Training state-of-the-art models for human pose estimation in videos requires datasets with annotations that are really hard and expensive to obtain. Although transformers have been recently utilized for body pose sequence modeling, related methods rely on pseudo-ground truth to augment the currently limited training data available for learning such models. In this paper, we introduce PoseBERT, a transformer module that is fully trained on 3D Motion Capture (MoCap) data via masked modeling. It is simple, generic and versatile, as it can be plugged on top of any image-based model to transform it in a video-based model leveraging temporal information. We showcase variants of PoseBERT with different inputs varying from 3D skeleton keypoints to rotations of a 3D parametric model for either the full body (SMPL) or just the hands (MANO). Since PoseBERT training is task agnostic, the model can be applied to several tasks such as pose refinement, future pose prediction or motion completion without finetuning. Our experimental results validate that adding PoseBERT on top of various state-of-the-art pose estimation methods consistently improves their performances, while its low computational cost allows us to use it in a real-time demo for smoothly animating a robotic hand via a webcam. Test code and models are available at https://github.com/naver/posebert.
The University of Exeter（埃克塞特大学）；Middle East Technical University（中东技术大学）；University of Glasgow（格拉斯哥大学）
Deep neural network approaches have demonstrated high performance in object recognition (CNN) and detection (Faster-RCNN) tasks, but experiments have shown that such architectures are vulnerable to adversarial attacks (FFF, UAP): low amplitude perturbations, barely perceptible by the human eye, can lead to a drastic reduction in labeling performance. This article proposes a new context module, called \textit{Transformer-Encoder Detector Module}, that can be applied to an object detector to (i) improve the labeling of object instances; and (ii) improve the detector's robustness to adversarial a…
Effectively encoding multi-scale contextual information is crucial for accurate semantic segmentation. Existing transformer-based segmentation models combine features across scales without any selection, where features on sub-optimal scales may degrade segmentation outcomes. Leveraging from the inherent properties of Vision Transformers, we propose a simple yet effective module, Transformer Scale Gate (TSG), to optimally combine multi-scale features.TSG exploits cues in self and cross attentions in Vision Transformers for the scale selection. TSG is a highly flexible plug-and-play module, and …
Deep learning based change detection methods have received wide attentoion, thanks to their strong capability in obtaining rich features from images. However, existing AI-based CD methods largely rely on three functionality-enhancing modules, i.e., semantic enhancement, attention mechanisms, and correspondence enhancement. The stacking of these modules leads to great model complexity. To unify these three modules into a simple pipeline, we introduce Relational Change Detection Transformer (RCDT), a novel and simple framework for remote sensing change detection tasks. The proposed RCDT consists…
Ulsan National Institute of Science and Technology（蔚山科学技术院）
Few-shot learning allows machines to classify novel classes using only a few labeled samples. Recently, few-shot segmentation aiming at semantic segmentation on low sample data has also seen great interest. In this paper, we propose a learnable module that can be placed on top of existing segmentation networks for performing few-shot segmentation. This module, called the task-adaptive feature transformer (TAFT), linearly transforms task-specific high-level features to a set of task agnostic features well-suited to conducting few-shot segmentation. The task-conditioned feature transformation al…
The Chinese University of Hong Kong（香港中文大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；HKUST（香港科技大学）
We present Voxel Transformer (VoTr), a novel and effective voxel-based Transformer backbone for 3D object detection from point clouds. Conventional 3D convolutional backbones in voxel-based 3D detectors cannot efficiently capture large context information, which is crucial for object recognition and localization, owing to the limited receptive fields. In this paper, we resolve the problem by introducing a Transformer-based architecture that enables long-range relationships between voxels by self-attention. Given the fact that non-empty voxels are naturally sparse but numerous, directly applyin…
Salient object detection is the pixel-level dense prediction task which can highlight the prominent object in the scene. Recently U-Net framework is widely used, and continuous convolution and pooling operations generate multi-level features which are complementary with each other. In view of the more contribution of high-level features for the performance, we propose a triplet transformer embedding module to enhance them by learning long-range dependencies across layers. It is the first to use three transformer encoders with shared weights to enhance multi-level features. By further designing…
Due to the fact that fully supervised semantic segmentation methods require sufficient fully-labeled data to work well and can not generalize to unseen classes, few-shot segmentation has attracted lots of research attention. Previous arts extract features from support and query images, which are processed jointly before making predictions on query images. The whole process is based on convolutional neural networks (CNN), leading to the problem that only local information is used. In this paper, we propose a TRansformer-based Few-shot Semantic segmentation method (TRFS). Specifically, our model…
Baidu Research（百度研究院）；National Engineering Laboratory for Deep Learning Technology and Application（深度学习技术与应用国家工程实验室）
Recently, it has attracted more and more attentions to fuse multi-scale features for semantic image segmentation. Various works were proposed to employ progressive local or global fusion, but the feature fusions are not rich enough for modeling multi-scale context features. In this work, we focus on fusing multi-scale features from Transformer-based backbones for semantic segmentation, and propose a Feature Selective Transformer (FeSeFormer), which aggregates features from all scales (or levels) for each query feature. Specifically, we first propose a Scale-level Feature Selection (SFS) module…
University of Florida（佛罗里达大学）；ByteDance Inc.（字节跳动公司）
Video object detection needs to solve feature degradation situations that rarely happen in the image domain. One solution is to use the temporal information and fuse the features from the neighboring frames. With Transformerbased object detectors getting a better performance on the image domain tasks, recent works began to extend those methods to video object detection. However, those existing Transformer-based video object detectors still follow the same pipeline as those used for classical object detectors, like enhancing the object feature representations by aggregation. In this work, we ta…
National Taiwan University（国立台湾大学）；Mobile Drive Technology（移动驱动科技公司）
Monocular 3D object detection is an important yet challenging task in autonomous driving. Some existing methods leverage depth information from an off-the-shelf depth estimator to assist 3D detection, but suffer from the additional computational burden and achieve limited performance caused by inaccurate depth priors. To alleviate this, we propose MonoDTR, a novel end-to-end depth-aware transformer network for monocular 3D object detection. It mainly consists of two components: (1) the Depth-Aware Feature Enhancement (DFE) module that implicitly learns depth-aware features with auxiliary super…
TransReg: Cross-transformer as auto-registration module for multi-view mammogram mass detection
VinUni-Illinois Smart Health Center, VinUniversity（VinUni-Illinois智慧健康中心，VinUniversity）；College of Engineering and Computer Science, VinUniversity（VinUniversity工程与计算机科学学院）
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Beijing Aerospace Intelligent Manufacturing Technology Development Co., Ltd（北京航天智能制造技术发展有限公司）；Hong Kong Metropolitan University（香港都会大学）
We propose PSFormer, an effective point transformer model for 3D salient object detection. PSFormer is an encoder-decoder network that takes full advantage of transformers to model the contextual information in both multi-scale point- and scene-wise manners. In the encoder, we develop a Point Context Transformer (PCT) module to capture region contextual features at the point level; PCT contains two different transformers to excavate the relationship among points. In the decoder, we develop a Scene Context Transformer (SCT) module to learn context representations at the scene level; SCT contain…
Most existing transformer based video instance segmentation methods extract per frame features independently, hence it is challenging to solve the appearance deformation problem. In this paper, we observe the temporal information is important as well and we propose TAFormer to aggregate spatio-temporal features both in transformer encoder and decoder. Specifically, in transformer encoder, we propose a novel spatio-temporal joint multi-scale deformable attention module which dynamically integrates the spatial and temporal information to obtain enriched spatio-temporal features. In transformer d…
Salient Object Detection is the task of predicting the human attended region in a given scene. Fusing depth information has been proven effective in this task. The main challenge of this problem is how to aggregate the complementary information from RGB modality and depth modality. However, conventional deep models heavily rely on CNN feature extractors, and the long-range contextual dependencies are usually ignored. In this work, we propose Dual Swin-Transformer based Mutual Interactive Network. We adopt Swin-Transformer as the feature extractor for both RGB and depth modality to model the lo…
Most approaches for semantic segmentation use only information from color cameras to parse the scenes, yet recent advancements show that using depth data allows to further improve performances. In this work, we focus on transformer-based deep learning architectures, that have achieved state-of-the-art performances on the segmentation task, and we propose to employ depth information by embedding it in the positional encoding. Effectively, we extend the network to multimodal data without adding any parameters and in a natural way that makes use of the strength of transformers' self-attention mod…
National University of Singapore（新加坡国立大学）；Yitu Technology（依图科技）
Recently, DETR pioneered the solution of vision tasks with transformers, it directly translates the image feature map into the object detection result. Though effective, translating the full feature map can be costly due to redundant computation on some area like the background. In this work, we encapsulate the idea of reducing spatial redundancy into a novel poll and pool (PnP) sampling module, with which we build an end-to-end PnP-DETR architecture that adaptively allocates its computation spatially to be more efficient. Concretely, the PnP module abstracts the image feature map into fine fo…
Transformers have become one of the dominant architectures in deep learning, particularly as a powerful alternative to convolutional neural networks (CNNs) in computer vision. However, Transformer training and inference in previous works can be prohibitively expensive due to the quadratic complexity of self-attention over a long sequence of representations, especially for high-resolution dense prediction tasks. To this end, we present a novel Less attention vIsion Transformer (LIT), building upon the fact that the early self-attention layers in Transformers still focus on local patterns and br…
University of Science and Technology of China（中国科学技术大学）；SenseTime Research（商汤科技研究院）；The Chinese University of Hong Kong（香港中文大学）
DETR has been recently proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance. However, it suffers from slow convergence and limited feature spatial resolution, due to the limitation of Transformer attention modules in processing image feature maps. To mitigate these issues, we proposed Deformable DETR, whose attention modules only attend to a small set of key sampling points around a reference. Deformable DETR can achieve better performance than DETR (especially on small objects) with 10 times less training epochs. Extensive e…
School of Computer Science, Southeast University（东南大学计算机科学与工程学院）
Most of existing RGB-D salient object detection (SOD) methods follow the CNN-based paradigm, which is unable to model long-range dependencies across space and modalities due to the natural locality of CNNs. Here we propose the Hierarchical Cross-modal Transformer (HCT), a new multi-modal transformer, to tackle this problem. Unlike previous multi-modal transformers that directly connecting all patches from two modalities, we explore the cross-modal complementarity hierarchically to respect the modality gap and spatial discrepancy in unaligned regions. Specifically, we propose to use intra-modal…
RWTH Aachen University（亚琛工业大学）；Shahid Beheshti University（沙希德·贝赫什提大学）；Mila, Quebec AI Institute（米拉魁北克人工智能研究所）；University of Montreal（蒙特利尔大学）；Polytechnique Montreal（蒙特利尔理工学院）；University of Regensburg（雷根斯堡大学）；Fraunhofer Institute for Digital Medicine MEVIS（弗劳恩霍夫数字医学MEVIS研究所）
While CNN-based methods have been the cornerstone of medical image segmentation due to their promising performance and robustness, they suffer from limitations in capturing long-range dependencies. Transformer-based approaches are currently prevailing since they enlarge the reception field to model global contextual correlation. To further extract rich representations, some extensions of the U-Net employ multi-scale feature extraction and fusion modules and obtain improved performance. Inspired by this idea, we propose TransCeption for medical image segmentation, a pure transformer-based U-sha…
Transformers have made great progress in dealing with computer vision tasks. However, existing vision transformers do not yet possess the ability of building the interactions among features of different scales, which is perceptually important to visual inputs. The reasons are two-fold: (1) Input embeddings of each layer are equal-scale, so no cross-scale feature can be extracted; (2) to lower the computational cost, some vision transformers merge adjacent embeddings inside the self-attention module, thus sacrificing small-scale (fine-grained) features of the embeddings and also disabling the c…
Training state-of-the-art models for human body pose and shape recovery from images or videos requires datasets with corresponding annotations that are really hard and expensive to obtain. Our goal in this paper is to study whether poses from 3D Motion Capture (MoCap) data can be used to improve image-based and video-based human mesh recovery methods. We find that fine-tune image-based models with synthetic renderings from MoCap data can increase their performance, by providing them with a wider variety of poses, textures and backgrounds. In fact, we show that simply fine-tuning the batch norm…
The University of Sydney（悉尼大学）；JD Explore Academy（京东探索研究院）
Attention mechanisms have been very popular in deep neural networks, where the Transformer architecture has achieved great success in not only natural language processing but also visual recognition applications. Recently, a new Transformer module, applying on batch dimension rather than spatial/channel dimension, i.e., BatchFormer [18], has been introduced to explore sample relationships for overcoming data scarcity challenges. However, it only works with image-level representations for classification. In this paper, we devise a more general batch Transformer module, BatchFormerV2, which furt…
Washington State University（华盛顿州立大学）；University of California, Davis（加利福尼亚大学戴维斯分校）
The key idea of current deep learning methods for dense prediction is to apply a model on a regular patch centered on each pixel to make pixel-wise predictions. These methods are limited in the sense that the patches are determined by network architecture instead of learned from data. In this work, we propose the dense transformer networks, which can learn the shapes and sizes of patches from data. The dense transformer networks employ an encoder-decoder architecture, and a pair of dense transformer modules are inserted into each of the encoder and decoder paths. The novelty of this work is th…
3D single object tracking is a key issue for robotics. In this paper, we propose a transformer module called Point-Track-Transformer (PTT) for point cloud-based 3D single object tracking. PTT module contains three blocks for feature embedding, position encoding, and self-attention feature computation. Feature embedding aims to place features closer in the embedding space if they have similar semantic information. Position encoding is used to encode coordinates of point clouds into high dimension distinguishable features. Self-attention generates refined attention features by computing attentio…
Samsung Research China - Beijing (SRC-B)（三星中国研究院-北京）
Recent works achieve excellent results in defocus deblurring task based on dual-pixel data using convolutional neural network (CNN), while the scarcity of data limits the exploration and attempt of vision transformer in this task. In addition, the existing works use fixed parameters and network architecture to deblur images with different distribution and content information, which also affects the generalization ability of the model. In this paper, we propose a dynamic multi-scale network, named DMTNet, for dual-pixel images defocus deblurring. DMTNet mainly contains two modules: feature extr…
Ping An Property & Casualty Insurance Company（平安财产保险股份有限公司）
Modeling semantic information is helpful for scene text recognition. In this work, we propose to model semantic and visual information jointly with a Visual-Semantic Transformer (VST). The VST first explicitly extracts primary semantic information from visual feature maps with a transformer module and a primary visual-semantic alignment module. The semantic information is then joined with the visual feature maps (viewed as a sequence) to form a pseudo multi-domain sequence combining visual and semantic information, which is subsequently fed into an transformer-based interaction module to enabl…
Fujitsu Limited（富士通有限公司）；Fujitsu Research of America, Inc.（美国富士通研究公司）；Massachusetts Institute of Technology（麻省理工学院）；Center for Brains, Minds and Machines（大脑、心智与机器中心）
Transformers achieve great performance on Visual Question Answering (VQA). However, their systematic generalization capabilities, i.e., handling novel combinations of known concepts, is unclear. We reveal that Neural Module Networks (NMNs), i.e., question-specific compositions of modules that tackle a sub-task, achieve better or similar systematic generalization performance than the conventional Transformers, even though NMNs' modules are CNN-based. In order to address this shortcoming of Transformers with respect to NMNs, in this paper we investigate whether and how modularity can bring benef…
The Chinese University of Hong Kong（香港中文大学）；SmartMore
We study the vision transformer structure in the mobile level in this paper, and find a dramatic performance drop. We analyze the reason behind this phenomenon, and propose a novel irregular patch embedding module and adaptive patch fusion module to improve the performance. We conjecture that the vision transformer blocks (which consist of multi-head attention and feed-forward network) are more suitable to handle high-level information than low-level features. The irregular patch embedding module extracts patches that contain rich high-level information with different receptive fields. The tra…
The pretrain-then-finetune paradigm has been widely adopted in computer vision. But as the size of Vision Transformer (ViT) grows exponentially, the full finetuning becomes prohibitive in view of the heavier storage overhead. Motivated by parameter-efficient transfer learning (PETL) on language transformers, recent studies attempt to insert lightweight adaptation modules (e.g., adapter layers or prompt tokens) to pretrained ViT and only finetune these modules while the pretrained weights are frozen. However, these modules were originally proposed to finetune language models and did not take in…
Transformers are becoming increasingly popular due to their superior performance over conventional convolutional neural networks(CNNs). However, transformers usually require a much larger amount of memory to train than CNNs, which prevents their application in many low resource settings. Local learning, which divides the network into several distinct modules and trains them individually, is a promising alternative to the end-to-end (E2E) training approach to reduce the amount of memory for training and to increase parallelism. This paper is the first to apply Local Learning on transformers for…
Technische Universität Berlin（柏林工业大学）；Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究所）；University of Bonn（波恩大学）；Microsoft（微软）；University of California, Davis（加州大学戴维斯分校）；Meta Reality Labs（Meta现实实验室）
While state-of-the-art vision transformer models achieve promising results in image classification, they are computationally expensive and require many GFLOPs. Although the GFLOPs of a vision transformer can be decreased by reducing the number of tokens in the network, there is no setting that is optimal for all input images. In this work, we therefore introduce a differentiable parameter-free Adaptive Token Sampler (ATS) module, which can be plugged into any existing vision transformer architecture. ATS empowers vision transformers by scoring and adaptively sampling significant tokens. As a r…
Zhejiang University（浙江大学）；Beijing Research Institute of Megvii Inc（旷视科技北京研究院）
Partial person re-identification (ReID) is a challenging task because only partial information of person images is available for matching target persons. Few studies, especially on deep learning, have focused on matching partial person images with holistic person images. This study presents a novel deep partial ReID framework based on pairwise spatial transformer networks (STNReID), which can be trained on existing holistic person datasets. STNReID includes a spatial transformer network (STN) module and a ReID module. The STN module samples an affined image (a semantically corresponding patch)…
Sun Yat-sen University（中山大学）；Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）；Queen Mary University of London（伦敦玛丽女王大学）；The University of Melbourne（墨尔本大学）
Effective learning of spatial-temporal information within a point cloud sequence is highly important for many down-stream tasks such as 4D semantic segmentation and 3D action recognition. In this paper, we propose a novel framework named Point Spatial-Temporal Transformer (PST2) to learn spatial-temporal representations from dynamic 3D point cloud sequences. Our PST2 consists of two major modules: a Spatio-Temporal Self-Attention (STSA) module and a Resolution Embedding (RE) module. Our STSA module is introduced to capture the spatial-temporal context information across adjacent frames, while …
University of Science and Technology Beijing（北京科技大学）；Beijing Jiaotong University（北京交通大学）
Image denoising is an important low-level computer vision task, which aims to reconstruct a noise-free and high-quality image from a noisy image. With the development of deep learning, convolutional neural network (CNN) has been gradually applied and achieved great success in image denoising, image compression, image enhancement, etc. Recently, Transformer has been a hot technique, which is widely used to tackle computer vision tasks. However, few Transformer-based methods have been proposed for low-level vision tasks. In this paper, we proposed an image denoising network structure based on Tr…
Beihang University（北京航空航天大学）；Tsinghua University（清华大学）；University of Science and Technology of China（中国科学技术大学）；Pengcheng Laboratory（鹏城实验室）；Xidian University（西安电子科技大学）
Recently, the Transformer module has been transplanted from natural language processing to computer vision. This paper applies the Transformer to video-based person re-identification, where the key issue is to extract the discriminative information from a tracklet. We show that, despite the strong learning ability, the vanilla Transformer suffers from an increased risk of over-fitting, arguably due to a large number of attention parameters and insufficient training data. To solve this problem, we propose a novel pipeline where the model is pre-trained on a set of synthesized video data and the…
Remarkable performance from Transformer networks in Natural Language Processing promote the development of these models in dealing with computer vision tasks such as image recognition and segmentation. In this paper, we introduce a novel framework, called Multi-level Multi-scale Point Transformer (MLMSPT) that works directly on the irregular point clouds for representation learning. Specifically, a point pyramid transformer is investigated to model features with diverse resolutions or scales we defined, followed by a multi-level transformer module to aggregate contextual information from diffe…
Information Engineering College, Capital Normal University（首都师范大学信息工程学院）；State Key Lab of Software Development Environment, School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机学院软件开发环境国家重点实验室）；Computer Vision Perception Department of ZongMu Technology（纵目科技计算机视觉感知部）
In recent years, 2D Convolutional Networks-based video action recognition has encouragingly gained wide popularity; However, constrained by the lack of long-range non-linear temporal relation modeling and reverse motion information modeling, the performance of existing models is, therefore, undercut seriously. To address this urgent problem, we introduce a startling Temporal Transformer Network with Self-supervision (TTSN). Our high-performance TTSN mainly consists of a temporal transformer module and a temporal sequence self-supervision module. Concisely speaking, we utilize the efficient tem…
Jiangnan University（江南大学）；University of Surrey（萨里大学）
The end-to-end image fusion framework has achieved promising performance, with dedicated convolutional networks aggregating the multi-modal local appearance. However, long-range dependencies are directly neglected in existing CNN fusion approaches, impeding balancing the entire image-level perception for complex scenario fusion. In this paper, therefore, we propose an infrared and visible image fusion algorithm based on a lightweight transformer module and adversarial learning. Inspired by the global interaction power, we use the transformer technique to learn the effective global fusion relat…
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）
Fine-grained visual categorization (FGVC) aims at recognizing objects from similar subordinate categories, which is challenging and practical for human's accurate automatic recognition needs. Most FGVC approaches focus on the attention mechanism research for discriminative regions mining while neglecting their interdependencies and composed holistic object structure, which are essential for model's discriminative information localization and understanding ability. To address the above limitations, we propose the Structure Information Modeling Transformer (SIM-Trans) to incorporate object struc…
Microsoft Research（微软研究院）；Shanghai Jiao Tong University（上海交通大学）
We study on image super-resolution (SR), which aims to recover realistic textures from a low-resolution (LR) image. Recent progress has been made by taking high-resolution images as references (Ref), so that relevant textures can be transferred to LR images. However, existing SR approaches neglect to use attention mechanisms to transfer high-resolution (HR) textures from Ref images, which limits these approaches in challenging cases. In this paper, we propose a novel Texture Transformer Network for Image Super-Resolution (TTSR), in which the LR and Ref images are formulated as queries and keys…
The University of Sydney（悉尼大学）；SenseTime Group Limited（商汤科技集团）；BAIDU USA LLC（百度美国有限责任公司）；University of Oxford（牛津大学）
We introduce the first Neural Architecture Search (NAS) method to find a better transformer architecture for image recognition. Recently, transformers without CNN-based backbones are found to achieve impressive performance for image recognition. However, the transformer is designed for NLP tasks and thus could be sub-optimal when directly used for image recognition. In order to improve the visual representation ability for transformers, we propose a new search space and searching algorithm. Specifically, we introduce a locality module that models the local correlations in images explicitly wit…
Although transformer networks are recently employed in various vision tasks with outperforming performance, extensive training data and a lengthy training time are required to train a model to disregard an inductive bias. Using trainable links between the channel-wise spatial attention of a pre-trained Convolutional Neural Network (CNN) and the attention head of Vision Transformers (ViT), we present a regularization technique to improve the training efficiency of ViT. The trainable links are referred to as the attention augmentation module, which is trained simultaneously with ViT, boosting th…
Baidu Inc.（百度公司）；Dalian University of technology（大连理工大学）
Table structure recognition is a crucial part of document image analysis domain. Its difficulty lies in the need to parse the physical coordinates and logical indices of each cell at the same time. However, the existing methods are difficult to achieve both these goals, especially when the table splitting lines are blurred or tilted. In this paper, we propose an accurate and end-to-end transformer-based table structure recognition method, referred to as TRUST. Transformers are suitable for table structure recognition because of their global computations, perfect memory, and parallel computatio…
