Yushi Lan, Yuan Liu, Maoqing Tian, Xinchi Zhou, Xuesen Zhang, Shuai Yi, Hongsheng Li
Although person re-identification (ReID) has achieved significant improvement recently by enforcing part alignment, it is still a challenging task when it comes to distinguishing visually similar identities or identifying the occluded person. In these scenarios, magnifying details in each part features and selectively fusing them together may provide a feasible solution. In this work, we propose MagnifierNet, a triple-branch network which accurately mines details from whole to parts. Firstly, the holistic salient features are encoded by a global branch. Secondly, to enhance detailed representation for each semantic region, the "Semantic Adversarial Branch" is designed to learn from dynamically generated semantic-occluded samples during training. Meanwhile, we introduce "Semantic Fusion Branch" to filter out irrelevant noises by selectively fusing semantic region information sequentially. To further improve feature diversity, we introduce a novel loss function "Semantic Diversity Loss" to remove redundant overlaps across learned semantic representations. State-of-the-art performance has been achieved on three benchmarks by large margins. Specifically, the mAP score is improved by 6% and 5% on the most challenging CUHK03-L and CUHK03-D benchmarks.
Jianbo Liu, Junjun He, Jimmy S. Ren, Yu Qiao, Hongsheng Li
Long-range contextual information is essential for achieving high-performance semantic segmentation. Previous feature re-weighting methods demonstrate that using global context for re-weighting feature channels can effectively improve the accuracy of semantic segmentation. However, the globally-sharing feature re-weighting vector might not be optimal for regions of different classes in the input image. In this paper, we propose a Context-adaptive Convolution Network (CaC-Net) to predict a spatially-varying feature weighting vector for each spatial location of the semantic feature maps. In CaC-Net, a set of context-adaptive convolution kernels are predicted from the global contextual information in a parameter-efficient manner. When used for convolution with the semantic feature maps, the predicted convolutional kernels can generate the spatially-varying feature weighting factors capturing both global and local contextual information. Comprehensive experimental results show that our CaC-Net achieves superior segmentation performance on three public datasets, PASCAL Context, PASCAL VOC 2012 and ADE20K.
Xiao Zhang, Rui Zhao, Yu Qiao, Xiaogang Wang, Hongsheng Li
The cosine-based softmax losses and their variants achieve great success in deep learning based face recognition. However, hyperparameter settings in these losses have significant influences on the optimization path as well as the final recognition performance. Manually tuning those hyperparameters heavily relies on user experience and requires many training tricks. In this paper, we investigate in depth the effects of two important hyperparameters of cosine-based softmax losses, the scale parameter and angular margin parameter, by analyzing how they modulate the predicted classification probability. Based on these analysis, we propose a novel cosine-based softmax loss, AdaCos, which is hyperparameter-free and leverages an adaptive scale parameter to automatically strengthen the training supervisions during the training process. We apply the proposed AdaCos loss to large-scale face verification and identification datasets, including LFW, MegaFace, and IJB-C 1:1 Verification. Our results show that training deep neural networks with the AdaCos loss is stable and able to achieve high face recognition accuracy. Our method outperforms state-of-the-art softmax losses on all the three datasets.
Yixiao Ge, Feng Zhu, Dapeng Chen, Rui Zhao, Hongsheng Li
Domain adaptive object re-ID aims to transfer the learned knowledge from the labeled source domain to the unlabeled target domain to tackle the open-class re-identification problems. Although state-of-the-art pseudo-label-based methods have achieved great success, they did not make full use of all valuable information because of the domain gap and unsatisfying clustering performance. To solve these problems, we propose a novel self-paced contrastive learning framework with hybrid memory. The hybrid memory dynamically generates source-domain class-level, target-domain cluster-level and un-clustered instance-level supervisory signals for learning feature representations. Different from the conventional contrastive learning strategy, the proposed framework jointly distinguishes source-domain classes, and target-domain clusters and un-clustered instances. Most importantly, the proposed self-paced method gradually creates more reliable clusters to refine the hybrid memory and learning targets, and is shown to be the key to our outstanding performance. Our method outperforms state-of-the-arts on multiple domain adaptation tasks of object re-ID and even boosts the performance on the source domain without any extra annotations. Our generalized version on unsupervised object re-ID surpasses state-of-the-art algorithms by considerable 16.7% and 7.9% on Market-1501 and MSMT17 benchmarks.
Zixuan Huang, Junming Fan, Shenggan Cheng, Shuai Yi, Xiaogang Wang, Hongsheng Li
Dense depth cues are important and have wide applications in various computer vision tasks. In autonomous driving, LIDAR sensors are adopted to acquire depth measurements around the vehicle to perceive the surrounding environments. However, depth maps obtained by LIDAR are generally sparse because of its hardware limitation. The task of depth completion attracts increasing attention, which aims at generating a dense depth map from an input sparse depth map. To effectively utilize multi-scale features, we propose three novel sparsity-invariant operations, based on which, a sparsity-invariant multi-scale encoder-decoder network (HMS-Net) for handling sparse inputs and sparse feature maps is also proposed. Additional RGB features could be incorporated to further improve the depth completion performance. Our extensive experiments and component analysis on two public benchmarks, KITTI depth completion benchmark and NYU-depth-v2 dataset, demonstrate the effectiveness of the proposed approach. As of Aug. 12th, 2018, on KITTI depth completion leaderboard, our proposed model without RGB guidance ranks first among all peer-reviewed methods without using RGB information, and our model with RGB guidance ranks second among all RGB-guided methods.
Shaoshuai Shi, Xiaogang Wang, Hongsheng Li
In this paper, we propose PointRCNN for 3D object detection from raw point cloud. The whole framework is composed of two stages: stage-1 for the bottom-up 3D proposal generation and stage-2 for refining proposals in the canonical coordinates to obtain the final detection results. Instead of generating proposals from RGB image or projecting point cloud to bird's view or voxels as previous methods do, our stage-1 sub-network directly generates a small number of high-quality 3D proposals from point cloud in a bottom-up manner via segmenting the point cloud of the whole scene into foreground points and background. The stage-2 sub-network transforms the pooled points of each proposal to canonical coordinates to learn better local spatial features, which is combined with global semantic features of each point learned in stage-1 for accurate box refinement and confidence prediction. Extensive experiments on the 3D detection benchmark of KITTI dataset show that our proposed architecture outperforms state-of-the-art methods with remarkable margins by using only point cloud as input. The code is available at https://github.com/sshaoshuai/PointRCNN.
Yi Zhang, Dasong Li, Ka Lung Law, Xiaogang Wang, Hongwei Qin, Hongsheng Li
The lack of large-scale noisy-clean image pairs restricts supervised denoising methods' deployment in actual applications. While existing unsupervised methods are able to learn image denoising without ground-truth clean images, they either show poor performance or work under impractical settings (e.g., paired noisy images). In this paper, we present a practical unsupervised image denoising method to achieve state-of-the-art denoising performance. Our method only requires single noisy images and a noise model, which is easily accessible in practical raw image denoising. It performs two steps iteratively: (1) Constructing a noisier-noisy dataset with random noise from the noise model; (2) training a model on the noisier-noisy dataset and using the trained model to refine noisy images to obtain the targets used in the next round. We further approximate our full iterative method with a fast algorithm for more efficient training while keeping its original high performance. Experiments on real-world, synthetic, and correlated noise show that our proposed unsupervised denoising approach has superior performances over existing unsupervised methods and competitive performance with supervised methods. In addition, we argue that existing denoising datasets are of low quality and contain only a small number of scenes. To evaluate raw image denoising performance in real-world applications, we build a high-quality raw image dataset SenseNoise-500 that contains 500 real-life scenes. The dataset can serve as a strong benchmark for better evaluating raw image denoising. Code and dataset will be released at https://github.com/zhangyi-3/IDR
Renrui Zhang, Rongyao Fang, Wei Zhang, Peng Gao, Kunchang Li, Jifeng Dai, Yu Qiao, Hongsheng Li
Contrastive Vision-Language Pre-training, known as CLIP, has provided a new paradigm for learning visual representations by using large-scale contrastive image-text pairs. It shows impressive performance on zero-shot knowledge transfer to downstream tasks. To further enhance CLIP's few-shot capability, CLIP-Adapter proposed to fine-tune a lightweight residual feature adapter and significantly improves the performance for few-shot classification. However, such a process still needs extra training and computational resources. In this paper, we propose \textbf{T}raining-Free CL\textbf{IP}-\textbf{Adapter} (\textbf{Tip-Adapter}), which not only inherits CLIP's training-free advantage but also performs comparably or even better than CLIP-Adapter. Tip-Adapter does not require any back propagation for training the adapter, but creates the weights by a key-value cache model constructed from the few-shot training set. In this non-parametric manner, Tip-Adapter acquires well-performed adapter weights without any training, which is both efficient and effective. Moreover, the performance of Tip-Adapter can be further boosted by fine-tuning such properly initialized adapter for only a few epochs with super-fast convergence speed. We conduct extensive experiments of few-shot classification on ImageNet and other 10 datasets to demonstrate the superiority of proposed Tip-Adapter. The code will be released at \url{https://github.com/gaopengcuhk/Tip-Adapter}.
Xihui Liu, Zhe Lin, Jianming Zhang, Handong Zhao, Quan Tran, Xiaogang Wang, Hongsheng Li
We propose a novel algorithm, named Open-Edit, which is the first attempt on open-domain image manipulation with open-vocabulary instructions. It is a challenging task considering the large variation of image domains and the lack of training supervision. Our approach takes advantage of the unified visual-semantic embedding space pretrained on a general image-caption dataset, and manipulates the embedded visual features by applying text-guided vector arithmetic on the image feature maps. A structure-preserving image decoder then generates the manipulated images from the manipulated feature maps. We further propose an on-the-fly sample-specific optimization approach with cycle-consistency constraints to regularize the manipulated images and force them to preserve details of the source images. Our approach shows promising results in manipulating open-vocabulary color, texture, and high-level attributes for various scenarios of open-domain images.
Ziniu Wan, Zhengjia Li, Maoqing Tian, Jianbo Liu, Shuai Yi, Hongsheng Li
3D human shape and pose estimation is the essential task for human motion analysis, which is widely used in many 3D applications. However, existing methods cannot simultaneously capture the relations at multiple levels, including spatial-temporal level and human joint level. Therefore they fail to make accurate predictions in some hard scenarios when there is cluttered background, occlusion, or extreme pose. To this end, we propose Multi-level Attention Encoder-Decoder Network (MAED), including a Spatial-Temporal Encoder (STE) and a Kinematic Topology Decoder (KTD) to model multi-level attentions in a unified framework. STE consists of a series of cascaded blocks based on Multi-Head Self-Attention, and each block uses two parallel branches to learn spatial and temporal attention respectively. Meanwhile, KTD aims at modeling the joint level attention. It regards pose estimation as a top-down hierarchical process similar to SMPL kinematic tree. With the training set of 3DPW, MAED outperforms previous state-of-the-art methods by 6.2, 7.2, and 2.4 mm of PA-MPJPE on the three widely used benchmarks 3DPW, MPI-INF-3DHP, and Human3.6M respectively. Our code is available at https://github.com/ziniuwan/maed.
Zhipeng Luo, Zhongang Cai, Changqing Zhou, Gongjie Zhang, Haiyu Zhao, Shuai Yi, Shijian Lu, Hongsheng Li, Shanghang Zhang, Ziwei Liu
Deep learning-based 3D object detection has achieved unprecedented success with the advent of large-scale autonomous driving datasets. However, drastic performance degradation remains a critical challenge for cross-domain deployment. In addition, existing 3D domain adaptive detection methods often assume prior access to the target domain annotations, which is rarely feasible in the real world. To address this challenge, we study a more realistic setting, unsupervised 3D domain adaptive detection, which only utilizes source domain annotations. 1) We first comprehensively investigate the major underlying factors of the domain gap in 3D detection. Our key insight is that geometric mismatch is the key factor of domain shift. 2) Then, we propose a novel and unified framework, Multi-Level Consistency Network (MLC-Net), which employs a teacher-student paradigm to generate adaptive and reliable pseudo-targets. MLC-Net exploits point-, instance- and neural statistics-level consistency to facilitate cross-domain transfer. Extensive experiments demonstrate that MLC-Net outperforms existing state-of-the-art methods (including those using additional target domain information) on standard benchmarks. Notably, our approach is detector-agnostic, which achieves consistent gains on both single- and two-stage 3D detectors.
Ning Wang, Guangming Zhu, Liang Zhang, Peiyi Shen, Hongsheng Li, Cong Hua
For a given video-based Human-Object Interaction scene, modeling the spatio-temporal relationship between humans and objects are the important cue to understand the contextual information presented in the video. With the effective spatio-temporal relationship modeling, it is possible not only to uncover contextual information in each frame but also to directly capture inter-time dependencies. It is more critical to capture the position changes of human and objects over the spatio-temporal dimension when their appearance features may not show up significant changes over time. The full use of appearance features, the spatial location and the semantic information are also the key to improve the video-based Human-Object Interaction recognition performance. In this paper, Spatio-Temporal Interaction Graph Parsing Networks (STIGPN) are constructed, which encode the videos with a graph composed of human and object nodes. These nodes are connected by two types of relations: (i) spatial relations modeling the interactions between human and the interacted objects within each frame. (ii) inter-time relations capturing the long range dependencies between human and the interacted objects across frame. With the graph, STIGPN learn spatio-temporal features directly from the whole video-based Human-Object Interaction scenes. Multi-modal features and a multi-stream fusion strategy are used to enhance the reasoning capability of STIGPN. Two Human-Object Interaction video datasets, including CAD-120 and Something-Else, are used to evaluate the proposed architectures, and the state-of-the-art performance demonstrates the superiority of STIGPN.
Peng Gao, Minghang Zheng, Xiaogang Wang, Jifeng Dai, Hongsheng Li
The recently proposed Detection Transformer (DETR) model successfully applies Transformer to objects detection and achieves comparable performance with two-stage object detection frameworks, such as Faster-RCNN. However, DETR suffers from its slow convergence. Training DETR \cite{carion2020end} from scratch needs 500 epochs to achieve a high accuracy. To accelerate its convergence, we propose a simple yet effective scheme for improving the DETR framework, namely Spatially Modulated Co-Attention (SMCA) mechanism. The core idea of SMCA is to conduct regression-aware co-attention in DETR by constraining co-attention responses to be high near initially estimated bounding box locations. Our proposed SMCA increases DETR's convergence speed by replacing the original co-attention mechanism in the decoder while keeping other operations in DETR unchanged. Furthermore, by integrating multi-head and scale-selection attention designs into SMCA, our fully-fledged SMCA can achieve better performance compared to DETR with a dilated convolution-based backbone (45.6 mAP at 108 epochs vs. 43.3 mAP at 500 epochs). We perform extensive ablation studies on COCO dataset to validate the effectiveness of the proposed SMCA.
Xinge Zhu, Hui Zhou, Tai Wang, Fangzhou Hong, Wei Li, Yuexin Ma, Hongsheng Li, Ruigang Yang, Dahua Lin
State-of-the-art methods for driving-scene LiDAR-based perception (including point cloud semantic segmentation, panoptic segmentation and 3D detection, \etc) often project the point clouds to 2D space and then process them via 2D convolution. Although this cooperation shows the competitiveness in the point cloud, it inevitably alters and abandons the 3D topology and geometric relations. A natural remedy is to utilize the 3D voxelization and 3D convolution network. However, we found that in the outdoor point cloud, the improvement obtained in this way is quite limited. An important reason is the property of the outdoor point cloud, namely sparsity and varying density. Motivated by this investigation, we propose a new framework for the outdoor LiDAR segmentation, where cylindrical partition and asymmetrical 3D convolution networks are designed to explore the 3D geometric pattern while maintaining these inherent properties. The proposed model acts as a backbone and the learned features from this model can be used for downstream tasks such as point cloud semantic and panoptic segmentation or 3D detection. In this paper, we benchmark our model on these three tasks. For semantic segmentation, we evaluate the proposed model on several large-scale datasets, \ie, SemanticKITTI, nuScenes and A2D2. Our method achieves the state-of-the-art on the leaderboard of SemanticKITTI (both single-scan and multi-scan challenge), and significantly outperforms existing methods on nuScenes and A2D2 dataset. Furthermore, the proposed 3D framework also shows strong performance and good generalization on LiDAR panoptic segmentation and LiDAR 3D detection.
Kunchang Li, Yali Wang, Peng Gao, Guanglu Song, Yu Liu, Hongsheng Li, Yu Qiao
It is a challenging task to learn rich and multi-scale spatiotemporal semantics from high-dimensional videos, due to large local redundancy and complex global dependency between video frames. The recent advances in this research have been mainly driven by 3D convolutional neural networks and vision transformers. Although 3D convolution can efficiently aggregate local context to suppress local redundancy from a small 3D neighborhood, it lacks the capability to capture global dependency because of the limited receptive field. Alternatively, vision transformers can effectively capture long-range dependency by self-attention mechanism, while having the limitation on reducing local redundancy with blind similarity comparison among all the tokens in each layer. Based on these observations, we propose a novel Unified transFormer (UniFormer) which seamlessly integrates merits of 3D convolution and spatiotemporal self-attention in a concise transformer format, and achieves a preferable balance between computation and accuracy. Different from traditional transformers, our relation aggregator can tackle both spatiotemporal redundancy and dependency, by learning local and global token affinity respectively in shallow and deep layers. We conduct extensive experiments on the popular video benchmarks, e.g., Kinetics-400, Kinetics-600, and Something-Something V1&V2. With only ImageNet-1K pretraining, our UniFormer achieves 82.9%/84.8% top-1 accuracy on Kinetics-400/Kinetics-600, while requiring 10x fewer GFLOPs than other state-of-the-art methods. For Something-Something V1 and V2, our UniFormer achieves new state-of-the-art performances of 60.9% and 71.2% top-1 accuracy respectively. Code is available at https://github.com/Sense-X/UniFormer.
Renrui Zhang, Ziyu Guo, Wei Zhang, Kunchang Li, Xupeng Miao, Bin Cui, Yu Qiao, Peng Gao, Hongsheng Li
Recently, zero-shot and few-shot learning via Contrastive Vision-Language Pre-training (CLIP) have shown inspirational performance on 2D visual recognition, which learns to match images with their corresponding texts in open-vocabulary settings. However, it remains under explored that whether CLIP, pre-trained by large-scale image-text pairs in 2D, can be generalized to 3D recognition. In this paper, we identify such a setting is feasible by proposing PointCLIP, which conducts alignment between CLIP-encoded point cloud and 3D category texts. Specifically, we encode a point cloud by projecting it into multi-view depth maps without rendering, and aggregate the view-wise zero-shot prediction to achieve knowledge transfer from 2D to 3D. On top of that, we design an inter-view adapter to better extract the global feature and adaptively fuse the few-shot knowledge learned from 3D into CLIP pre-trained in 2D. By just fine-tuning the lightweight adapter in the few-shot settings, the performance of PointCLIP could be largely improved. In addition, we observe the complementary property between PointCLIP and classical 3D-supervised networks. By simple ensembling, PointCLIP boosts baseline's performance and even surpasses state-of-the-art models. Therefore, PointCLIP is a promising alternative for effective 3D point cloud understanding via CLIP under low resource cost and data regime. We conduct thorough experiments on widely-adopted ModelNet10, ModelNet40 and the challenging ScanObjectNN to demonstrate the effectiveness of PointCLIP. The code is released at https://github.com/ZrrSkywalker/PointCLIP.
Zhe Wang, Hongsheng Li, Qinwei Zhang, Jing Yuan, Xiaogang Wang
Magnetic Resonance Fingerprinting (MRF) is a novel technique that simultaneously estimates multiple tissue-related parameters, such as the longitudinal relaxation time T1, the transverse relaxation time T2, off resonance frequency B0 and proton density, from a scanned object in just tens of seconds. However, the MRF method suffers from aliasing artifacts because it significantly undersamples the k-space data. In this work, we propose a compressed sensing (CS) framework for simultaneously estimating multiple tissue-related parameters based on the MRF method. It is more robust to low sampling ratio and is therefore more efficient in estimating MR parameters for all voxels of an object. Furthermore, the MRF method requires identifying the nearest atoms of the query fingerprints from the MR-signal-evolution dictionary with the L2 distance. However, we observed that the L2 distance is not always a proper metric to measure the similarities between MR Fingerprints. Adaptively learning a distance metric from the undersampled training data can significantly improve the matching accuracy of the query fingerprints. Numerical results on extensive simulated cases show that our method substantially outperforms stateof-the-art methods in terms of accuracy of parameter estimation.
Haiyang Wang, Shaoshuai Shi, Ze Yang, Rongyao Fang, Qi Qian, Hongsheng Li, Bernt Schiele, Liwei Wang
As a fundamental problem in computer vision, 3D object detection is experiencing rapid growth. To extract the point-wise features from the irregularly and sparsely distributed points, previous methods usually take a feature grouping module to aggregate the point features to an object candidate. However, these methods have not yet leveraged the surface geometry of foreground objects to enhance grouping and 3D box generation. In this paper, we propose the RBGNet framework, a voting-based 3D detector for accurate 3D object detection from point clouds. In order to learn better representations of object shape to enhance cluster features for predicting 3D boxes, we propose a ray-based feature grouping module, which aggregates the point-wise features on object surfaces using a group of determined rays uniformly emitted from cluster centers. Considering the fact that foreground points are more meaningful for box estimation, we design a novel foreground biased sampling strategy in downsample process to sample more points on object surfaces and further boost the detection performance. Our model achieves state-of-the-art 3D detection performance on ScanNet V2 and SUN RGB-D with remarkable performance gains. Code will be available at https://github.com/Haiyang-W/RBGNet.
Wei Cheng, Su Xu, Jingtan Piao, Chen Qian, Wayne Wu, Kwan-Yee Lin, Hongsheng Li
This work targets at using a general deep learning framework to synthesize free-viewpoint images of arbitrary human performers, only requiring a sparse number of camera views as inputs and skirting per-case fine-tuning. The large variation of geometry and appearance, caused by articulated body poses, shapes and clothing types, are the key bottlenecks of this task. To overcome these challenges, we present a simple yet powerful framework, named Generalizable Neural Performer (GNR), that learns a generalizable and robust neural body representation over various geometry and appearance. Specifically, we compress the light fields for novel view human rendering as conditional implicit neural radiance fields from both geometry and appearance aspects. We first introduce an Implicit Geometric Body Embedding strategy to enhance the robustness based on both parametric 3D human body model and multi-view images hints. We further propose a Screen-Space Occlusion-Aware Appearance Blending technique to preserve the high-quality appearance, through interpolating source view appearance to the radiance fields with a relax but approximate geometric guidance. To evaluate our method, we present our ongoing effort of constructing a dataset with remarkable complexity and diversity. The dataset GeneBody-1.0, includes over 360M frames of 370 subjects under multi-view cameras capturing, performing a large variety of pose actions, along with diverse body shapes, clothing, accessories and hairdos. Experiments on GeneBody-1.0 and ZJU-Mocap show better robustness of our methods than recent state-of-the-art generalizable methods among all cross-dataset, unseen subjects and unseen poses settings. We also demonstrate the competitiveness of our model compared with cutting-edge case-specific ones. Dataset, code and model will be made publicly available.
Junting Pan, Adrian Bulat, Fuwen Tan, Xiatian Zhu, Lukasz Dudziak, Hongsheng Li, Georgios Tzimiropoulos, Brais Martinez
Self-attention based models such as vision transformers (ViTs) have emerged as a very competitive architecture alternative to convolutional neural networks (CNNs) in computer vision. Despite increasingly stronger variants with ever-higher recognition accuracies, due to the quadratic complexity of self-attention, existing ViTs are typically demanding in computation and model size. Although several successful design choices (e.g., the convolutions and hierarchical multi-stage structure) of prior CNNs have been reintroduced into recent ViTs, they are still not sufficient to meet the limited resource requirements of mobile devices. This motivates a very recent attempt to develop light ViTs based on the state-of-the-art MobileNet-v2, but still leaves a performance gap behind. In this work, pushing further along this under-studied direction we introduce EdgeViTs, a new family of light-weight ViTs that, for the first time, enable attention-based vision models to compete with the best light-weight CNNs in the tradeoff between accuracy and on-device efficiency. This is realized by introducing a highly cost-effective local-global-local (LGL) information exchange bottleneck based on optimal integration of self-attention and convolutions. For device-dedicated evaluation, rather than relying on inaccurate proxies like the number of FLOPs or parameters, we adopt a practical approach of focusing directly on on-device latency and, for the first time, energy efficiency. Specifically, we show that our models are Pareto-optimal when both accuracy-latency and accuracy-energy trade-offs are considered, achieving strict dominance over other ViTs in almost all cases and competing with the most efficient CNNs. Code is available at https://github.com/saic-fi/edgevit.