Understanding the 3D world is a fundamental problem in computer vision. However, learning a good representation of 3D objects is still an open problem due to the high dimensionality of the data and many factors of variation involved. In this work, we investigate the task of single-view 3D object reconstruction from a learning agent's perspective. We formulate the learning process as an interaction between 3D and 2D representations and propose an encoder-decoder network with a novel projection loss defined by the perspective transformation. More importantly, the projection loss enables the unsupervised learning using 2D observation without explicit 3D supervision. We demonstrate the ability of the model in generating 3D volume from a single 2D image with three sets of experiments: (1) learning from single-class objects; (2) learning from multi-class objects and (3) testing on novel object classes. Results show superior performance and better generalization ability for 3D object reconstruction when the projection loss is involved.
Hikvision Research Institute (HRI), Hangzhou Hikvision Digital Technology Co. Ltd（海康威视研究院（HRI），杭州海康威视数字技术有限公司）
This paper addresses the importance of full-image supervision for monocular depth estimation. We propose a semi-supervised architecture, which combines both unsupervised framework of using image consistency and supervised framework of dense depth completion. The latter provides full-image depth as supervision for the former. Ego-motion from navigation system is also embedded into the unsupervised framework as output supervision of an inner temporal transform network, making monocular depth estimation better. In the evaluation, we show that our proposed model outperforms other approaches on dep…
Facial landmark localisation in images captured in-the-wild is an important and challenging problem. The current state-of-the-art revolves around certain kinds of Deep Convolutional Neural Networks (DCNNs) such as stacked U-Nets and Hourglass networks. In this work, we innovatively propose stacked dense U-Nets for this task. We design a novel scale aggregation network topology structure and a channel aggregation building block to improve the model's capacity without sacrificing the computational complexity and model size. With the assistance of deformable convolutions inside the stacked dense …
Universitat Pompeu Fabra（庞培法布拉大学）；University of Adelaide（阿德莱德大学）；ICREA（加泰罗尼亚研究与创新高级研究所）
This paper compares well-established Convolutional Neural Networks (CNNs) to recently introduced Vision Transformers for the task of Diabetic Foot Ulcer Classification, in the context of the DFUC 2021 Grand-Challenge, in which this work attained the first position. Comprehensive experiments demonstrate that modern CNNs are still capable of outperforming Transformers in a low-data regime, likely owing to their ability for better exploiting spatial correlations. In addition, we empirically demonstrate that the recent Sharpness-Aware Minimization (SAM) optimization algorithm considerably improves…
Department of Computer Science, University of York（约克大学计算机科学系）
We generalise Spatial Transformer Networks (STN) by replacing the parametric transformation of a fixed, regular sampling grid with a deformable, statistical shape model which is itself learnt. We call this a Statistical Transformer Network (StaTN). By training a network containing a StaTN end-to-end for a particular task, the network learns the optimal nonrigid alignment of the input data for the task. Moreover, the statistical shape model is learnt with no direct supervision (such as landmarks) and can be reused for other tasks. Besides training for a specific task, we also show that a StaTN …
Understanding temporal dynamics of video is an essential aspect of learning better video representations. Recently, transformer-based architectural designs have been extensively explored for video tasks due to their capability to capture long-term dependency of input sequences. However, we found that these Video Transformers are still biased to learn spatial dynamics rather than temporal ones, and debiasing the spurious correlation is critical for their performance. Based on the observations, we design simple yet effective self-supervised tasks for video models to learn temporal dynamics bette…
Multimodal imaging and correlative analysis typically require image alignment. Contrastive learning can generate representations of multimodal images, reducing the challenging task of multimodal image registration to a monomodal one. Previously, additional supervision on intermediate layers in contrastive learning has improved biomedical image classification. We evaluate if a similar approach improves representations learned for registration to boost registration performance. We explore three approaches to add contrastive supervision to the latent features of the bottleneck layer in the U-Nets…
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…
Renault Software Factory（雷诺软件工厂）；CNRS-I3S（法国国家科学研究中心I3S实验室）；Côte d’Azur University（蔚蓝海岸大学）
This paper addresses the problem of end-to-end self-supervised forecasting of depth and ego motion. Given a sequence of raw images, the aim is to forecast both the geometry and ego-motion using a self supervised photometric loss. The architecture is designed using both convolution and transformer modules. This leverages the benefits of both modules: Inductive bias of CNN, and the multi-head attention of transformers, thus enabling a rich spatio-temporal representation that enables accurate depth forecasting. Prior work attempts to solve this problem using multi-modal input/output with supervis…
Harbin Institute of Technology（哈尔滨工业大学）；National University of Singapore（新加坡国立大学）
The few-shot learning ability of vision transformers (ViTs) is rarely investigated though heavily desired. In this work, we empirically find that with the same few-shot learning frameworks, \eg~Meta-Baseline, replacing the widely used CNN feature extractor with a ViT model often severely impairs few-shot classification performance. Moreover, our empirical study shows that in the absence of inductive bias, ViTs often learn the low-qualified token dependencies under few-shot learning regime where only a few labeled training data are available, which largely contributes to the above performance d…
What is the right object representation for manipulation? We would like robots to visually perceive scenes and learn an understanding of the objects in them that (i) is task-agnostic and can be used as a building block for a variety of manipulation tasks, (ii) is generally applicable to both rigid and non-rigid objects, (iii) takes advantage of the strong priors provided by 3D vision, and (iv) is entirely learned from self-supervision. This is hard to achieve with previous methods: much recent work in grasping does not extend to grasping specific objects or other tasks, whereas task-specific l…
Technische Universität München（慕尼黑工业大学）；Google（谷歌）
The video action segmentation task is regularly explored under weaker forms of supervision, such as transcript supervision, where a list of actions is easier to obtain than dense frame-wise labels. In this formulation, the task presents various challenges for sequence modeling approaches due to the emphasis on action transition points, long sequence lengths, and frame contextualization, making the task well-posed for transformers. Given developments enabling transformers to scale linearly, we demonstrate through our architecture how they can be applied to improve action alignment accuracy over…
LoopREG: Representation Supervision Enables Test-Time Recurrent Depth in Diffusion Transformers
Chongqing University of Posts and Telecommunications（重庆邮电大学）；China United Network Communications Group Co., Ltd.（中国联合网络通信集团有限公司）；Dongbei University of Finance and Economics（东北财经大学）；University of Electronic Science and Technology of China（电子科技大学）
MGRQ: Post-Training Quantization For Vision Transformer With Mixed Granularity Reconstruction
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
With the recent successful adaptation of transformers to the vision domain, particularly when trained in a self-supervised fashion, it has been shown that vision transformers can learn impressive object-reasoning-like behaviour and features expressive for the task of object segmentation in images. In this paper, we build on the self-supervision task of masked autoencoding and explore its effectiveness for explicitly learning object-centric representations with transformers. To this end, we design an object-centric autoencoder using transformers only and train it end-to-end to reconstruct full …
Lanzhou University（兰州大学）；University of Guelph（圭尔夫大学）；Zhejiang Sci-Tech University（浙江理工大学）；Chongqing University（重庆大学）
The ever-increasing demands for intuitive interactions in Virtual Reality has triggered a boom in the realm of Facial Expression Recognition (FER). To address the limitations in existing approaches (e.g., narrow receptive fields and homogenous supervisory signals) and further cement the capacity of FER tools, a novel multifarious supervision-steering Transformer for FER in the wild is proposed in this paper. Referred as FER-former, our approach features multi-granularity embedding integration, hybrid self-attention scheme, and heterogeneous domain-steering supervision. In specific, to dig deep…
Bilkent University（比尔肯特大学）；National Magnetic Resonance Research Center, Bilkent University（比尔肯特大学国家磁共振研究中心）
Supervised reconstruction models are characteristically trained on matched pairs of undersampled and fully-sampled data to capture an MRI prior, along with supervision regarding the imaging operator to enforce data consistency. To reduce supervision requirements, the recent deep image prior framework instead conjoins untrained MRI priors with the imaging operator during inference. Yet, canonical convolutional architectures are suboptimal in capturing long-range relationships, and priors based on randomly initialized networks may yield suboptimal performance. To address these limitations, here …
Yale University（耶鲁大学）；New York University（纽约大学）；Hyperfine Research（Hyperfine研究公司）
Multi-contrast MRI (MC-MRI) captures multiple complementary imaging modalities to aid in radiological decision-making. Given the need for lowering the time cost of multiple acquisitions, current deep accelerated MRI reconstruction networks focus on exploiting the redundancy between multiple contrasts. However, existing works are largely supervised with paired data and/or prohibitively expensive fully-sampled MRI sequences. Further, reconstruction networks typically rely on convolutional architectures which are limited in their capacity to model long-range interactions and may lead to suboptima…
360$^\circ$ video saliency detection is one of the challenging benchmarks for 360$^\circ$ video understanding since non-negligible distortion and discontinuity occur in the projection of any format of 360$^\circ$ videos, and capture-worthy viewpoint in the omnidirectional sphere is ambiguous by nature. We present a new framework named Panoramic Vision Transformer (PAVER). We design the encoder using Vision Transformer with deformable convolution, which enables us not only to plug pretrained models from normal videos into our architecture without additional modules or finetuning but also to per…
Beijing National Research Center for Information Science and Technology（北京国家信息科学与技术研究中心）；Tsinghua University（清华大学）；PhiGent Robotics（鉴智机器人）
The pretrain-finetune paradigm in modern computer vision facilitates the success of self-supervised learning, which tends to achieve better transferability than supervised learning. However, with the availability of massive labeled data, a natural question emerges: how to train a better model with both self and full supervision signals? In this paper, we propose Omni-suPErvised Representation leArning with hierarchical supervisions (OPERA) as a solution. We provide a unified perspective of supervisions from labeled and unlabeled data and propose a unified framework of fully supervised and self…
The Cooperative Network Architecture: Learning Structured Networks as Representation of Sensory Patterns
Zurich University of Applied Sciences（苏黎世应用科学大学）；University of Zurich（苏黎世大学）；ETH Zurich（苏黎世联邦理工学院）；Frankfurt Institute for Advanced Studies（法兰克福高级研究 institute）
Tencent Jarvis Lab（腾讯Jarvis实验室）；University of Science and Technology of China（中国科学技术大学）
Automated salient object detection (SOD) plays an increasingly crucial role in many computer vision applications. By reformulating the depth information as supervision rather than as input, depth-supervised convolutional neural networks (CNN) have achieved promising results on both RGB and RGB-D SOD scenarios with the merits of no requirements for extra depth networks and depth inputs in the inference stage. This paper, for the first time, seeks to expand the applicability of depth supervision to the Transformer architecture. Specifically, we develop a Depth-supervised Fusion TRansformer (DFTR…
Despite the great progress in 3D human pose estimation from videos, it is still an open problem to take full advantage of a redundant 2D pose sequence to learn representative representations for generating one 3D pose. To this end, we propose an improved Transformer-based architecture, called Strided Transformer, which simply and effectively lifts a long sequence of 2D joint locations to a single 3D pose. Specifically, a Vanilla Transformer Encoder (VTE) is adopted to model long-range dependencies of 2D pose sequences. To reduce the redundancy of the sequence, fully-connected layers in the fee…
The goal of this paper is Human-object Interaction (HO-I) detection. HO-I detection aims to find interacting human-objects regions and classify their interaction from an image. Researchers obtain significant improvement in recent years by relying on strong HO-I alignment supervision from [5]. HO-I alignment supervision pairs humans with their interacted objects, and then aligns human-object pair(s) with their interaction categories. Since collecting such annotation is expensive, in this paper, we propose to detect HO-I without alignment supervision. We instead rely on image-level supervision t…
King’s College London（伦敦国王学院）；Technical University of Munich（慕尼黑工业大学）
Brain tumor segmentation from multiple Magnetic Resonance Imaging (MRI) modalities is a challenging task in medical image computation. The main challenges lie in the generalizability to a variety of scanners and imaging protocols. In this paper, we explore strategies to increase model robustness without increasing inference time. Towards this aim, we explore finding a robust ensemble from models trained using different losses, optimizers, and train-validation data split. Importantly, we explore the inclusion of a transformer in the bottleneck of the U-Net architecture. While we find transforme…
The University of Hong Kong（香港大学）；Xiamen University（厦门大学）
Pre-training lays the foundation for recent successes in radiograph analysis supported by deep learning. It learns transferable image representations by conducting large-scale fully-supervised or self-supervised learning on a source domain. However, supervised pre-training requires a complex and labor intensive two-stage human-assisted annotation process while self-supervised learning cannot compete with the supervised paradigm. To tackle these issues, we propose a cross-supervised methodology named REviewing FreE-text Reports for Supervision (REFERS), which acquires free supervision signals f…
Sun Yat-sen University（中山大学）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；University of Technology Sydney（悉尼科技大学）；Oxford University（牛津大学）
Automatic data augmentation (AutoAugment) strategies are indispensable in supervised data-efficient training protocols of vision transformers, and have led to state-of-the-art results in supervised learning. Despite the success, its development and application on self-supervised vision transformers have been hindered by several barriers, including the high search cost, the lack of supervision, and the unsuitable search space. In this work, we propose AutoView, a self-regularized adversarial AutoAugment method, to learn views for self-supervised vision transformers, by addressing the above barr…
University of British Columbia（不列颠哥伦比亚大学）；Massachusetts Institute of Technology（麻省理工学院）；South China University of Technology（华南理工大学）；Google Research（谷歌研究院）；Tsinghua University（清华大学）；Vector Institute for AI（向量人工智能研究所）
Inspired by the success of self-supervised autoregressive representation learning in natural language (GPT and its variants), and advances in recent visual architecture design with Vision Transformers (ViTs), in this paper, we explore the effect various design choices have on the success of applying such training strategies for visual feature learning. Specifically, we introduce a novel strategy that we call Random Segments with Autoregressive Coding (RandSAC). In RandSAC, we group patch representations (image tokens) into hierarchically arranged segments; within each segment, tokens are predi…
GLF-Q: Global-Local Feature-based Quantization for Vision Transformers
State Key Laboratory of Novel Software Technology, Nanjing University（南京大学计算机软件新技术全国重点实验室）；School of Artificial Intelligence, Nanjing University（南京大学人工智能学院）；Zhongguancun Academy（中关村学院）
Weakly Supervised Point Clouds Transformer for 3D Object Detection
College of Software Engineering, Southeast University（东南大学软件学院）；Quanzhou Institute of Equipment Manufacturing, Haixi Institutes, Chinese Academy of Sciences（中国科学院海西研究院泉州装备制造研究所）；College of Mechanical Engineering, Xinjiang University（新疆大学机械工程学院）
