It is widely known that very small datasets produce overfitting in Deep Neural Networks (DNNs), i.e., the network becomes highly biased to the data it has been trained on. This issue is often alleviated using transfer learning, regularization techniques and/or data augmentation. This work presents a new approach, independent but complementary to the previous mentioned techniques, for improving the generalization of DNNs on very small datasets in which the involved classes share many visual features. The proposed methodology, called FuCiTNet (Fusion Class inherent Transformations Network), inspired by GANs, creates as many generators as classes in the problem. Each generator, $k$, learns the transformations that bring the input image into the k-class domain. We introduce a classification loss in the generators to drive the leaning of specific k-class transformations. Our experiments demonstrate that the proposed transformations improve the generalization of the classification model in three diverse datasets.
Beijing University of Posts and Telecommunications（北京邮电大学）；Midea Group（美的集团）
The raw depth image captured by the indoor depth sensor usually has an extensive range of missing depth values due to inherent limitations such as the inability to perceive transparent objects and limited distance range. The incomplete depth map burdens many downstream vision tasks, and a rising number of depth completion methods have been proposed to alleviate this issue. While most existing methods can generate accurate dense depth maps from sparse and uniformly sampled depth maps, they are not suitable for complementing the large contiguous regions of missing depth values, which is common a…
A Survey of Deep Learning Based Radar and Vision Fusion for 3D Object Detection in Autonomous Driving
School of Automation, Northwestern Polytechnical University（西北工业大学自动化学院）；School of Electronic and Information Engineering, Suzhou University of Science and Technology（苏州科技大学电子与信息工程学院）
In this work, we seek to exploit the deep structure of multi-modal data to robustly exploit the group subspace distribution of the information using the Convolutional Neural Network (CNN) formalism. Upon unfolding the set of subspaces constituting each data modality, and learning their corresponding encoders, an optimized integration of the generated inherent information is carried out to yield a characterization of various classes. Referred to as deep Multimodal Robust Group Subspace Clustering (DRoGSuRe), this approach is compared against the independently developed state-of-the-art approach…
Liquid Fusion of Heterogeneous Representations Towards General Salient Object Detection
School of Computer Science and Artificial Intelligence, Changzhou University（常州大学计算机科学与人工智能学院）；College of Computer Science and Artificial Intelligence, Fudan University（复旦大学计算机科学与人工智能学院）；Faculty of Data Science, City University of Macau（澳门城市大学数据科学学院）
Little Strokes Fell Great Oaks: Boosting the Hierarchical Features for Multi-exposure Image Fusion
College of Computer Science and Technology, Zhejiang University of Technology（浙江工业大学计算机科学与技术学院）；School of Mechanical Engineering, Dalian University of Technology（大连理工大学机械工程学院）
Aiming at the problems that the convolutional neural networks neglect to capture the inherent attributes of natural images and extract features only in a single scale in the field of image super-resolution reconstruction, a network structure based on attention mechanism and multi-scale feature fusion is proposed. By using the attention mechanism, the network can effectively integrate the non-local information and second-order features of the image, so as to improve the feature expression ability of the network. At the same time, the convolution kernel of different scales is used to extract the…
Although deep learning has yielded impressive performance for face recognition, many studies have shown that different networks learn different feature maps: while some networks are more receptive to pose and illumination others appear to capture more local information. Thus, in this work, we propose a deep heterogeneous feature fusion network to exploit the complementary information present in features generated by different deep convolutional neural networks (DCNNs) for template-based face recognition, where a template refers to a set of still face images or video frames from different sourc…
University of Sherbrooke（舍布鲁克大学）；University of Mons（蒙斯大学）
Event classification is inherently sequential and multimodal. Therefore, deep neural models need to dynamically focus on the most relevant time window and/or modality of a video. In this study, we propose the Multi-level Attention Fusion network (MAFnet), an architecture that can dynamically fuse visual and audio information for event recognition. Inspired by prior studies in neuroscience, we couple both modalities at different levels of visual and audio paths. Furthermore, the network dynamically highlights a modality at a given time window relevant to classify events. Experimental results in…
Multi-modal Fusion and Query Refinement Network for Video Moment Retrieval and Highlight Detection
School of Electronic Science and Engineering, Nanjing University（南京大学电子科学与工程学院）；School of Physics and Electronics, Hubei Normal University（湖北师范大学物理与电子科学学院）；Gosuncn Chuanglian Technology Co., Ltd.（高新兴创联科技有限公司）
In recent years, most of the accuracy gains for video action recognition have come from the newly designed CNN architectures (e.g., 3D-CNNs). These models are trained by applying a deep CNN on single clip of fixed temporal length. Since each video segment are processed by the 3D-CNN module separately, the corresponding clip descriptor is local and the inter-clip relationships are inherently implicit. Common method that directly averages the clip-level outputs as a video-level prediction is prone to fail due to the lack of mechanism that can extract and integrate relevant information to represe…
Can Optical Denoising Clean Sonar Images? A Benchmark and Fusion Approach
Hangzhou Institute of Technology, Xidian University（杭州理工大学）；Department of Engineering, Shenzhen MSU-BIT University（深圳MSU-BIT大学工程系）；School of Information Engineering, Jiangxi University of Science（江西理工大学信息工程学院）；Institute of Deep-sea Science（深海科学研究院）；School of Computer Science, Northwestern Polytechnical University（西北工业大学计算机学院）；College of Cyber Security, Jinan University（广州大学网络安全学院）
Multimodal Fusion for Sim2real Transfer in Visual Reinforcement Learning
Medical Artificial Intelligence Lab, The First Hospital of Hebei Medical University, Hebei Medical University（医学人工智能实验室，河北医科大学第一医院，河北医科大学）；State Key Laboratory of Robotics and Systems, Harbin Institute of Technology（机器人系统国家重点实验室，哈尔滨工业大学）
Fusion and Grouping Strategies in Deep Learning for Local Climate Zone Classification of Multimodal Remote Sensing Data
Graphics-Visualization-Computing Lab, International Institute of Information Technology Bangalore, Karnataka 560100, India（图形可视化计算实验室，国际信息学院班加罗尔，卡纳塔克邦560100，印度）
Emotion Recognition in Conversations (ERC) is crucial in developing sympathetic human-machine interaction. In conversational videos, emotion can be present in multiple modalities, i.e., audio, video, and transcript. However, due to the inherent characteristics of these modalities, multi-modal ERC has always been considered a challenging undertaking. Existing ERC research focuses mainly on using text information in a discussion, ignoring the other two modalities. We anticipate that emotion recognition accuracy can be improved by employing a multi-modal approach. Thus, in this study, we propose …
