CA-Stream: Attention-based pooling for interpretable image recognition
Centrale Marseille（马赛中央理工学院）；Aix Marseille Univ（艾克斯-马赛大学）；CNRS（法国国家科学研究中心）；Institute of Intelligent Software（智能软件研究所）；Institute of Advanced Research on Artificial Intelligence (IARAI)（高级人工智能研究所（IARAI））
Felipe Torres, Hanwei Zhang, Ronan Sicre, Stéphane Ayache, Yannis Avrithis
Explanations obtained from transformer-based architectures in the form of raw attention, can be seen as a class-agnostic saliency map. Additionally, attention-based pooling serves as a form of masking the in feature space. Motivated by this observation, we design an attention-based pooling mechanism intended to replace Global Average Pooling (GAP) at inference. This mechanism, called Cross-Attention Stream (CA-Stream), comprises a stream of cross attention blocks interacting with features at different network depths. CA-Stream enhances interpretability in models, while preserving recognition performance.
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
In group activity recognition, hierarchical framework is widely adopted to represent the relationships between individuals and their corresponding group, and has achieved promising performance. However, the existing methods simply employed max/average pooling in this framework, which ignored the distinct contributions of different individuals to the group activity recognition. In this paper, we propose a new contextual pooling scheme, named attentive pooling, which enables the weighted information transition from individual actions to group activity. By utilizing the attention mechanism, the a…
Sea-Net: A Small and Inherently Interpretable Neural Network for Time Series Classification
Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL)（里尔信息、信号与自动化研究中心）；University of Lille（里尔大学）；CNRS（法国国家科学研究中心）；Centrale Lille（里尔中央理工学院）
Clinical-Prior Guided Multi-Modal Learning with Latent Attention Pooling for Gait-Based Scoliosis Screening
Orthopaedic Centre, The University of Hong Kong - Shenzhen Hospital, Shenzhen, China（香港大学深圳医院骨科中心）；Translational Medicine Centre, The University of Hong Kong - Shenzhen Hospital, China（香港大学深圳医院转化医学中心）；Department of Orthopaedics and Traumatology, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong, China（香港大学李嘉成医学院骨科及创伤外科学院）；Huawei, China（华为）
Attention Pooling Enhances NCA-based Classification of Microscopy Images
Institute of AI for Health, Computational Health Center, Helmholtz Munich, Munich, Germany（人工智能与健康研究所，计算健康中心，海德堡慕尼黑研究中心，慕尼黑，德国）；Computer Aided Medical Procedures, Technical University of Munich, Munich, Germany（计算机辅助医疗程序，慕尼黑技术大学，慕尼黑，德国）；Institute of Pathology, Technical University Munich, Munich, Germany（病理研究所，慕尼黑技术大学，慕尼黑，德国）；Munich Center for Machine Learning, Munich, Germany（慕尼黑机器学习中心，慕尼黑，德国）
Tianjin University（天津大学）；Hefei University of Technology（合肥工业大学）
Deep ConvNets have shown its good performance in image classification tasks. However it still remains as a problem in deep video representation for action recognition. The problem comes from two aspects: on one hand, current video ConvNets are relatively shallow compared with image ConvNets, which limits its capability of capturing the complex video action information; on the other hand, temporal information of videos is not properly utilized to pool and encode the video sequences. Towards these issues, in this paper, we utilize two state-of-the-art ConvNets, i.e., the very deep spatial net (V…
University of Central Florida（中佛罗里达大学）；North Carolina State University（北卡罗来纳州立大学）；OPPO Seattle Research Center（OPPO西雅图研究中心）；Westlake University（西湖大学）
Transformer architectures have achieved SOTA performance on the human mesh recovery (HMR) from monocular images. However, the performance gain has come at the cost of substantial memory and computational overhead. A lightweight and efficient model to reconstruct accurate human mesh is needed for real-world applications. In this paper, we propose a pure transformer architecture named POoling aTtention TransformER (POTTER) for the HMR task from single images. Observing that the conventional attention module is memory and computationally expensive, we propose an efficient pooling attention module…
Fully supervised semantic segmentation learns from dense masks, which requires heavy annotation cost for closed set. In this paper, we use natural language as supervision without any pixel-level annotation for open world segmentation. We call the proposed framework as FreeSeg, where the mask is freely available from raw feature map of pretraining model. Compared with zero-shot or openset segmentation, FreeSeg doesn't require any annotated masks, and it widely predicts categories beyond class-agnostic unsupervised segmentation. Specifically, FreeSeg obtains free mask from Image-Text Similarity …
Currently, owing to the ubiquity of mobile devices, online handwritten Chinese character recognition (HCCR) has become one of the suitable choice for feeding input to cell phones and tablet devices. Over the past few years, larger and deeper convolutional neural networks (CNNs) have extensively been employed for improving character recognition performance. However, its substantial storage requirement is a significant obstacle in deploying such networks into portable electronic devices. To circumvent this problem, we propose a novel technique called DropWeight for pruning redundant connections …
Inria（法国国家信息与自动化研究所）；WILLOW（威洛实验室）；Departement d’Informatique de l’École Normale Supérieure（巴黎高等师范学院信息学系）；PSL Research University（巴黎文理研究大学）；Czech Institute of Informatics, Robotics and Cybernetics（捷克理工大学信息学、机器人学与控制论研究所）；Czech Technical University in Prague（布拉格捷克理工大学）
Current methods for video analysis often extract frame-level features using pre-trained convolutional neural networks (CNNs). Such features are then aggregated over time e.g., by simple temporal averaging or more sophisticated recurrent neural networks such as long short-term memory (LSTM) or gated recurrent units (GRU). In this work we revise existing video representations and study alternative methods for temporal aggregation. We first explore clustering-based aggregation layers and propose a two-stream architecture aggregating audio and visual features. We then introduce a learnable non-lin…
School of Signal and Information Processing, Southeast University（东南大学信号与信息处理学院）；SenseTime Group Limited（商汤科技集团有限公司）
Face anti-spoofing is an important task to protect the security of face recognition. Most of previous work either struggle to capture discriminative and generalizable feature or rely on auxiliary information which is unavailable for most of industrial product. Inspired by the video classification work, we propose an efficient two-stream model to capture the key differences between live and spoof faces, which takes multi-frames and RGB difference as input respectively. Feature pyramid modules with two opposite fusion directions and pyramid pooling modules are applied to enhance feature represen…
University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Purdue University（普渡大学）
Pose guided person image generation means to generate a photo-realistic person image conditioned on an input person image and a desired pose. This task requires spatial manipulation of the source image according to the target pose. However, the generative adversarial networks (GANs) widely used for image generation and translation rely on spatially local and translation equivariant operators, i.e., convolution, pooling and unpooling, which cannot handle large image deformation. This paper introduces a novel two-stream appearance transfer network (2s-ATN) to address this challenge. It is a mult…
Boston University（波士顿大学）；Baidu Research（百度研究院）；University of British Columbia（英属哥伦比亚大学）
Dense video captioning is a fine-grained video understanding task that involves two sub-problems: localizing distinct events in a long video stream, and generating captions for the localized events. We propose the Joint Event Detection and Description Network (JEDDi-Net), which solves the dense video captioning task in an end-to-end fashion. Our model continuously encodes the input video stream with three-dimensional convolutional layers, proposes variable-length temporal events based on pooled features, and generates their captions. Proposal features are extracted within each proposal segment…
University of Maryland, College Park（马里兰大学帕克分校）；Adobe Research（Adobe研究院）
Image manipulation detection is different from traditional semantic object detection because it pays more attention to tampering artifacts than to image content, which suggests that richer features need to be learned. We propose a two-stream Faster R-CNN network and train it endto- end to detect the tampered regions given a manipulated image. One of the two streams is an RGB stream whose purpose is to extract features from the RGB image input to find tampering artifacts like strong contrast difference, unnatural tampered boundaries, and so on. The other is a noise stream that leverages the noi…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Three dimensional convolutional neural networks (3D CNNs) have been established as a powerful tool to simultaneously learn features from both spatial and temporal dimensions, which is suitable to be applied to video-based action recognition. In this work, we propose not to directly use the activations of fully-connected layers of a 3D CNN as the video feature, but to use selective convolutional layer activations to form a discriminative descriptor for video. It pools the feature on the convolutional layers under the guidance of body joint positions. Two schemes of mapping body joints into conv…
IBM T.J. Watson Research Center（IBM T.J. 沃森研究中心）；Memorial Sloan-Kettering Cancer Center（纪念斯隆-凯特琳癌症中心）
Automated dermoscopic image analysis has witnessed rapid growth in diagnostic performance. Yet adoption faces resistance, in part, because no evidence is provided to support decisions. In this work, an approach for evidence-based classification is presented. A feature embedding is learned with CNNs, triplet-loss, and global average pooling, and used to classify via kNN search. Evidence is provided as both the discovered neighbors, as well as localized image regions most relevant to measuring distance between query and neighbors. To ensure that results are relevant in terms of both label accura…
University of Munich（慕尼黑大学）；Siemens AG, Corporate Technology（西门子股份公司，企业技术部）
Capsule Networks, as alternatives to Convolutional Neural Networks, have been proposed to recognize objects from images. The current literature demonstrates many advantages of CapsNets over CNNs. However, how to create explanations for individual classifications of CapsNets has not been well explored. The widely used saliency methods are mainly proposed for explaining CNN-based classifications; they create saliency map explanations by combining activation values and the corresponding gradients, e.g., Grad-CAM. These saliency methods require a specific architecture of the underlying classifiers…
In this work, we introduce a new video representation for action classification that aggregates local convolutional features across the entire spatio-temporal extent of the video. We do so by integrating state-of-the-art two-stream networks with learnable spatio-temporal feature aggregation. The resulting architecture is end-to-end trainable for whole-video classification. We investigate different strategies for pooling across space and time and combining signals from the different streams. We find that: (i) it is important to pool jointly across space and time, but (ii) appearance and motion …
University of Oulu（奥卢大学）；Delft University of Technology（代尔夫特理工大学）
To address the problem of training on small datasets for action recognition tasks, most prior works are either based on a large number of training samples or require pre-trained models transferred from other large datasets to tackle overfitting problems. However, it limits the research within organizations that have strong computational abilities. In this work, we try to propose a data-efficient framework that can train the model from scratch on small datasets while achieving promising results. Specifically, by introducing a 3D central difference convolution operation, we proposed a novel C3D …
Adaptive Enhancement and Dual-Pooling Sequential Attention for Lightweight Underwater Object Detection with YOLOv10
1,2Department of Computer Science；Engineering, Dhaka University of Engineering \& Technology Gazipur, 1707, Bangladesh 3Department of Computer Science；Engineering, BRAC University Dhaka, Bangladesh
Graz University of Technology（格拉茨技术大学）；University of Oxford（牛津大学）
Recent applications of Convolutional Neural Networks (ConvNets) for human action recognition in videos have proposed different solutions for incorporating the appearance and motion information. We study a number of ways of fusing ConvNet towers both spatially and temporally in order to best take advantage of this spatio-temporal information. We make the following findings: (i) that rather than fusing at the softmax layer, a spatial and temporal network can be fused at a convolution layer without loss of performance, but with a substantial saving in parameters; (ii) that it is better to fuse su…
In this paper, a new video classification methodology is proposed which can be applied in both first and third person videos. The main idea behind the proposed strategy is to capture complementary information of appearance and motion efficiently by performing two independent streams on the videos. The first stream is aimed to capture long-term motions from shorter ones by keeping track of how elements in optical flow images have changed over time. Optical flow images are described by pre-trained networks that have been trained on large scale image datasets. A set of multi-channel time series a…
Visual Question answering is a challenging problem requiring a combination of concepts from Computer Vision and Natural Language Processing. Most existing approaches use a two streams strategy, computing image and question features that are consequently merged using a variety of techniques. Nonetheless, very few rely on higher level image representations, which can capture semantic and spatial relationships. In this paper, we propose a novel graph-based approach for Visual Question Answering. Our method combines a graph learner module, which learns a question specific graph representation of t…
Visual Computing Institute RWTH Aachen University（亚琛工业大学视觉计算研究所）
Semantic image segmentation is an essential component of modern autonomous driving systems, as an accurate understanding of the surrounding scene is crucial to navigation and action planning. Current state-of-the-art approaches in semantic image segmentation rely on pre-trained networks that were initially developed for classifying images as a whole. While these networks exhibit outstanding recognition performance (i.e., what is visible?), they lack localization accuracy (i.e., where precisely is something located?). Therefore, additional processing steps have to be performed in order to obtai…
In this paper, we propose the use of a semantic image, an improved representation for video analysis, principally in combination with Inception networks. The semantic image is obtained by applying localized sparse segmentation using global clustering (LSSGC) prior to the approximate rank pooling which summarizes the motion characteristics in single or multiple images. It incorporates the background information by overlaying a static background from the window onto the subsequent segmented frames. The idea is to improve the action-motion dynamics by focusing on the region which is important for…
Southwest Jiaotong University（西南交通大学）；Georgia State University（佐治亚州立大学）
This paper aims to develop a new architecture that can make full use of the feature maps of convolutional networks. To this end, we study a number of methods for video-based person re-identification and make the following findings: 1) Max-pooling only focuses on the maximum value of a receptive field, wasting a lot of information. 2) Networks with different streams even including the one with the worst performance work better than networks with same streams, where each one has the best performance alone. 3) A full connection layer at the end of convolutional networks is not necessary. Based on…
PointGL: A Simple Global-Local Framework for Efficient Point Cloud Analysis
Beijing Institute of Technology（北京理工大学）；Key Laboratory of Photoelectronic Imaging Technology and System, Ministry of Education of China（光电成像技术与系统教育部重点实验室）；Chongqing Innovation Center, Beijing Institute of Technology（北京理工大学重庆创新中心）
Bilinear pooling (BLP) refers to a family of operations recently developed for fusing features from different modalities predominantly developed for VQA models. A bilinear (outer-product) expansion is thought to encourage models to learn interactions between two feature spaces and has experimentally outperformed `simpler' vector operations (concatenation and element-wise-addition/multiplication) on VQA benchmarks. Successive BLP techniques have yielded higher performance with lower computational expense and are often implemented alongside attention mechanisms. However, despite significant prog…
Multi-instance learning (MIL) is a form of weakly supervised learning where a single class label is assigned to a bag of instances while the instance-level labels are not available. Training classifiers to accurately determine the bag label and instance labels is a challenging but critical task in many practical scenarios, such as computational histopathology. Recently, MIL models fully parameterized by neural networks have become popular due to the high flexibility and superior performance. Most of these models rely on attention mechanisms that assign attention scores across the instance embe…
Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）；University of Chinese Academy of Sciences (UCAS)（中国科学院大学）
From the frame/clip-level feature learning to the video-level representation building, deep learning methods in action recognition have developed rapidly in recent years. However, current methods suffer from the confusion caused by partial observation training, or without end-to-end learning, or restricted to single temporal scale modeling and so on. In this paper, we build upon two-stream ConvNets and propose Deep networks with Temporal Pyramid Pooling (DTPP), an end-to-end video-level representation learning approach, to address these problems. Specifically, at first, RGB images and optical …
Despite the growing discriminative capabilities of modern deep learning methods for recognition tasks, the inner workings of the state-of-art models still remain mostly black-boxes. In this paper, we propose a systematic interpretation of model parameters and hidden representations of Residual Temporal Convolutional Networks (Res-TCN) for action recognition in time-series data. We also propose a Feature Map Decoder as part of the interpretation analysis, which outputs a representation of model's hidden variables in the same domain as the input. Such analysis empowers us to expose model's chara…
The University of Queensland（昆士兰大学）；The University of New South Wales（新南威尔士大学）
Fine-grained visual recognition typically depends on modeling subtle difference from object parts. However, these parts often exhibit dramatic visual variations such as occlusions, viewpoints, and spatial transformations, making it hard to detect. In this paper, we present a novel attention-based model to automatically, selectively and accurately focus on critical object regions with higher importance against appearance variations. Given an image, two different Convolutional Neural Networks (CNNs) are constructed, where the outputs of two CNNs are correlated through bilinear pooling to simulta…
TMFNet: Two-Stream Multi-Channels Fusion Networks for Color Image Operation Chain Detection
Henan University（河南大学）；Henan Key Laboratory of Big Data Analysis and Processing（河南省大数据分析与处理重点实验室）；School of Computer and Information Engineering（计算机与信息工程学院）
All Eyes on the Workflow: Automated and Efficient Event Discovery from Video Streams
Chair of Process and Data Science, RWTH Aachen University（过程与数据科学教授席位，亚琛工业大学）；Artificial Intelligence & Machine Learning Lab, Technical University of Darmstadt（人工智能与机器学习实验室，达姆施塔特技术大学）
Jiangsu Ocean University（江苏海洋大学）；Xuzhou Medical University（徐州医科大学）
It is well known that hyperspectral images (HSI) contain rich spatial-spectral contextual information, and how to effectively combine both spectral and spatial information using DNN for HSI classification has become a new research hotspot. Compared with CNN with square kernels, GCN have exhibited exciting potential to model spatial contextual structure and conduct flexible convolution on arbitrarily irregular image regions. However, current GCN only using first-order spectral-spatial signatures can result in boundary blurring and isolated misclassification. To address these, we first designed …
Peter Munk Cardiac Center（彼得·芒克心脏中心）；University of Toronto（多伦多大学）；Vector Institute（向量研究所）；University of Waterloo（滑铁卢大学）
Medical image segmentation is a difficult but important task for many clinical operations such as cardiac bi-ventricular volume estimation. More recently, there has been a shift to utilizing deep learning and fully convolutional neural networks (CNNs) to perform image segmentation that has yielded state-of-the-art results in many public benchmark datasets. Despite the progress of deep learning in medical image segmentation, standard CNNs are still not fully adopted in clinical settings as they lack robustness and interpretability. Shapes are generally more meaningful features than solely textu…
Attention-Guided Dual-Stream Learning for Group Engagement Recognition: Fusing Transformer-Encoded Motion Dynamics with Scene Context via Adaptive Gating
We proposed a deep learning method for interpretable diabetic retinopathy (DR) detection. The visual-interpretable feature of the proposed method is achieved by adding the regression activation map (RAM) after the global averaging pooling layer of the convolutional networks (CNN). With RAM, the proposed model can localize the discriminative regions of an retina image to show the specific region of interest in terms of its severity level. We believe this advantage of the proposed deep learning model is highly desired for DR detection because in practice, users are not only interested with high …
University of Queensland（昆士兰大学）；Australian e-Health Research Centre, CSIRO（澳大利亚联邦科学与工业研究组织澳大利亚电子健康研究中心）
Data scarcity is common in deep learning models for medical image segmentation. Previous works proposed multi-dataset learning, either simultaneously or via transfer learning to expand training sets. However, medical image datasets have diverse-sized images and features, and developing a model simultaneously for multiple datasets is challenging. This work proposes Fabric Image Representation Encoding Network (FIRENet), a universal architecture for simultaneous multi-dataset segmentation and transfer learning involving arbitrary numbers of dataset(s). To handle different-sized image and feature…
