We propose a new convolution called Dynamic Region-Aware Convolution (DRConv), which can automatically assign multiple filters to corresponding spatial regions where features have similar representation. In this way, DRConv outperforms standard convolution in modeling semantic variations. Standard convolutional layer can increase the number of filers to extract more visual elements but results in high computational cost. More gracefully, our DRConv transfers the increasing channel-wise filters to spatial dimension with learnable instructor, which not only improve representation ability of convolution, but also maintains computational cost and the translation-invariance as standard convolution dose. DRConv is an effective and elegant method for handling complex and variable spatial information distribution. It can substitute standard convolution in any existing networks for its plug-and-play property, especially to power convolution layers in efficient networks. We evaluate DRConv on a wide range of models (MobileNet series, ShuffleNetV2, etc.) and tasks (Classification, Face Recognition, Detection and Segmentation). On ImageNet classification, DRConv-based ShuffleNetV2-0.5x achieves state-of-the-art performance of 67.1% at 46M multiply-adds level with 6.3% relative improvement.
The Hong Kong University of Science and Technology（香港科技大学）；University of Colorado at Boulder（科罗拉多大学博尔德分校）
As convolution has empowered many smart applications, dynamic convolution further equips it with the ability to adapt to diverse inputs. However, the static and dynamic convolutions are either layout-agnostic or computation-heavy, making it inappropriate for layout-specific applications, e.g., face recognition and medical image segmentation. We observe that these applications naturally exhibit the characteristics of large intra-image (spatial) variance and small cross-image variance. This observation motivates our efficient translation variant convolution (TVConv) for layout-aware visual proce…
Most existing re-identification methods focus on learning robust and discriminative features with deep convolution networks. However, many of them consider content similarity separately and fail to utilize the context information of the query and gallery sets, e.g. probe-gallery and gallery-gallery relations, thus hard samples may not be well solved due to the limited or even misleading information. In this paper, we present a novel Context-Aware Graph Convolution Network (CAGCN), where the probe-gallery relations are encoded into the graph nodes and the graph edge connections are well control…
QA-ReID: Quality-Aware Query-Adaptive Convolution Leveraging Fused Global and Structural Cues for Clothes-Changing ReID
School of Business, Stevens Institute of Technology（斯蒂文斯理工学院商学院）；Electrical and Computer Engineering, University of California, San Diego（加州大学圣地亚哥分校电子与计算机工程系）；Tandon School of Engineering, New York University（纽约大学塔恩工学院）；Institute of Operations Research and Analytics, National University of Singapore（新加坡国立大学运筹与分析研究所）
Guangxi Normal University（广西师范大学）；Huaqiao University（华侨大学）；Harbin Institute of Technology（哈尔滨工业大学）；Peng Cheng Laboratory（鹏城实验室）；Beijing Seetatech Technology（北京中科视拓科技有限公司）；Institute of Automation, CAS（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Centre for Artificial Intelligence and Robotics, HKISI_CAS（香港中科院人工智能与机器人中心）
A practical long-term tracker typically contains three key properties, i.e. an efficient model design, an effective global re-detection strategy and a robust distractor awareness mechanism. However, most state-of-the-art long-term trackers (e.g., Pseudo and re-detecting based ones) do not take all three key properties into account and therefore may either be time-consuming or drift to distractors. To address the issues, we propose a two-task tracking frame work (named DMTrack), which utilizes two core components (i.e., one-shot detection and re-identification (re-id) association) to achieve di…
Multiple instance learning (MIL) is the preferred approach for whole slide image classification. However, most MIL approaches do not exploit the interdependencies of tiles extracted from a whole slide image, which could provide valuable cues for classification. This paper presents a novel MIL approach that exploits the spatial relationship of tiles for classifying whole slide images. To do so, a sparse map is built from tiles embeddings, and is then classified by a sparse-input CNN. It obtained state-of-the-art performance over popular MIL approaches on the classification of cancer subtype inv…
Nanjing University of Science and Technology（南京理工大学）；National University of Defense Technology（国防科技大学）；Monash University（莫纳什大学）
In hyperspectral image (HSI) classification, spatial context has demonstrated its significance in achieving promising performance. However, conventional spatial context-based methods simply assume that spatially neighboring pixels should correspond to the same land-cover class, so they often fail to correctly discover the contextual relations among pixels in complex situations, and thus leading to imperfect classification results on some irregular or inhomogeneous regions such as class boundaries. To address this deficiency, we develop a new HSI classification method based on the recently prop…
We propose a fully-convolutional neural-network architecture for image denoising which is simple yet powerful. Its structure allows to exploit the gradual nature of the denoising process, in which shallow layers handle local noise statistics, while deeper layers recover edges and enhance textures. Our method advances the state-of-the-art when trained for different noise levels and distributions (both Gaussian and Poisson). In addition, we show that making the denoiser class-aware by exploiting semantic class information boosts performance, enhances textures and reduces artifacts.
The University of Adelaide（阿德莱德大学）；Monash University（莫纳什大学）
We propose a fully convolutional multi-person pose estimation framework using dynamic instance-aware convolutions, termed FCPose. Different from existing methods, which often require ROI (Region of Interest) operations and/or grouping post-processing, FCPose eliminates the ROIs and grouping post-processing with dynamic instance-aware keypoint estimation heads. The dynamic keypoint heads are conditioned on each instance (person), and can encode the instance concept in the dynamically-generated weights of their filters. Moreover, with the strong representation capacity of dynamic convolutions, t…
South China University of Technology（华南理工大学）；Key Laboratory of Big Data and Intelligent Robot, Ministry of Education（教育部大数据与智能机器人重点实验室）；Pazhou Laboratory（琶洲实验室）；Microsoft Research Asia（微软亚洲研究院）
Convolutional Neural Networks (CNNs) have achieved great success due to the powerful feature learning ability of convolution layers. Specifically, the standard convolution traverses the input images/features using a sliding window scheme to extract features. However, not all the windows contribute equally to the prediction results of CNNs. In practice, the convolutional operation on some of the windows (e.g., smooth windows that contain very similar pixels) can be very redundant and may introduce noises into the computation. Such redundancy may not only deteriorate the performance but also inc…
Existing 3D instance segmentation methods are predominated by the bottom-up design -- manually fine-tuned algorithm to group points into clusters followed by a refinement network. However, by relying on the quality of the clusters, these methods generate susceptible results when (1) nearby objects with the same semantic class are packed together, or (2) large objects with loosely connected regions. To address these limitations, we introduce ISBNet, a novel cluster-free method that represents instances as kernels and decodes instance masks via dynamic convolution. To efficiently generate high-r…
Carnegie Mellon University（卡内基梅隆大学）；Ryerson University（瑞尔森大学）；Facebook AI Research（Facebook人工智能研究院）
We introduce an approach to integrate segmentation information within a convolutional neural network (CNN). This counter-acts the tendency of CNNs to smooth information across regions and increases their spatial precision. To obtain segmentation information, we set up a CNN to provide an embedding space where region co-membership can be estimated based on Euclidean distance. We use these embeddings to compute a local attention mask relative to every neuron position. We incorporate such masks in CNNs and replace the convolution operation with a "segmentation-aware" variant that allows a neuron …
University of Amsterdam（阿姆斯特丹大学）；Google Research（谷歌研究院）
A key challenge for RGB-D segmentation is how to effectively incorporate 3D geometric information from the depth channel into 2D appearance features. We propose to model the effective receptive field of 2D convolution based on the scale and locality from the 3D neighborhood. Standard convolutions are local in the image space ($u, v$), often with a fixed receptive field of 3x3 pixels. We propose to define convolutions local with respect to the corresponding point in the 3D real-world space ($x, y, z$), where the depth channel is used to adapt the receptive field of the convolution, which yields…
University of Zaragoza（萨拉戈萨大学）；University of Freiburg（弗莱堡大学）；Intel Labs（英特尔实验室）；Bitbrain（Bitbrain（公司））；cs.uni-freiburg.de（（注：原文本中该部分为邮箱域名，不应作为机构提取，实际有效机构为上述列出的））
Single-view depth estimation suffers from the problem that a network trained on images from one camera does not generalize to images taken with a different camera model. Thus, changing the camera model requires collecting an entirely new training dataset. In this work, we propose a new type of convolution that can take the camera parameters into account, thus allowing neural networks to learn calibration-aware patterns. Experiments confirm that this improves the generalization capabilities of depth prediction networks considerably, and clearly outperforms the state of the art when the train an…
Huaqiao University（华侨大学）；Guangdong Second Provincial General Hospital（广东省第二人民医院）
Semantic segmentation of electron microscopy (EM) is an essential step to efficiently obtain reliable morphological statistics. Despite the great success achieved using deep convolutional neural networks (CNNs), they still produce coarse segmentations with lots of discontinuities and false positives for mitochondria segmentation. In this study, we introduce a centerline-aware multitask network by utilizing centerline as an intrinsic shape cue of mitochondria to regularize the segmentation. Since the application of 3D CNNs on large medical volumes is usually hindered by their substantial comput…
University of Washington（华盛顿大学）；NEC Laboratories America, Inc.（美国NEC实验室公司）；Baidu, Inc.（百度公司）；Stanford University（斯坦福大学）
In CNN-based object detection methods, region proposal becomes a bottleneck when objects exhibit significant scale variation, occlusion or truncation. In addition, these methods mainly focus on 2D object detection and cannot estimate detailed properties of objects. In this paper, we propose subcategory-aware CNNs for object detection. We introduce a novel region proposal network that uses subcategory information to guide the proposal generating process, and a new detection network for joint detection and subcategory classification. By using subcategories related to object pose, we achieve stat…
Beihang University（北京航空航天大学）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）
Since the superiority of Transformer in learning long-term dependency, the sign language Transformer model achieves remarkable progress in Sign Language Recognition (SLR) and Translation (SLT). However, there are several issues with the Transformer that prevent it from better sign language understanding. The first issue is that the self-attention mechanism learns sign video representation in a frame-wise manner, neglecting the temporal semantic structure of sign gestures. Secondly, the attention mechanism with absolute position encoding is direction and distance unaware, thus limiting its abil…
Deep Learning could drastically boost the classification accuracy for Hyperspectral Imaging (HSI). Still, the training on the mostly small hyperspectral data sets is not trivial. Two key challenges are the large channel dimension of the recordings and the incompatibility between cameras of different manufacturers. By introducing a suitable model bias and continuously defining the channel dimension, we propose a 2D convolution optimized for these challenges of Hyperspectral Imaging. We evaluate the method based on two different hyperspectral applications (inline inspection and remote sensing). …
Litemaze；VinAI Research（VinAI 研究院）；VinUniversity（Vin 大学）；Hong Kong University of Science and Technology（香港科技大学）
Recent advances in deep learning for 3D point clouds have shown great promises in scene understanding tasks thanks to the introduction of convolution operators to consume 3D point clouds directly in a neural network. Point cloud data, however, could have arbitrary rotations, especially those acquired from 3D scanning. Recent works show that it is possible to design point cloud convolutions with rotation invariance property, but such methods generally do not perform as well as translation-invariant only convolution. We found that a key reason is that compared to point coordinates, rotation-inva…
Washington University in St. Louis（圣路易斯华盛顿大学）；Megvii Inc.（旷视科技）
In this paper, we propose a novel learning-based pipeline for partially overlapping 3D point cloud registration. The proposed model includes an iterative distance-aware similarity matrix convolution module to incorporate information from both the feature and Euclidean space into the pairwise point matching process. These convolution layers learn to match points based on joint information of the entire geometric features and Euclidean offset for each point pair, overcoming the disadvantage of matching by simply taking the inner product of feature vectors. Furthermore, a two-stage learnable poin…
Skeleton-based action recognition receives increasing attention because the skeleton representations reduce the amount of training data by eliminating visual information irrelevant to actions. To further improve the sample efficiency, meta-learning-based one-shot learning solutions were developed for skeleton-based action recognition. These methods find the nearest neighbor according to the similarity between instance-level global average embedding. However, such measurement holds unstable representativity due to inadequate generalized learning on local invariant and noisy features, while intu…
Chonnam National University（全南国立大学）；Xidian University（西安电子科技大学）
Although deep convolutional neural networks (CNNs) have obtained outstanding performance in image superresolution (SR), their computational cost increases geometrically as CNN models get deeper and wider. Meanwhile, the features of intermediate layers are treated equally across the channel, thus hindering the representational capability of CNNs. In this paper, we propose an attention-aware linear depthwise network to address the problems for single image SR, named ALDNet. Specifically, linear depthwise convolution allows CNN-based SR models to preserve useful information for reconstructing a s…
In this paper, we investigate the dynamics-aware adversarial attack problem in deep neural networks. Most existing adversarial attack algorithms are designed under a basic assumption -- the network architecture is fixed throughout the attack process. However, this assumption does not hold for many recently proposed networks, e.g. 3D sparse convolution network, which contains input-dependent execution to improve computational efficiency. It results in a serious issue of lagged gradient, making the learned attack at the current step ineffective due to the architecture changes afterward. To addre…
Finding semantic correspondences is a challenging problem. With the breakthrough of CNNs stronger features are available for tasks like classification but not specifically for the requirements of semantic matching. In the following we present a weakly supervised metric learning approach which generates stronger features by encoding far more context than previous methods. First, we generate more suitable training data using a geometrically informed correspondence mining method which is less prone to spurious matches and requires only image category labels as supervision. Second, we introduce a …
New York University（纽约大学）；Tandon School of Engineering, New York University（纽约大学坦登工程学院）；Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）
To better address challenging issues of the irregularity and inhomogeneity inherently present in 3D point clouds, researchers have been shifting their focus from the design of hand-craft point feature towards the learning of 3D point signatures using deep neural networks for 3D point cloud classification. Recent proposed deep learning based point cloud classification methods either apply 2D CNN on projected feature images or apply 1D convolutional layers directly on raw point sets. These methods cannot adequately recognize fine-grained local structures caused by the uneven density distribution…
Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所）；Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences（中国科学院机器人与智能制造创新研究院）；University of Chinese Academy of Sciences（中国科学院大学）
Rotation-invariant (RI) 3D deep learning methods suffer performance degradation as they typically design RI representations as input that lose critical global information comparing to 3D coordinates. Most state-of-the-arts address it by incurring additional blocks or complex global representations in a heavy and ineffective manner. In this paper, we reveal that the global information loss stems from an unexplored pose information loss problem, which can be solved more efficiently and effectively as we only need to restore more lightweight local pose in each layer, and the global information ca…
Northwestern Polytechnical University（西北工业大学）；Inception Institute of Artificial Intelligence（人工智能初始研究所）
Humans perform co-saliency detection by first summarizing the consensus knowledge in the whole group and then searching corresponding objects in each image. Previous methods usually lack robustness, scalability, or stability for the first process and simply fuse consensus features with image features for the second process. In this paper, we propose a novel consensus-aware dynamic convolution model to explicitly and effectively perform the "summarize and search" process. To summarize consensus image features, we first summarize robust features for every single image using an effective pooling …
Depth Completion deals with the problem of converting a sparse depth map to a dense one, given the corresponding color image. Convolutional spatial propagation network (CSPN) is one of the state-of-the-art (SoTA) methods of depth completion, which recovers structural details of the scene. In this paper, we propose CSPN++, which further improves its effectiveness and efficiency by learning adaptive convolutional kernel sizes and the number of iterations for the propagation, thus the context and computational resources needed at each pixel could be dynamically assigned upon requests. Specificall…
MX Media Co., Ltd.（MX媒体有限公司）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Interactions between users and videos are the major data source of performing video recommendation. Despite lots of existing recommendation methods, user behaviors on videos, which imply the complex relations between users and videos, are still far from being fully explored. In the paper, we present a model named Sagittarius. Sagittarius adopts a graph convolutional neural network to capture the influence between users and videos. In particular, Sagittarius differentiates between different user behaviors by weighting and fuses the semantics of user behaviors into the embeddings of users and vi…
University of Toronto（多伦多大学）；LG AI Research（LG人工智能研究院）
Visualizing the features captured by Convolutional Neural Networks (CNNs) is one of the conventional approaches to interpret the predictions made by these models in numerous image recognition applications. Grad-CAM is a popular solution that provides such a visualization by combining the activation maps obtained from the model. However, the average gradient-based terms deployed in this method underestimates the contribution of the representations discovered by the model to its predictions. Addressing this problem, we introduce a solution to tackle this issue by computing the path integral of t…
Recently, vision transformers started to show impressive results which outperform large convolution based models significantly. However, in the area of small models for mobile or resource constrained devices, ConvNet still has its own advantages in both performance and model complexity. We propose ParC-Net, a pure ConvNet based backbone model that further strengthens these advantages by fusing the merits of vision transformers into ConvNets. Specifically, we propose position aware circular convolution (ParC), a light-weight convolution op which boasts a global receptive field while producing l…
Graph Neural Networks (GNNs) generalize neural networks from applications on regular structures to applications on arbitrary graphs, and have shown success in many application domains such as computer vision, social networks and chemistry. In this paper, we extend GNNs along two directions: a) allowing features at each node to be represented by 2D spatial confidence maps instead of 1D vectors; and b) proposing an efficient operation to integrate information from neighboring nodes through 2D convolutions with different learnable kernels at each edge. The proposed SIA-GCN can efficiently extract…
University of Queensland（昆士兰大学）；University of Adelaide（阿德莱德大学）
Most video based action recognition approaches create the video-level representation by temporally pooling the features extracted at each frame. The pooling methods that they adopt, however, usually completely or partially neglect the dynamic information contained in the temporal domain, which may undermine the discriminative power of the resulting video representation since the video sequence order could unveil the evolution of a specific event or action. To overcome this drawback and explore the importance of incorporating the temporal order information, in this paper we propose a novel temp…
We propose a novel visual context-aware filter generation module which incorporates contextual information present in images into Convolutional Neural Networks (CNNs). In contrast to traditional CNNs, we do not employ the same set of learned convolution filters for all input image instances. Our proposed input-conditioned convolution filters when combined with techniques inspired by Multi-instance learning and max-pooling, results in a transformation-invariant neural network. We investigated the performance of our proposed framework on three MNIST variations, which covers both rotation and sca…
Shenzhen University（深圳大学）；National University of Defense Technology（国防科技大学）；Tel Aviv University（特拉维夫大学）
Without a shape-aware response, it is hard to characterize the 3D geometry of a point cloud efficiently with a compact set of kernels. In this paper, we advocate the use of Hausdorff distance as a shape-aware distance measure for calculating point convolutional responses. The technique we present, coined Hausdorff Point Convolution (HPC), is shape-aware. We show that HPC constitutes a powerful point feature learning with a rather compact set of only four types of geometric priors as kernels. We further develop a HPC-based deep neural network (HPC-DNN). Task-specific learning can be achieved by…
North Carolina State University（北卡罗来纳州立大学）；Alibaba Group（阿里巴巴集团）；Jilin University（吉林大学）
Jointly integrating aspect ratio and context has been extensively studied and shown performance improvement in traditional object detection systems such as the DPMs. It, however, has been largely ignored in deep neural network based detection systems. This paper presents a method of integrating a mixture of object models and region-based convolutional networks for accurate object detection. Each mixture component accounts for both object aspect ratio and multi-scale contextual information explicitly: (i) it exploits a mixture of tiling configurations in the RoI pooling to remedy the warping ar…
Online semantic 3D segmentation in company with real-time RGB-D reconstruction poses special challenges such as how to perform 3D convolution directly over the progressively fused 3D geometric data, and how to smartly fuse information from frame to frame. We propose a novel fusion-aware 3D point convolution which operates directly on the geometric surface being reconstructed and exploits effectively the inter-frame correlation for high quality 3D feature learning. This is enabled by a dedicated dynamic data structure which organizes the online acquired point cloud with global-local trees. Glob…
Detecting human-object interactions is essential for comprehensive understanding of visual scenes. In particular, spatial connections between humans and objects are important cues for reasoning interactions. To this end, we propose a skeleton-aware graph convolutional network for human-object interaction detection, named SGCN4HOI. Our network exploits the spatial connections between human keypoints and object keypoints to capture their fine-grained structural interactions via graph convolutions. It fuses such geometric features with visual features and spatial configuration features obtained f…
An Efficient Deep Template Matching and In-Plane Pose Estimation Method via Template-Aware Dynamic Convolution
School of Computer Science, Chengdu University of Information Technology（成都信息工程大学计算机科学学院）；Faculty of Mechanical Engineering and Mechanics, Ningbo University（宁波大学机械与力学学院）
Technical University of Munich（慕尼黑工业大学）；Google Inc.（谷歌公司）
With the advent of deep learning, estimating depth from a single RGB image has recently received a lot of attention, being capable of empowering many different applications ranging from path planning for robotics to computational cinematography. Nevertheless, while the depth maps are in their entirety fairly reliable, the estimates around object discontinuities are still far from satisfactory. This can be contributed to the fact that the convolutional operator naturally aggregates features across object discontinuities, resulting in smooth transitions rather than clear boundaries. Therefore, i…
We present a hardware-efficient architecture of convolutional neural network, which has a repvgg-like architecture. Flops or parameters are traditional metrics to evaluate the efficiency of networks which are not sensitive to hardware including computing ability and memory bandwidth. Thus, how to design a neural network to efficiently use the computing ability and memory bandwidth of hardware is a critical problem. This paper proposes a method how to design hardware-aware neural network. Based on this method, we designed EfficientRep series convolutional networks, which are high-computation ha…
With a wide range of shadows in many collected images, shadow removal has aroused increasing attention since uncontaminated images are of vital importance for many downstream multimedia tasks. Current methods consider the same convolution operations for both shadow and non-shadow regions while ignoring the large gap between the color mappings for the shadow region and the non-shadow region, leading to poor quality of reconstructed images and a heavy computation burden. To solve this problem, this paper introduces a novel plug-and-play Shadow-Aware Dynamic Convolution (SADC) module to decouple …
Enhanced Deformable Convolution with Center-invariant Offset and Edge-aware Mask
Beihang University（北京航空航天大学）；Shanghai Academy of Spaceflight Technology（上海航天技术研究院）；Shanghai Radio Equipment Research Institute（上海无线电设备研究所）；Cardiff University（卡迪夫大学）；Shenzhen University（深圳大学）；Sun Yat-sen University（中山大学）；Lancaster University（兰卡斯特大学）
A new method of recognizing apple leaf diseases through region-of-interest-aware deep convolutional neural network is proposed in this paper. The primary idea is that leaf disease symptoms appear in the leaf area whereas the background region contains no useful information regarding leaf diseases. To realize this idea, two subnetworks are first designed. One is for the division of the input image into three areas: background, leaf area, and spot area indicating the leaf diseases, which is the region of interest, and the other is for the classification of leaf diseases. The two subnetworks exhi…
The Chinese University of Hong Kong（香港中文大学）；Massachusetts Institute of Technology（麻省理工学院）；MEGVII Technology（旷视科技）
In this paper, we explore the mask representation in instance segmentation with Point-of-Interest (PoI) features. Differentiating multiple potential instances within a single PoI feature is challenging because learning a high-dimensional mask feature for each instance using vanilla convolution demands a heavy computing burden. To address this challenge, we propose an instance-aware convolution. It decomposes this mask representation learning task into two tractable modules as instance-aware weights and instance-agnostic features. The former is to parametrize convolution for producing mask feat…
This paper tackles the problem of few-shot learning, which aims to learn new visual concepts from a few examples. A common problem setting in few-shot classification assumes random sampling strategy in acquiring data labels, which is inefficient in practical applications. In this work, we introduce a new budget-aware few-shot learning problem that not only aims to learn novel object categories, but also needs to select informative examples to annotate in order to achieve data efficiency. We develop a meta-learning strategy for our budget-aware few-shot learning task, which jointly learns a nov…
University of Liverpool（利物浦大学）；University of Portsmouth（朴茨茅斯大学）；Chinese Academy of Sciences（中国科学院）；Remark AI UK Limited（Remark AI 英国有限公司）
Segmentation is an essential operation of image processing. The convolution operation suffers from a limited receptive field, while global modelling is fundamental to segmentation tasks. In this paper, we apply graph convolution into the segmentation task and propose an improved \textit{Laplacian}. Different from existing methods, our \textit{Laplacian} is data-dependent, and we introduce two attention diagonal matrices to learn a better vertex relationship. In addition, it takes advantage of both region and boundary information when performing graph-based information propagation. Specifically…
