shape in the scene. To make up the limitations of single frame and model multi-view geometry explicitly, we further propose a surface filter module for noise suppression. Experimental results show that our method achieves significantly better performance than previous works in terms of 3D detection (more than 0.1 AP improvement on some categories of ScanNet). The code will be publicly available.

Yabiao Wang, Shuo Wang, Jiangning Zhang et al.

Human-human motion generation is essential for understanding humans as social beings. Current methods fall into two main categories: single-person-based methods and separate modeling-based methods. To delve into this field, we abstract the overall generation process into a general framework MetaMotion, which consists of two phases: temporal modeling and interaction mixing. For temporal modeling, the single-person-based methods concatenate two people into a single one directly, while the separate modeling-based methods skip the modeling of interaction sequences. The inadequate modeling described above resulted in sub-optimal performance and redundant model parameters. In this paper, we introduce TIMotion (Temporal and Interactive Modeling), an efficient and effective framework for human-human motion generation. Specifically, we first propose Causal Interactive Injection to model two separate sequences as a causal sequence leveraging the temporal and causal properties. Then we present Role-Evolving Scanning to adjust to the change in the active and passive roles throughout the interaction. Finally, to generate smoother and more rational motion, we design Localized Pattern Amplification to capture short-term motion patterns. Extensive experiments on InterHuman and InterX demonstrate that our method achieves superior performance. Project page: https://aigc-explorer.github.io/TIMotion-page/

Zhenfeng Xue, Jiandang Yang, Jie Ren et al.

Image learning and colorization are hot spots in multimedia domain. Inspired by the learning capability of humans, in this paper, we propose an automatic colorization method with a learning framework. This method can be viewed as a hybrid of exemplar-based and learning-based method, and it decouples the colorization process and learning process so as to generate various color styles for the same gray image. The matching process in the exemplar-based colorization method can be regarded as a parameterized function, and we employ a large amount of color images as the training samples to fit the parameters. During the training process, the color images are the ground truths, and we learn the optimal parameters for the matching process by minimizing the errors in terms of the parameters for the matching function. To deal with images with various compositions, a global feature is introduced, which can be used to classify the images with respect to their compositions, and then learn the optimal matching parameters for each image category individually. What's more, a spatial consistency based post-processing is design to smooth the extracted color information from the reference image to remove matching errors. Extensive experiments are conducted to verify the effectiveness of the method, and it achieves comparable performance against the state-of-the-art colorization algorithms.

Shipeng Bai, Jun Chen, Xintian Shen et al.

Structured pruning and quantization are promising approaches for reducing the inference time and memory footprint of neural networks. However, most existing methods require the original training dataset to fine-tune the model. This not only brings heavy resource consumption but also is not possible for applications with sensitive or proprietary data due to privacy and security concerns. Therefore, a few data-free methods are proposed to address this problem, but they perform data-free pruning and quantization separately, which does not explore the complementarity of pruning and quantization. In this paper, we propose a novel framework named Unified Data-Free Compression(UDFC), which performs pruning and quantization simultaneously without any data and fine-tuning process. Specifically, UDFC starts with the assumption that the partial information of a damaged(e.g., pruned or quantized) channel can be preserved by a linear combination of other channels, and then derives the reconstruction form from the assumption to restore the information loss due to compression. Finally, we formulate the reconstruction error between the original network and its compressed network, and theoretically deduce the closed-form solution. We evaluate the UDFC on the large-scale image classification task and obtain significant improvements over various network architectures and compression methods. For example, we achieve a 20.54% accuracy improvement on ImageNet dataset compared to SOTA method with 30% pruning ratio and 6-bit quantization on ResNet-34.

Shaojie Li, Sheng Ouyang, Yong Liu

The theoretical analysis of spectral clustering mainly focuses on consistency, while there is relatively little research on its generalization performance. In this paper, we study the excess risk bounds of the popular spectral clustering algorithms: \emph{relaxed} RatioCut and \emph{relaxed} NCut. Firstly, we show that their excess risk bounds between the empirical continuous optimal solution and the population-level continuous optimal solution have a $\mathcal{O}(1/\sqrt{n})$ convergence rate, where $n$ is the sample size. Secondly, we show the fundamental quantity in influencing the excess risk between the empirical discrete optimal solution and the population-level discrete optimal solution. At the empirical level, algorithms can be designed to reduce this quantity. Based on our theoretical analysis, we propose two novel algorithms that can not only penalize this quantity, but also cluster the out-of-sample data without re-eigendecomposition on the overall sample. Experiments verify the effectiveness of the proposed algorithms.

Kai Su, Yoichi Tomioka, Qiangfu Zhao et al.

In the realm of Tiny AI, we introduce ``You Only Look at Interested Cells" (YOLIC), an efficient method for object localization and classification on edge devices. Through seamlessly blending the strengths of semantic segmentation and object detection, YOLIC offers superior computational efficiency and precision. By adopting Cells of Interest for classification instead of individual pixels, YOLIC encapsulates relevant information, reduces computational load, and enables rough object shape inference. Importantly, the need for bounding box regression is obviated, as YOLIC capitalizes on the predetermined cell configuration that provides information about potential object location, size, and shape. To tackle the issue of single-label classification limitations, a multi-label classification approach is applied to each cell for effectively recognizing overlapping or closely situated objects. This paper presents extensive experiments on multiple datasets to demonstrate that YOLIC achieves detection performance comparable to the state-of-the-art YOLO algorithms while surpassing in speed, exceeding 30fps on a Raspberry Pi 4B CPU. All resources related to this study, including datasets, cell designer, image annotation tool, and source code, have been made publicly available on our project website at https://kai3316.github.io/yolic.github.io

Junyu Zhu, Lina Liu, Yong Liu et al.

The great potential of unsupervised monocular depth estimation has been demonstrated by many works due to low annotation cost and impressive accuracy comparable to supervised methods. To further improve the performance, recent works mainly focus on designing more complex network structures and exploiting extra supervised information, e.g., semantic segmentation. These methods optimize the models by exploiting the reconstructed relationship between the target and reference images in varying degrees. However, previous methods prove that this image reconstruction optimization is prone to get trapped in local minima. In this paper, our core idea is to guide the optimization with prior knowledge from pretrained Flow-Net. And we show that the bottleneck of unsupervised monocular depth estimation can be broken with our simple but effective framework named FG-Depth. In particular, we propose (i) a flow distillation loss to replace the typical photometric loss that limits the capacity of the model and (ii) a prior flow based mask to remove invalid pixels that bring the noise in training loss. Extensive experiments demonstrate the effectiveness of each component, and our approach achieves state-of-the-art results on both KITTI and NYU-Depth-v2 datasets.

Yue Han, Jiangning Zhang, Junwei Zhu et al.

This work presents FaceX framework, a novel facial generalist model capable of handling diverse facial tasks simultaneously. To achieve this goal, we initially formulate a unified facial representation for a broad spectrum of facial editing tasks, which macroscopically decomposes a face into fundamental identity, intra-personal variation, and environmental factors. Based on this, we introduce Facial Omni-Representation Decomposing (FORD) for seamless manipulation of various facial components, microscopically decomposing the core aspects of most facial editing tasks. Furthermore, by leveraging the prior of a pretrained StableDiffusion (SD) to enhance generation quality and accelerate training, we design Facial Omni-Representation Steering (FORS) to first assemble unified facial representations and then effectively steer the SD-aware generation process by the efficient Facial Representation Controller (FRC). %Without any additional features, Our versatile FaceX achieves competitive performance compared to elaborate task-specific models on popular facial editing tasks. Full codes and models will be available at https://github.com/diffusion-facex/FaceX.

Zhucun Xue, Jiangning Zhang, Teng Hu et al.

The quality of the video dataset (image quality, resolution, and fine-grained caption) greatly influences the performance of the video generation model. The growing demand for video applications sets higher requirements for high-quality video generation models. For example, the generation of movie-level Ultra-High Definition (UHD) videos and the creation of 4K short video content. However, the existing public datasets cannot support related research and applications. In this paper, we first propose a high-quality open-sourced UHD-4K (22.4\% of which are 8K) text-to-video dataset named UltraVideo, which contains a wide range of topics (more than 100 kinds), and each video has 9 structured captions with one summarized caption (average of 824 words). Specifically, we carefully design a highly automated curation process with four stages to obtain the final high-quality dataset: \textit{i)} collection of diverse and high-quality video clips. \textit{ii)} statistical data filtering. \textit{iii)} model-based data purification. \textit{iv)} generation of comprehensive, structured captions. In addition, we expand Wan to UltraWan-1K/-4K, which can natively generate high-quality 1K/4K videos with more consistent text controllability, demonstrating the effectiveness of our data curation.We believe that this work can make a significant contribution to future research on UHD video generation. UltraVideo dataset and UltraWan models are available at https://xzc-zju.github.io/projects/UltraVideo.

Haocheng Yu, Yaxiong Wu, Hao Wang et al.

Interactive recommendation is a typical information-seeking task that allows users to interactively express their needs through natural language and obtain personalized recommendations. Large language model-powered (LLM-powered) agents have become a new paradigm in interactive recommendations, effectively capturing users' real-time needs and enhancing personalized experiences. However, due to limited planning and generalization capabilities, existing formulations of LLM-powered interactive recommender agents struggle to effectively address diverse and complex user intents, such as intuitive, unrefined, or occasionally ambiguous requests. To tackle this challenge, we propose a novel thought-augmented interactive recommender agent system (TAIRA) that addresses complex user intents through distilled thought patterns. Specifically, TAIRA is designed as an LLM-powered multi-agent system featuring a manager agent that orchestrates recommendation tasks by decomposing user needs and planning subtasks, with its planning capacity strengthened through Thought Pattern Distillation (TPD), a thought-augmentation method that extracts high-level thoughts from the agent's and human experts' experiences. Moreover, we designed a set of user simulation schemes to generate personalized queries of different difficulties and evaluate the recommendations based on specific datasets. Through comprehensive experiments conducted across multiple datasets, TAIRA exhibits significantly enhanced performance compared to existing methods. Notably, TAIRA shows a greater advantage on more challenging tasks while generalizing effectively on novel tasks, further validating its superiority in managing complex user intents within interactive recommendation systems. The code is publicly available at:https://github.com/Alcein/TAIRA.

Lei Zhu, Jun Zhou, Rick Siow Mong Goh et al.

Vision Transformer has recently gained tremendous popularity in medical image segmentation task due to its superior capability in capturing long-range dependencies. However, transformer requires a large amount of labeled data to be effective, which hinders its applicability in annotation scarce semi-supervised learning scenario where only limited labeled data is available. State-of-the-art semi-supervised learning methods propose combinatorial CNN-Transformer learning to cross teach a transformer with a convolutional neural network, which achieves promising results. However, it remains a challenging task to effectively train the transformer with limited labeled data. In this paper, we propose an adversarial masked image modeling method to fully unleash the potential of transformer for semi-supervised medical image segmentation. The key challenge in semi-supervised learning with transformer lies in the lack of sufficient supervision signal. To this end, we propose to construct an auxiliary masked domain from original domain with masked image modeling and train the transformer to predict the entire segmentation mask with masked inputs to increase supervision signal. We leverage the original labels from labeled data and pseudo-labels from unlabeled data to learn the masked domain. To further benefit the original domain from masked domain, we provide a theoretical analysis of our method from a multi-domain learning perspective and devise a novel adversarial training loss to reduce the domain gap between the original and masked domain, which boosts semi-supervised learning performance. We also extend adversarial masked image modeling to CNN network. Extensive experiments on three public medical image segmentation datasets demonstrate the effectiveness of our method, where our method outperforms existing methods significantly. Our code is publicly available at https://github.com/zlheui/AdvMIM.

Guanghao Zhu, Lin Liu, Yuhao Hu et al.

Micro-expressions are subtle facial movements that occur spontaneously when people try to conceal real emotions. Micro-expression recognition is crucial in many fields, including criminal analysis and psychotherapy. However, micro-expression recognition is challenging since micro-expressions have low intensity and public datasets are small in size. To this end, a three-stream temporal-shift attention network based on self-knowledge distillation is proposed in this paper. Firstly, to address the low intensity of muscle movements, we utilize learning-based motion magnification modules to enhance the intensity of muscle movements. Secondly, we employ efficient channel attention modules in the local-spatial stream to make the network focus on facial regions that are highly relevant to micro-expressions. In addition, temporal shift modules are used in the dynamic-temporal stream, which enables temporal modeling with no additional parameters by mixing motion information from two different temporal domains. Furthermore, we introduce self-knowledge distillation into the micro-expression recognition task by introducing auxiliary classifiers and using the deepest section of the network for supervision, encouraging all blocks to fully explore the features of the training set. Finally, extensive experiments are conducted on five publicly available micro-expression datasets. The experimental results demonstrate that our network outperforms other existing methods and achieves new state-of-the-art performance. Our code is available at https://github.com/GuanghaoZhu663/SKD-TSTSAN.

Xiuchao Sui, Shaohua Li, Xue Geng et al.

Optical flow estimation aims to find the 2D motion field by identifying corresponding pixels between two images. Despite the tremendous progress of deep learning-based optical flow methods, it remains a challenge to accurately estimate large displacements with motion blur. This is mainly because the correlation volume, the basis of pixel matching, is computed as the dot product of the convolutional features of the two images. The locality of convolutional features makes the computed correlations susceptible to various noises. On large displacements with motion blur, noisy correlations could cause severe errors in the estimated flow. To overcome this challenge, we propose a new architecture "CRoss-Attentional Flow Transformer" (CRAFT), aiming to revitalize the correlation volume computation. In CRAFT, a Semantic Smoothing Transformer layer transforms the features of one frame, making them more global and semantically stable. In addition, the dot-product correlations are replaced with transformer Cross-Frame Attention. This layer filters out feature noises through the Query and Key projections, and computes more accurate correlations. On Sintel (Final) and KITTI (foreground) benchmarks, CRAFT has achieved new state-of-the-art performance. Moreover, to test the robustness of different models on large motions, we designed an image shifting attack that shifts input images to generate large artificial motions. Under this attack, CRAFT performs much more robustly than two representative methods, RAFT and GMA. The code of CRAFT is is available at https://github.com/askerlee/craft.

Ying Chen, Dihe Huang, Shang Xu et al.

Local image feature matching under large appearance, viewpoint, and distance changes is challenging yet important. Conventional methods detect and match tentative local features across the whole images, with heuristic consistency checks to guarantee reliable matches. In this paper, we introduce a novel Overlap Estimation method conditioned on image pairs with TRansformer, named OETR, to constrain local feature matching in the commonly visible region. OETR performs overlap estimation in a two-step process of feature correlation and then overlap regression. As a preprocessing module, OETR can be plugged into any existing local feature detection and matching pipeline, to mitigate potential view angle or scale variance. Intensive experiments show that OETR can boost state-of-the-art local feature matching performance substantially, especially for image pairs with small shared regions. The code will be publicly available at https://github.com/AbyssGaze/OETR.

Jiajun Lv, Kewei Hu, Jinhong Xu et al.

In this paper, we propose a highly accurate continuous-time trajectory estimation framework dedicated to SLAM (Simultaneous Localization and Mapping) applications, which enables fuse high-frequency and asynchronous sensor data effectively. We apply the proposed framework in a 3D LiDAR-inertial system for evaluations. The proposed method adopts a non-rigid registration method for continuous-time trajectory estimation and simultaneously removing the motion distortion in LiDAR scans. Additionally, we propose a two-state continuous-time trajectory correction method to efficiently and efficiently tackle the computationally-intractable global optimization problem when loop closure happens. We examine the accuracy of the proposed approach on several publicly available datasets and the data we collected. The experimental results indicate that the proposed method outperforms the discrete-time methods regarding accuracy especially when aggressive motion occurs. Furthermore, we open source our code at \url{https://github.com/APRIL-ZJU/clins} to benefit research community.

Mengmeng Wang, Jiazheng Xing, Boyuan Jiang et al.

Recently, the rise of large-scale vision-language pretrained models like CLIP, coupled with the technology of Parameter-Efficient FineTuning (PEFT), has captured substantial attraction in video action recognition. Nevertheless, prevailing approaches tend to prioritize strong supervised performance at the expense of compromising the models' generalization capabilities during transfer. In this paper, we introduce a novel Multimodal, Multi-task CLIP adapting framework named \name to address these challenges, preserving both high supervised performance and robust transferability. Firstly, to enhance the individual modality architectures, we introduce multimodal adapters to both the visual and text branches. Specifically, we design a novel visual TED-Adapter, that performs global Temporal Enhancement and local temporal Difference modeling to improve the temporal representation capabilities of the visual encoder. Moreover, we adopt text encoder adapters to strengthen the learning of semantic label information. Secondly, we design a multi-task decoder with a rich set of supervisory signals to adeptly satisfy the need for strong supervised performance and generalization within a multimodal framework. Experimental results validate the efficacy of our approach, demonstrating exceptional performance in supervised learning while maintaining strong generalization in zero-shot scenarios.

Mengmeng Wang, Teli Ma, Xingxing Zuo et al.

3D LiDAR-based single object tracking (SOT) has gained increasing attention as it plays a crucial role in 3D applications such as autonomous driving. The central problem is how to learn a target-aware representation from the sparse and incomplete point clouds. In this paper, we propose a novel Correlation Pyramid Network (CorpNet) with a unified encoder and a motion-factorized decoder. Specifically, the encoder introduces multi-level self attentions and cross attentions in its main branch to enrich the template and search region features and realize their fusion and interaction, respectively. Additionally, considering the sparsity characteristics of the point clouds, we design a lateral correlation pyramid structure for the encoder to keep as many points as possible by integrating hierarchical correlated features. The output features of the search region from the encoder can be directly fed into the decoder for predicting target locations without any extra matcher. Moreover, in the decoder of CorpNet, we design a motion-factorized head to explicitly learn the different movement patterns of the up axis and the x-y plane together. Extensive experiments on two commonly-used datasets show our CorpNet achieves state-of-the-art results while running in real-time.

Zhuofei Huang, Jianlin Liu, Shang Xu et al.

Multi-view stereo depth estimation based on cost volume usually works better than self-supervised monocular depth estimation except for moving objects and low-textured surfaces. So in this paper, we propose a multi-frame depth estimation framework which monocular depth can be refined continuously by multi-frame sequential constraints, leveraging a Bayesian fusion layer within several iterations. Both monocular and multi-view networks can be trained with no depth supervision. Our method also enhances the interpretability when combining monocular estimation with multi-view cost volume. Detailed experiments show that our method surpasses state-of-the-art unsupervised methods utilizing single or multiple frames at test time on KITTI benchmark.

Chao Xu, Shaoting Zhu, Junwei Zhu et al.

Multimodal-driven talking face generation refers to animating a portrait with the given pose, expression, and gaze transferred from the driving image and video, or estimated from the text and audio. However, existing methods ignore the potential of text modal, and their generators mainly follow the source-oriented feature rearrange paradigm coupled with unstable GAN frameworks. In this work, we first represent the emotion in the text prompt, which could inherit rich semantics from the CLIP, allowing flexible and generalized emotion control. We further reorganize these tasks as the target-oriented texture transfer and adopt the Diffusion Models. More specifically, given a textured face as the source and the rendered face projected from the desired 3DMM coefficients as the target, our proposed Texture-Geometry-aware Diffusion Model decomposes the complex transfer problem into multi-conditional denoising process, where a Texture Attention-based module accurately models the correspondences between appearance and geometry cues contained in source and target conditions, and incorporate extra implicit information for high-fidelity talking face generation. Additionally, TGDM can be gracefully tailored for face swapping. We derive a novel paradigm free of unstable seesaw-style optimization, resulting in simple, stable, and effective training and inference schemes. Extensive experiments demonstrate the superiority of our method.

Chao Xu, Junwei Zhu, Jiangning Zhang et al.

Recently, emotional talking face generation has received considerable attention. However, existing methods only adopt one-hot coding, image, or audio as emotion conditions, thus lacking flexible control in practical applications and failing to handle unseen emotion styles due to limited semantics. They either ignore the one-shot setting or the quality of generated faces. In this paper, we propose a more flexible and generalized framework. Specifically, we supplement the emotion style in text prompts and use an Aligned Multi-modal Emotion encoder to embed the text, image, and audio emotion modality into a unified space, which inherits rich semantic prior from CLIP. Consequently, effective multi-modal emotion space learning helps our method support arbitrary emotion modality during testing and could generalize to unseen emotion styles. Besides, an Emotion-aware Audio-to-3DMM Convertor is proposed to connect the emotion condition and the audio sequence to structural representation. A followed style-based High-fidelity Emotional Face generator is designed to generate arbitrary high-resolution realistic identities. Our texture generator hierarchically learns flow fields and animated faces in a residual manner. Extensive experiments demonstrate the flexibility and generalization of our method in emotion control and the effectiveness of high-quality face synthesis.

Fan Wang, Chaofan Zhang, Fulin Tang et al.

Mapping and localization are two essential tasks for mobile robots in real-world applications. However, largescale and dynamic scenes challenge the accuracy and robustness of most current mature solutions. This situation becomes even worse when computational resources are limited. In this paper, we present a novel lightweight object-level mapping and localization method with high accuracy and robustness. Different from previous methods, our method does not need a prior constructed precise geometric map, which greatly releases the storage burden, especially for large-scale navigation. We use object-level features with both semantic and geometric information to model landmarks in the environment. Particularly, a learning topological primitive is first proposed to efficiently obtain and organize the object-level landmarks. On the basis of this, we use a robot-centric mapping framework to represent the environment as a semantic topology graph and relax the burden of maintaining global consistency at the same time. Besides, a hierarchical memory management mechanism is introduced to improve the efficiency of online mapping with limited computational resources. Based on the proposed map, the robust localization is achieved by constructing a novel local semantic scene graph descriptor, and performing multi-constraint graph matching to compare scene similarity. Finally, we test our method on a low-cost embedded platform to demonstrate its advantages. Experimental results on a large scale and multi-session real-world environment show that the proposed method outperforms the state of arts in terms of lightweight and robustness.

Jiangning Zhang, Chao Xu, Jian Li et al.

In the practical application of restoring low-resolution gray-scale images, we generally need to run three separate processes of image colorization, super-resolution, and dows-sampling operation for the target device. However, this pipeline is redundant and inefficient for the independent processes, and some inner features could have been shared. Therefore, we present an efficient paradigm to perform {S}imultaneously Image {C}olorization and {S}uper-resolution (SCS) and propose an end-to-end SCSNet to achieve this goal. The proposed method consists of two parts: colorization branch for learning color information that employs the proposed plug-and-play \emph{Pyramid Valve Cross Attention} (PVCAttn) module to aggregate feature maps between source and reference images; and super-resolution branch for integrating color and texture information to predict target images, which uses the designed \emph{Continuous Pixel Mapping} (CPM) module to predict high-resolution images at continuous magnification. Furthermore, our SCSNet supports both automatic and referential modes that is more flexible for practical application. Abundant experiments demonstrate the superiority of our method for generating authentic images over state-of-the-art methods, e.g., averagely decreasing FID by 1.8$\downarrow$ and 5.1 $\downarrow$ compared with current best scores for automatic and referential modes, respectively, while owning fewer parameters (more than $\times$2$\downarrow$) and faster running speed (more than $\times$3$\uparrow$).

Xianfang Zeng, Jiangning Zhang, Liang Liu et al.

In spite of the success on benchmark datasets, most advanced face super-resolution models perform poorly in real scenarios since the remarkable domain gap between the real images and the synthesized training pairs. To tackle this problem, we propose a novel domain-adaptive degradation network for face super-resolution in the wild. This degradation network predicts a flow field along with an intermediate low resolution image. Then, the degraded counterpart is generated by warping the intermediate image. With the preference of capturing motion blur, such a model performs better at preserving identity consistency between the original images and the degraded. We further present the self-conditioned block for super-resolution network. This block takes the input image as a condition term to effectively utilize facial structure information, eliminating the reliance on explicit priors, e.g. facial landmarks or boundary. Our model achieves state-of-the-art performance on both CelebA and real-world face dataset. The former demonstrates the powerful generative ability of our proposed architecture while the latter shows great identity consistency and perceptual quality in real-world images.

Zizhang Li, Mengmeng Wang, Jianbiao Mei et al.

Referring image segmentation is a typical multi-modal task, which aims at generating a binary mask for referent described in given language expressions. Prior arts adopt a bimodal solution, taking images and languages as two modalities within an encoder-fusion-decoder pipeline. However, this pipeline is sub-optimal for the target task for two reasons. First, they only fuse high-level features produced by uni-modal encoders separately, which hinders sufficient cross-modal learning. Second, the uni-modal encoders are pre-trained independently, which brings inconsistency between pre-trained uni-modal tasks and the target multi-modal task. Besides, this pipeline often ignores or makes little use of intuitively beneficial instance-level features. To relieve these problems, we propose MaIL, which is a more concise encoder-decoder pipeline with a Mask-Image-Language trimodal encoder. Specifically, MaIL unifies uni-modal feature extractors and their fusion model into a deep modality interaction encoder, facilitating sufficient feature interaction across different modalities. Meanwhile, MaIL directly avoids the second limitation since no uni-modal encoders are needed anymore. Moreover, for the first time, we propose to introduce instance masks as an additional modality, which explicitly intensifies instance-level features and promotes finer segmentation results. The proposed MaIL set a new state-of-the-art on all frequently-used referring image segmentation datasets, including RefCOCO, RefCOCO+, and G-Ref, with significant gains, 3%-10% against previous best methods. Code will be released soon.

WeiFu Fu, CongChong Nie, Ting Sun et al.

This report introduces the technical details of the team FuXi-Fresher for LVIS Challenge 2021. Our method focuses on the problem in following two aspects: the long-tail distribution and the segmentation quality of mask and boundary. Based on the advanced HTC instance segmentation algorithm, we connect transformer backbone(Swin-L) through composite connections inspired by CBNetv2 to enhance the baseline results. To alleviate the problem of long-tail distribution, we design a Distribution Balanced method which includes dataset balanced and loss function balaced modules. Further, we use a Mask and Boundary Refinement method composed with mask scoring and refine-mask algorithms to improve the segmentation quality. In addition, we are pleasantly surprised to find that early stopping combined with EMA method can achieve a great improvement. Finally, by using multi-scale testing and increasing the upper limit of the number of objects detected per image, we achieved more than 45.4% boundary AP on the val set of LVIS Challenge 2021. On the test data of LVIS Challenge 2021, we rank 1st and achieve 48.1% AP. Notably, our APr 47.5% is very closed to the APf 48.0%.

Ling Cheng, Wei Wei, Feida Zhu et al.

Recent advancements of image captioning have featured Visual-Semantic Fusion or Geometry-Aid attention refinement. However, those fusion-based models, they are still criticized for the lack of geometry information for inter and intra attention refinement. On the other side, models based on Geometry-Aid attention still suffer from the modality gap between visual and semantic information. In this paper, we introduce a novel Geometry-Entangled Visual Semantic Transformer (GEVST) network to realize the complementary advantages of Visual-Semantic Fusion and Geometry-Aid attention refinement. Concretely, a Dense-Cap model proposes some dense captions with corresponding geometry information at first. Then, to empower GEVST with the ability to bridge the modality gap among visual and semantic information, we build four parallel transformer encoders VV(Pure Visual), VS(Semantic fused to Visual), SV(Visual fused to Semantic), SS(Pure Semantic) for final caption generation. Both visual and semantic geometry features are used in the Fusion module and also the Self-Attention module for better attention measurement. To validate our model, we conduct extensive experiments on the MS-COCO dataset, the experimental results show that our GEVST model can obtain promising performance gains.

Fuzhao Xue, Ziji Shi, Futao Wei et al.

More transformer blocks with residual connections have recently achieved impressive results on various tasks. To achieve better performance with fewer trainable parameters, recent methods are proposed to go shallower by parameter sharing or model compressing along with the depth. However, weak modeling capacity limits their performance. Contrastively, going wider by inducing more trainable matrixes and parameters would produce a huge model requiring advanced parallelism to train and inference. In this paper, we propose a parameter-efficient framework, going wider instead of deeper. Specially, following existing works, we adapt parameter sharing to compress along depth. But, such deployment would limit the performance. To maximize modeling capacity, we scale along model width by replacing feed-forward network (FFN) with mixture-of-experts (MoE). Across transformer blocks, instead of sharing normalization layers, we propose to use individual layernorms to transform various semantic representations in a more parameter-efficient way. To evaluate our plug-and-run framework, we design WideNet and conduct comprehensive experiments on popular computer vision and natural language processing benchmarks. On ImageNet-1K, our best model outperforms Vision Transformer (ViT) by $1.5\%$ with $0.72 \times$ trainable parameters. Using $0.46 \times$ and $0.13 \times$ parameters, our WideNet can still surpass ViT and ViT-MoE by $0.8\%$ and $2.1\%$, respectively. On four natural language processing datasets, WideNet outperforms ALBERT by $1.8\%$ on average and surpass BERT using factorized embedding parameterization by $0.8\%$ with fewer parameters.

Chenyi Lei, Shixian Luo, Yong Liu et al.

The pre-trained neural models have recently achieved impressive performances in understanding multimodal content. However, it is still very challenging to pre-train neural models for video and language understanding, especially for Chinese video-language data, due to the following reasons. Firstly, existing video-language pre-training algorithms mainly focus on the co-occurrence of words and video frames, but ignore other valuable semantic and structure information of video-language content, e.g., sequential order and spatiotemporal relationships. Secondly, there exist conflicts between video sentence alignment and other proxy tasks. Thirdly, there is a lack of large-scale and high-quality Chinese video-language datasets (e.g., including 10 million unique videos), which are the fundamental success conditions for pre-training techniques. In this work, we propose a novel video-language understanding framework named VICTOR, which stands for VIdeo-language understanding via Contrastive mulTimOdal pRe-training. Besides general proxy tasks such as masked language modeling, VICTOR constructs several novel proxy tasks under the contrastive learning paradigm, making the model be more robust and able to capture more complex multimodal semantic and structural relationships from different perspectives. VICTOR is trained on a large-scale Chinese video-language dataset, including over 10 million complete videos with corresponding high-quality textual descriptions. We apply the pre-trained VICTOR model to a series of downstream applications and demonstrate its superior performances, comparing against the state-of-the-art pre-training methods such as VideoBERT and UniVL. The codes and trained checkpoints will be publicly available to nourish further developments of the research community.

Senrong You, Yong Liu, Baiying Lei et al.

Magnetic resonance imaging plays an important role in computer-aided diagnosis and brain exploration. However, limited by hardware, scanning time and cost, it's challenging to acquire high-resolution (HR) magnetic resonance (MR) image clinically. In this paper, fine perceptive generative adversarial networks (FP-GANs) is proposed to produce HR MR images from low-resolution counterparts. It can cope with the detail insensitive problem of the existing super-resolution model in a divide-and-conquer manner. Specifically, FP-GANs firstly divides an MR image into low-frequency global approximation and high-frequency anatomical texture in wavelet domain. Then each sub-band generative adversarial network (sub-band GAN) conquers the super-resolution procedure of each single sub-band image. Meanwhile, sub-band attention is deployed to tune focus between global and texture information. It can focus on sub-band images instead of feature maps to further enhance the anatomical reconstruction ability of FP-GANs. In addition, inverse discrete wavelet transformation (IDWT) is integrated into model for taking the reconstruction of whole image into account. Experiments on MultiRes_7T dataset demonstrate that FP-GANs outperforms the competing methods quantitatively and qualitatively.

Shanqi Liu, Licheng Wen, Jinhao Cui et al.

Multi-agent path finding in formation has many potential real-world applications like mobile warehouse robots. However, previous multi-agent path finding (MAPF) methods hardly take formation into consideration. Furthermore, they are usually centralized planners and require the whole state of the environment. Other decentralized partially observable approaches to MAPF are reinforcement learning (RL) methods. However, these RL methods encounter difficulties when learning path finding and formation problem at the same time. In this paper, we propose a novel decentralized partially observable RL algorithm that uses a hierarchical structure to decompose the multi objective task into unrelated ones. It also calculates a theoretical weight that makes every task reward has equal influence on the final RL value function. Additionally, we introduce a communication method that helps agents cooperate with each other. Experiments in simulation show that our method outperforms other end-to-end RL methods and our method can naturally scale to large world sizes where centralized planner struggles. We also deploy and validate our method in a real world scenario.