Autonomous systems need to localize and track surrounding objects in 3D space for safe motion planning. As a result, 3D multi-object tracking (MOT) plays a vital role in autonomous navigation. Most MOT methods use a tracking-by-detection pipeline, which includes object detection and data association processing. However, many approaches detect objects in 2D RGB sequences for tracking, which is lack of reliability when localizing objects in 3D space. Furthermore, it is still challenging to learn discriminative features for temporally-consistent detection in different frames, and the affinity matrix is normally learned from independent object features without considering the feature interaction between detected objects in the different frames. To settle these problems, We firstly employ a joint feature extractor to fuse the 2D and 3D appearance features captured from both 2D RGB images and 3D point clouds respectively, and then propose a novel convolutional operation, named RelationConv, to better exploit the correlation between each pair of objects in the adjacent frames, and learn a deep affinity matrix for further data association. We finally provide extensive evaluation to reveal that our proposed model achieves state-of-the-art performance on KITTI tracking benchmark.
Open-world instance segmentation is the task of grouping pixels into object instances without any pre-determined taxonomy. This is challenging, as state-of-the-art methods rely on explicit class semantics obtained from large labeled datasets, and out-of-domain evaluation performance drops significantly. Here we propose a novel approach for mask proposals, Generic Grouping Networks (GGNs), constructed without semantic supervision. Our approach combines a local measure of pixel affinity with instance-level mask supervision, producing a training regimen designed to make the model as generic as th…
A Renaissance of Explicit Motion Information Mining from Transformers for Action Recognition
Shanghai AI Laboratory（上海人工智能实验室）；The University of Sydney（悉尼大学）；SenseTime Group Ltd.（时光机器集团有限公司）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究所，中国科学院）
University of Science and Technology of China（中国科学技术大学）；Hefei Comprehensive National Science Center（合肥综合性国家科学中心）
In content-based image retrieval, the first-round retrieval result by simple visual feature comparison may be unsatisfactory, which can be refined by visual re-ranking techniques. In image retrieval, it is observed that the contextual similarity among the top-ranked images is an important clue to distinguish the semantic relevance. Inspired by this observation, in this paper, we propose a visual re-ranking method by contextual similarity aggregation with self-attention. In our approach, for each image in the top-K ranking list, we represent it into an affinity feature vector by comparing it wi…
Universitat Oberta de Catalunya（加泰罗尼亚开放大学）；Universitat Autònoma de Barcelona（巴塞罗那自治大学）；University of Barcelona（巴塞罗那大学）
Person re-identification has received special attention by the human analysis community in the last few years. To address the challenges in this field, many researchers have proposed different strategies, which basically exploit either cross-view invariant features or cross-view robust metrics. In this work, we propose to exploit a post-ranking approach and combine different feature representations through ranking aggregation. Spatial information, which potentially benefits the person matching, is represented using a 2D body model, from which color and texture information are extracted and com…
Universitat Autonoma de Barcelona（巴塞罗那自治大学）；Nanjing University of Science and Technology（南京理工大学）；Huawei Kirin Solution（华为麒麟解决方案）
Domain adaptation (DA) aims to alleviate the domain shift between source domain and target domain. Most DA methods require access to the source data, but often that is not possible (e.g. due to data privacy or intellectual property). In this paper, we address the challenging source-free domain adaptation (SFDA) problem, where the source pretrained model is adapted to the target domain in the absence of source data. Our method is based on the observation that target data, which might no longer align with the source domain classifier, still forms clear clusters. We capture this intrinsic structu…
Multi-modality fusion is the guarantee of the stability of autonomous driving systems. In this paper, we propose a general multi-modality cascaded fusion framework, exploiting the advantages of decision-level and feature-level fusion, utilizing target position, size, velocity, appearance and confidence to achieve accurate fusion results. In the fusion process, dynamic coordinate alignment(DCA) is conducted to reduce the error between sensors from different modalities. In addition, the calculation of affinity matrix is the core module of sensor fusion, we propose an affinity loss that improves …
Exploiting Aggregation and Segregation of Representations for Domain Adaptive Human Pose Estimation
Center for Research in Computer Vision, University of Central Florida（中佛罗里达大学计算机视觉研究中心）；Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）；Department of Computer Science, Tulane University（杜兰大学计算机科学系）；University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）
SA$^{2}$Net: Scale-Adaptive Structure-Affinity Transformation for Spine Segmentation from Ultrasound Volume Projection Imaging
Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University（香港理工大学电子与电气工程系）；School of Artificial Intelligence, Shenzhen Polytechnic University（深圳理工大学人工智能学院）；School of Computing and Mathematic Sciences, University of Leicester（莱斯特大学计算与数学科学学院）；Department of Biomedical Engineering, The Hong Kong Polytechnic University（香港理工大学生物医学工程系）；School of Electrical and Data Engineering, University of Technology Sydney（悉尼大学电气与数据工程学院）
UiT The Arctic University of Norway（挪威北极大学）；NORCE (the Norwegian Research Centre)（挪威NORCE研究中心）；University of Genoa（热那亚大学）
Image translation with convolutional neural networks has recently been used as an approach to multimodal change detection. Existing approaches train the networks by exploiting supervised information of the change areas, which, however, is not always available. A main challenge in the unsupervised problem setting is to avoid that change pixels affect the learning of the translation function. We propose two new network architectures trained with loss functions weighted by priors that reduce the impact of change pixels on the learning objective. The change prior is derived in an unsupervised fash…
Computer Vision Lab. (CVLAB), Korea University（高丽大学计算机视觉实验室（CVLAB））
Establishing dense correspondences across semantically similar images is one of the challenging tasks due to the significant intra-class variations and background clutters. To solve these problems, numerous methods have been proposed, focused on learning feature extractor or cost aggregation independently, which yields sub-optimal performance. In this paper, we propose a novel framework for jointly learning feature extraction and cost aggregation for semantic correspondence. By exploiting the pseudo labels from each module, the networks consisting of feature extraction and cost aggregation mod…
In many applications, the pairwise constraint is a kind of weaker supervisory information which can be collected easily. The constraint propagation has been proved to be a success of exploiting such side-information. In recent years, some methods of multi-view constraint propagation have been proposed. However, the problem of reasonably fusing different views remains unaddressed. In this paper, we present a method dubbed Consensus Prior Constraint Propagation (CPCP), which can provide the prior knowledge of the robustness of each data instance and its neighborhood. With the robustness generate…
National Institute of Technology Tiruchirappalli（蒂鲁吉拉伯利国家理工学院）
Single-image haze removal is a long-standing hurdle for computer vision applications. Several works have been focused on transferring advances from image classification, detection, and segmentation to the niche of image dehazing, primarily focusing on contrastive learning and knowledge distillation. However, these approaches prove computationally expensive, raising concern regarding their applicability to on-the-edge use-cases. This work introduces a simple, lightweight, and efficient framework for single-image haze removal, exploiting rich "dark-knowledge" information from a lightweight pre-t…
The Chinese University of Hong Kong（香港中文大学）；Kuaishou Technology（快手科技）；Tsinghua University（清华大学）；SmartMore（思谋科技）
Video super-resolution (VSR) aims to utilize multiple low-resolution frames to generate a high-resolution prediction for each frame. In this process, inter- and intra-frames are the key sources for exploiting temporal and spatial information. However, there are a couple of limitations for existing VSR methods. First, optical flow is often used to establish temporal correspondence. But flow estimation itself is error-prone and affects recovery results. Second, similar patterns existing in natural images are rarely exploited for the VSR task. Motivated by these findings, we propose a temporal mu…
Nankai University（南开大学）；Beijing Institute of Technology（北京理工大学）；Hefei University of Technology（合肥工业大学）
Recent progress on salient object detection mainly aims at exploiting how to effectively integrate multi-scale convolutional features in convolutional neural networks (CNNs). Many popular methods impose deep supervision to perform side-output predictions that are linearly aggregated for final saliency prediction. In this paper, we theoretically and experimentally demonstrate that linear aggregation of side-output predictions is suboptimal, and it only makes limited use of the side-output information obtained by deep supervision. To solve this problem, we propose Deeply-supervised Nonlinear Agg…
Shanghai Jiao Tong University（上海交通大学）；University of Michigan, Ann Arbor（密歇根大学安娜堡分校）
We address the person re-identification problem by effectively exploiting a globally discriminative feature representation from a sequence of tracked human regions/patches. This is in contrast to previous person re-id works, which rely on either single frame based person to person patch matching, or graph based sequence to sequence matching. We show that a progressive/sequential fusion framework based on long short term memory (LSTM) network aggregates the frame-wise human region representation at each time stamp and yields a sequence level human feature representation. Since LSTM nodes can re…
UiT The Arctic University of Norway（北极挪威特罗姆瑟大学）；NORCE Norwegian Research Center（NORCE挪威研究中心）；University of Genoa（热那亚大学）
Image translation with convolutional autoencoders has recently been used as an approach to multimodal change detection in bitemporal satellite images. A main challenge is the alignment of the code spaces by reducing the contribution of change pixels to the learning of the translation function. Many existing approaches train the networks by exploiting supervised information of the change areas, which, however, is not always available. We propose to extract relational pixel information captured by domain-specific affinity matrices at the input and use this to enforce alignment of the code spaces…
SenseTime Research（商汤科技研究院）；Harbin Institute of Technology（哈尔滨工业大学）；Nanjing University of Science and Technology（南京理工大学）
Nowadays stereo cameras are more commonly adopted in emerging devices such as dual-lens smartphones and unmanned aerial vehicles. However, they also suffer from blurry images in dynamic scenes which leads to visual discomfort and hampers further image processing. Previous works have succeeded in monocular deblurring, yet there are few studies on deblurring for stereoscopic images. By exploiting the two-view nature of stereo images, we propose a novel stereo image deblurring network with Depth Awareness and View Aggregation, named DAVANet. In our proposed network, 3D scene cues from the depth a…
Peking University（北京大学）；Beijing University of Posts and Telecommunications（北京邮电大学）
Conventional deep learning based methods for object detection require a large amount of bounding box annotations for training, which is expensive to obtain such high quality annotated data. Few-shot object detection, which learns to adapt to novel classes with only a few annotated examples, is very challenging since the fine-grained feature of novel object can be easily overlooked with only a few data available. In this work, aiming to fully exploit features of annotated novel object and capture fine-grained features of query object, we propose Dense Relation Distillation with Context-aware Ag…
City University of Hong Kong（香港城市大学）；Beijing Jiaotong University（北京交通大学）；Nanyang Technological University（南洋理工大学）
Co-Salient Object Detection (CoSOD) aims at discovering salient objects that repeatedly appear in a given query group containing two or more relevant images. One challenging issue is how to effectively capture co-saliency cues by modeling and exploiting inter-image relationships. In this paper, we present an end-to-end collaborative aggregation-and-distribution network (CoADNet) to capture both salient and repetitive visual patterns from multiple images. First, we integrate saliency priors into the backbone features to suppress the redundant background information through an online intra-salie…
Beijing Laboratory of Advanced Information Networks（北京先进信息网络实验室）；Beijing University of Posts and Telecommunications（北京邮电大学）；Horizon Robotics（地平线机器人）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Human pose estimation has witnessed a significant advance thanks to the development of deep learning. Recent human pose estimation approaches tend to directly predict the location heatmaps, which causes quantization errors and inevitably deteriorates the performance within the reduced network output. Aim at solving it, we revisit the heatmap-offset aggregation method and propose the Offset-guided Network (OGN) with an intuitive but effective fusion strategy for both two-stages pose estimation and Mask R-CNN. For two-stages pose estimation, a greedy box generation strategy is also proposed to k…
National University of Singapore（新加坡国立大学）；Singapore-MIT Alliance for Research and Technology (SMART) Centre（新加坡-麻省理工学院研究与技术联盟中心）
Exploiting multi-scale features has shown great potential in tackling semantic segmentation problems. The aggregation is commonly done with sum or concatenation (concat) followed by convolutional (conv) layers. However, it fully passes down the high-level context to the following hierarchy without considering their interrelation. In this work, we aim to enable the low-level feature to aggregate the complementary context from adjacent high-level feature maps by a cross-scale pixel-to-region relation operation. We leverage cross-scale context propagation to make the long-range dependency captura…
Recent progress on salient object detection mainly aims at exploiting how to effectively integrate convolutional side-output features in convolutional neural networks (CNN). Based on this, most of the existing state-of-the-art saliency detectors design complex network structures to fuse the side-output features of the backbone feature extraction networks. However, should the fusion strategies be more and more complex for accurate salient object detection? In this paper, we observe that the contexts of a natural image can be well expressed by a high-to-low self-learning of side-output convoluti…
Recent advances in 3D sensing have created unique challenges for computer vision. One fundamental challenge is finding a good representation for 3D sensor data. Most popular representations (such as PointNet) are proposed in the context of processing truly 3D data (e.g. points sampled from mesh models), ignoring the fact that 3D sensored data such as a LiDAR sweep is in fact 2.5D. We argue that representing 2.5D data as collections of (x, y, z) points fundamentally destroys hidden information about freespace. In this paper, we demonstrate such knowledge can be efficiently recovered through 3D …
