This paper designs a high-performance deep convolutional network (DeepID2+) for face recognition. It is learned with the identification-verification supervisory signal. By increasing the dimension of hidden representations and adding supervision to early convolutional layers, DeepID2+ achieves new state-of-the-art on LFW and YouTube Faces benchmarks. Through empirical studies, we have discovered three properties of its deep neural activations critical for the high performance: sparsity, selectiveness and robustness. (1) It is observed that neural activations are moderately sparse. Moderate sparsity maximizes the discriminative power of the deep net as well as the distance between images. It is surprising that DeepID2+ still can achieve high recognition accuracy even after the neural responses are binarized. (2) Its neurons in higher layers are highly selective to identities and identity-related attributes. We can identify different subsets of neurons which are either constantly excited or inhibited when different identities or attributes are present. Although DeepID2+ is not taught to distinguish attributes during training, it has implicitly learned such high-level concepts. (3) It is much more robust to occlusions, although occlusion patterns are not included in the training set.
Online multi-object tracking is a fundamental problem in time-critical video analysis applications. A major challenge in the popular tracking-by-detection framework is how to associate unreliable detection results with existing tracks. In this paper, we propose to handle unreliable detection by collecting candidates from outputs of both detection and tracking. The intuition behind generating redundant candidates is that detection and tracks can complement each other in different scenarios. Detection results of high confidence prevent tracking drifts in the long term, and predictions of tracks …
In this paper, we address the problem of person re-identification, which refers to associating the persons captured from different cameras. We propose a simple yet effective human part-aligned representation for handling the body part misalignment problem. Our approach decomposes the human body into regions (parts) which are discriminative for person matching, accordingly computes the representations over the regions, and aggregates the similarities computed between the corresponding regions of a pair of probe and gallery images as the overall matching score. Our formulation, inspired by atten…
Labeling medical images depends on professional knowledge, making it difficult to acquire large amount of annotated medical images with high quality in a short time. Thus, making good use of limited labeled samples in a small dataset to build a high-performance model is the key to medical image classification problem. In this paper, we propose a deeply supervised Layer Selective Attention Network (LSANet), which comprehensively uses label information in feature-level and prediction-level supervision. For feature-level supervision, in order to better fuse the low-level features and high-level f…
This work details Sighthounds fully automated license plate detection and recognition system. The core technology of the system is built using a sequence of deep Convolutional Neural Networks (CNNs) interlaced with accurate and efficient algorithms. The CNNs are trained and fine-tuned so that they are robust under different conditions (e.g. variations in pose, lighting, occlusion, etc.) and can work across a variety of license plate templates (e.g. sizes, backgrounds, fonts, etc). For quantitative analysis, we show that our system outperforms the leading license plate detection and recognition…
Yonsei University（延世大学）；Chungnam National University（忠南国立大学）
Regularization-based image restoration has remained an active research topic in computer vision and image processing. It often leverages a guidance signal captured in different fields as an additional cue. In this work, we present a general framework for image restoration, called deeply aggregated alternating minimization (DeepAM). We propose to train deep neural network to advance two of the steps in the conventional AM algorithm: proximal mapping and ?- continuation. Both steps are learned from a large dataset in an end-to-end manner. The proposed framework enables the convolutional neural n…
University of Adelaide（阿德莱德大学）；ARC Centre of Excellence for Robotic Vision（澳大利亚研究理事会机器人视觉卓越中心）
Visual SLAM (Simultaneous Localization and Mapping) methods typically rely on handcrafted visual features or raw RGB values for establishing correspondences between images. These features, while suitable for sparse mapping, often lead to ambiguous matches in texture-less regions when performing dense reconstruction due to the aperture problem. In this work, we explore the use of learned features for the matching task in dense monocular reconstruction. We propose a novel convolutional neural network (CNN) architecture along with a deeply supervised feature learning scheme for pixel-wise regress…
University of Cambridge（剑桥大学）；Technion - Israel Institute of Technology（以色列理工学院）
Non-linear spectral decompositions of images based on one-homogeneous functionals such as total variation have gained considerable attention in the last few years. Due to their ability to extract spectral components corresponding to objects of different size and contrast, such decompositions enable filtering, feature transfer, image fusion and other applications. However, obtaining this decomposition involves solving multiple non-smooth optimisation problems and is therefore computationally highly intensive. In this paper, we present a neural network approximation of a non-linear spectral deco…
Deeply Learned Robust Matrix Completion for Large-scale Low-rank Data Recovery
School of Data, Mathematical, and Statistical Sciences and the Department of Computer Science, University of Central Florida（数据、数学与统计科学学院和计算机科学系，中央佛罗里达大学）；School of Data, Mathematical, and Statistical Sciences, University of Central Florida（数据、数学与统计科学学院，中央佛罗里达大学）；Damo Academy, Alibaba US（阿里云美国研究院）
Beihang University（北京航空航天大学）；Hangzhou Innovation Institute of Beihang University（北京航空航天大学杭州创新研究院）；Zhengzhou University（郑州大学）；University of Texas at Dallas（德克萨斯大学达拉斯分校）
Convolutional neural networks (CNNs) have achieved remarkable success in image recognition. Although the internal patterns of the input images are effectively learned by the CNNs, these patterns only constitute a small proportion of useful patterns contained in the input images. This can be attributed to the fact that the CNNs will stop learning if the learned patterns are enough to make a correct classification. Network regularization methods like dropout and SpatialDropout can ease this problem. During training, they randomly drop the features. These dropout methods, in essence, change the p…
MambaVC: Learned Visual Compression with Selective State Spaces
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Peng Cheng Laboratory（鹏城实验室）；Huawei Technologies Company Ltd.（华为技术有限公司）；Shenzhen University（深圳大学）
Recent self-supervised video representation learning methods focus on maximizing the similarity between multiple augmented views from the same video and largely rely on the quality of generated views. However, most existing methods lack a mechanism to prevent representation learning from bias towards static information in the video. In this paper, we propose frequency augmentation (FreqAug), a spatio-temporal data augmentation method in the frequency domain for video representation learning. FreqAug stochastically removes specific frequency components from the video so that learned representat…
Incheon National University（仁川大学）；Dain Technology, Inc.
Modern convolutional neural networks (CNNs) have massive identical convolution blocks, and, hence, recursive sharing of parameters across these blocks has been proposed to reduce the amount of parameters. However, naive sharing of parameters poses many challenges such as limited representational power and the vanishing/exploding gradients problem of recursively shared parameters. In this paper, we present a recursive convolution block design and training method, in which a recursively shareable part, or a filter basis, is separated and learned while effectively avoiding the vanishing/exploding…
Feature disentanglement of the foreground target objects and the background surrounding context has not been yet fully accomplished. The lack of network interpretability prevents advancing for feature disentanglement and better generalization robustness. We study the role of the context on interfering with a disentangled foreground target object representation in this work. We hypothesize that the representation of the surrounding context is heavily tied with the foreground object due to the dense hierarchical parametrization of convolutional networks with under-constrained learning algorithms…
Recent advance of large scale similarity search involves using deeply learned representations to improve the search accuracy and use vector quantization methods to increase the search speed. However, how to learn deep representations that strongly preserve similarities between data pairs and can be accurately quantized via vector quantization remains a challenging task. Existing methods simply leverage quantization loss and similarity loss, which result in unexpectedly biased back-propagating gradients and affect the search performances. To this end, we propose a novel gradient snapping layer …
The University of Trento（特伦托大学）；The University of Sydney（悉尼大学）；INRIA（法国国家信息与自动化研究所）；University of Perugia（佩鲁贾大学）；The Chinese University of Hong Kong（香港中文大学）
Recent works have shown that exploiting multi-scale representations deeply learned via convolutional neural networks (CNN) is of tremendous importance for accurate contour detection. This paper presents a novel approach for predicting contours which advances the state of the art in two fundamental aspects, i.e. multi-scale feature generation and fusion. Different from previous works directly consider- ing multi-scale feature maps obtained from the inner layers of a primary CNN architecture, we introduce a hierarchical deep model which produces more rich and complementary representations. Furth…
Mila（米拉研究所）；Université de Montréal（蒙特利尔大学）；University of Amsterdam（阿姆斯特丹大学）；Microsoft Research（微软研究院）
In this work we study locality and compositionality in the context of learning representations for Zero Shot Learning (ZSL). In order to well-isolate the importance of these properties in learned representations, we impose the additional constraint that, differently from most recent work in ZSL, no pre-training on different datasets (e.g. ImageNet) is performed. The results of our experiments show how locality, in terms of small parts of the input, and compositionality, i.e. how well can the learned representations be expressed as a function of a smaller vocabulary, are both deeply related to …
Mila - Québec AI Institute（米拉-魁北克人工智能研究所）；ByteDance（字节跳动）；Shanghai Jiao Tong University（上海交通大学）；University of Montréal（蒙特利尔大学）
Hierarchical semantic structures naturally exist in an image dataset, in which several semantically relevant image clusters can be further integrated into a larger cluster with coarser-grained semantics. Capturing such structures with image representations can greatly benefit the semantic understanding on various downstream tasks. Existing contrastive representation learning methods lack such an important model capability. In addition, the negative pairs used in these methods are not guaranteed to be semantically distinct, which could further hamper the structural correctness of learned image …
University of Wollongong（卧龙岗大学）；Motovis Inc（魔视智能科技有限公司）；Chinese Academy of Sciences（中国科学院）；National University of Defense Technology（国防科技大学）
A novel deep neural network training paradigm that exploits the conjoint information in multiple heterogeneous sources is proposed. Specifically, in a RGB-D based action recognition task, it cooperatively trains a single convolutional neural network (named c-ConvNet) on both RGB visual features and depth features, and deeply aggregates the two kinds of features for action recognition. Differently from the conventional ConvNet that learns the deep separable features for homogeneous modality-based classification with only one softmax loss function, the c-ConvNet enhances the discriminative power…
University of Oxford（牛津大学）；Oxford Robotics Institute（牛津大学机器人研究所）
In this work, we train a network to simultaneously perform segmentation and pixel-wise Out-of-Distribution (OoD) detection, such that the segmentation of unknown regions of scenes can be rejected. This is made possible by leveraging an OoD dataset with a novel contrastive objective and data augmentation scheme. By combining data including unknown classes in the training data, a more robust feature representation can be learned with known classes represented distinctly from those unknown. When presented with unknown classes or conditions, many current approaches for segmentation frequently exhi…
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；The University of Sydney（悉尼大学）
Deep networks have strong capacities of embedding data into latent representations and finishing following tasks. However, the capacities largely come from high-quality annotated labels, which are expensive to collect. Noisy labels are more affordable, but result in corrupted representations, leading to poor generalization performance. To learn robust representations and handle noisy labels, we propose selective-supervised contrastive learning (Sel-CL) in this paper. Specifically, Sel-CL extend supervised contrastive learning (Sup-CL), which is powerful in representation learning, but is degra…
Revolutionizing Disease Diagnosis with simultaneous functional PET/MR and Deeply Integrated Brain Metabolic, Hemodynamic, and Perfusion Networks
School of Biomedical Engineering, ShanghaiTech University（上海科技大学生物医学工程学院）；Zhongshan Hospital（中山医院）；State Key Laboratory of Advanced Medical Materials and Devices, ShanghaiTech University（上海科技大学先进医用材料与器件国家重点实验室）；Shanghai Clinical Research and Trial Center（上海临床研究与试验中心）
We propose a simple and efficient algorithm for learning sparse invariant representations from unlabeled data with fast inference. When trained on short movies sequences, the learned features are selective to a range of orientations and spatial frequencies, but robust to a wide range of positions, similar to complex cells in the primary visual cortex. We give a hierarchical version of the algorithm, and give guarantees of fast convergence under certain conditions.
Superpixels serve as a powerful preprocessing tool in numerous computer vision tasks. By using superpixel representation, the number of image primitives can be largely reduced by orders of magnitudes. With the rise of deep learning in recent years, a few works have attempted to feed deeply learned features / graphs into existing classical superpixel techniques. However, none of them are able to produce superpixels in near real-time, which is crucial to the applicability of superpixels in practice. In this work, we propose a two-stage graph-based framework for superpixel segmentation. In the fi…
Drexel University（德雷塞尔大学）；University of Delaware（特拉华大学）
Artificial neural networks (ANNs), specifically deep learning networks, have often been labeled as black boxes due to the fact that the internal representation of the data is not easily interpretable. In our work, we illustrate that an ANN, trained using sparse coding under specific sparsity constraints, yields a more interpretable model than the standard deep learning model. The dictionary learned by sparse coding can be more easily understood and the activations of these elements creates a selective feature output. We compare and contrast our sparse coding model with an equivalent feed forwa…
