Machine-learning algorithms have shown outstanding image recognition or classification performance for computer vision applications. However, the compute and energy requirement for implementing such classifier models for large-scale problems is quite high. In this paper, we propose Feature Driven Selective Classification (FALCON) inspired by the biological visual attention mechanism in the brain to optimize the energy-efficiency of machine-learning classifiers. We use the consensus in the characteristic features (color/texture) across images in a dataset to decompose the original classification problem and construct a tree of classifiers (nodes) with a generic-to-specific transition in the classification hierarchy. The initial nodes of the tree separate the instances based on feature information and selectively enable the latter nodes to perform object specific classification. The proposed methodology allows selective activation of only those branches and nodes of the classification tree that are relevant to the input while keeping the remaining nodes idle. Additionally, we propose a programmable and scalable Neuromorphic Engine (NeuE) that utilizes arrays of specialized neural computational elements to execute the FALCON based classifier models for diverse datasets. The structure of FALCON facilitates the reuse of nodes while scaling up from small classification problems to larger ones thus allowing us to construct classifier implementations that are significantly more efficient. We evaluate our approach for a 12-object classification task on the Caltech101 dataset and 10-object task on CIFAR-10 dataset by constructing FALCON models on the NeuE platform in 45nm technology. Our results demonstrate significant improvement in energy-efficiency and training time for minimal loss in output quality.
The difficulty of image recognition has gradually increased from general category recognition to fine-grained recognition and to the recognition of some subtle attributes such as temperature and geolocation. In this paper, we try to focus on the classification between sunrise and sunset and hope to give a hint about how to tell the difference in subtle attributes. Sunrise vs. sunset is a difficult recognition task, which is challenging even for humans. Towards understanding this new problem, we first collect a new dataset made up of over one hundred webcams from different places. Since existin…
School of Geosciences and Info Physics, Central South University（中南大学地球科学与信息物理学院）
Human vision possesses strong invariance in image recognition. The cognitive capability of deep convolutional neural network (DCNN) is close to the human visual level because of hierarchical coding directly from raw image. Owing to its superiority in feature representation, DCNN has exhibited remarkable performance in scene recognition of high-resolution remote sensing (HRRS) images and classification of hyper-spectral remote sensing images. In-depth investigation is still essential for understanding why DCNN can accurately identify diverse ground objects via its effective feature representati…
Multi-task learning is an effective learning strategy for deep-learning-based facial expression recognition tasks. However, most existing methods take into limited consideration the feature selection, when transferring information between different tasks, which may lead to task interference when training the multi-task networks. To address this problem, we propose a novel selective feature-sharing method, and establish a multi-task network for facial expression recognition and facial expression synthesis. The proposed method can effectively transfer beneficial features between different tasks,…
Human-object interaction recognition aims for identifying the relationship between a human subject and an object. Researchers incorporate global scene context into the early layers of deep Convolutional Neural Networks as a solution. They report a significant increase in the performance since generally interactions are correlated with the scene (\ie riding bicycle on the city street). However, this approach leads to the following problems. It increases the network size in the early layers, therefore not efficient. It leads to noisy filter responses when the scene is irrelevant, therefore not a…
Although dense local spatial-temporal features with bag-of-features representation achieve state-of-the-art performance for action recognition, the huge feature number and feature size prevent current methods from scaling up to real size problems. In this work, we investigate different types of feature sampling strategies for action recognition, namely dense sampling, uniformly random sampling and selective sampling. We propose two effective selective sampling methods using object proposal techniques. Experiments conducted on a large video dataset show that we are able to achieve better averag…
Most action recognition solutions rely on dense sampling to precisely cover the informative temporal clip. Extensively searching temporal region is expensive for a real-world application. In this work, we focus on improving the inference efficiency of current action recognition backbones on trimmed videos, and illustrate that one action model can also cover then informative region by dropping non-informative features. We present Selective Feature Compression (SFC), an action recognition inference strategy that greatly increase model inference efficiency without any accuracy compromise. Differe…
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Beihang University（北京航空航天大学）
Typically, the deployment of face recognition models in the wild needs to identify low-resolution faces with extremely low computational cost. To address this problem, a feasible solution is compressing a complex face model to achieve higher speed and lower memory at the cost of minimal performance drop. Inspired by that, this paper proposes a learning approach to recognize low-resolution faces via selective knowledge distillation. In this approach, a two-stream convolutional neural network (CNN) is first initialized to recognize high-resolution faces and resolution-degraded faces with a teach…
Privacy-Preserving Federated Action Recognition via Differentially Private Selective Tuning and Efficient Communication
School of Computing Science, University of Glasgow（格拉斯哥大学计算科学学院）；Infocomm Technology Cluster, Singapore Institute of Technology（新加坡理工学院信息通信技术集群）；The Edward S. Rogers Sr. Dept. of Electrical and Computer Engineering, University of Toronto（多伦多大学埃德华·S·罗杰斯Sr.电子与计算机工程系）
Facial Expression Recognition (FER) in the wild is extremely challenging due to occlusions, variant head poses, face deformation and motion blur under unconstrained conditions. Although substantial progresses have been made in automatic FER in the past few decades, previous studies were mainly designed for lab-controlled FER. Real-world occlusions, variant head poses and other issues definitely increase the difficulty of FER on account of these information-deficient regions and complex backgrounds. Different from previous pure CNNs based methods, we argue that it is feasible and practical to t…
RSC-GestureNet: Reliability-Aware Selective Causal Recognition of Chinese Traffic Police Gestures
Academy of Interdisciplinary Studies, The Hong Kong University of Science and Technology（香港科技大学跨学科研究学院）；Faculty of Innovation Engineering, Macau University of Science and Technology（澳门科技大学创新工程学院）
Convolutional neural networks have emerged as the leading method for the classification and segmentation of images. In some cases, it is desirable to focus the attention of the net on a specific region in the image; one such case is the recognition of the contents of transparent vessels, where the vessel region in the image is already known. This work presents a valve filter approach for focusing the attention of the net on a region of interest (ROI). In this approach, the ROI is inserted into the net as a binary map. The net uses a different set of convolution filters for the ROI and backgrou…
Scene Text Recognition (STR), the task of recognizing text against complex image backgrounds, is an active area of research. Current state-of-the-art (SOTA) methods still struggle to recognize text written in arbitrary shapes. In this paper, we introduce a novel architecture for STR, named Selective Context ATtentional Text Recognizer (SCATTER). SCATTER utilizes a stacked block architecture with intermediate supervision during training, that paves the way to successfully train a deep BiLSTM encoder, thus improving the encoding of contextual dependencies. Decoding is done using a two-step 1D at…
A human's attention can intuitively adapt to corrupted areas of an image by recalling a similar uncorrupted image they have previously seen. This observation motivates us to improve the attention of adversarial images by considering their clean counterparts. To accomplish this, we introduce Associative Adversarial Learning (AAL) into adversarial learning to guide a selective attack. We formulate the intrinsic relationship between attention and attack (perturbation) as a coupling optimization problem to improve their interaction. This leads to an attention backtracking algorithm that can effect…
PASS: Path-selective State Space Model for Event-based Recognition
AI Thrust, HKUST(GZ) International Digital Economy Academy（人工智能 thrust，香港科技大学（广州）国际数字经济学院）；School of Electrical and Electronic Engineering, Nanyang Technological University（南洋理工大学电子与电气工程学院）
The Chinese University of Hong Kong（香港中文大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
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 spa…
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…
Artificial Immune System of Secure Face Recognition Against Adversarial Attacks
School of Artificial Intelligence, Beijing Normal University（北京师范大学人工智能学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；China Academy of Railway Sciences（中国铁道科学研究院）
University of Melbourne（墨尔本大学）；Queensland University of Technology（昆士兰科技大学）
A key challenge in visual place recognition (VPR) is recognizing places despite drastic visual appearance changes due to factors such as time of day, season, weather or lighting conditions. Numerous approaches based on deep-learnt image descriptors, sequence matching, domain translation, and probabilistic localization have had success in addressing this challenge, but most rely on the availability of carefully curated representative reference images of the possible places. In this paper, we propose a novel approach, dubbed Bayesian Selective Fusion, for actively selecting and fusing informativ…
Baggage inspection systems using X-ray screening are crucial for security. Only 90% of threat objects are recognized from the X-ray system based in human inspection. Manual detection requires high concentration due to the images complexity and the challenges objects points of view. An algorithm based on Bag of Visual Word (BoVW) with Selective Search is proposed in this paper for handguns detection in single energy X-ray images from the public GDXray database. This approach is an adaptation of BoVW for X-ray baggage images context. In order to evaluate the proposed method the algorithm effecti…
Research and Academic Computer Network（研究与学术计算机网络）；Warsaw University of Technology（华沙理工大学）
With the recent shift towards mobile computing, new challenges for biometric authentication appear on the horizon. This paper provides a comprehensive study of cross-spectral iris recognition in a scenario, in which high quality color images obtained with a mobile phone are used against enrollment images collected in typical, near-infrared setups. Grayscale conversion of the color images that employs selective RGB channel choice depending on the iris coloration is shown to improve the recognition accuracy for some combinations of eye colors and matching software, when compared to using the red…
In this paper, we present an ultra lightweight system that can effectively recognize different circuit components in an image with very limited training data. Along with the system, we also release the data set we created for the task. A two-stage approach is employed by our system. Selective search was applied to find the location of each circuit component. Based on its result, we crop the original image into smaller pieces. The pieces are then fed to the Convolutional Neural Network (CNN) for classification to identify each circuit component. It is of engineering significance and works well …
Computer Vision Center（计算机视觉中心）；Media Integration and Communication Center (MICC)（媒体集成与通信中心 (MICC)）；Universita di Firenze（佛罗伦萨大学）
In this paper we propose an approach to lexicon-free recognition of text in scene images. Our approach relies on a LSTM-based soft visual attention model learned from convolutional features. A set of feature vectors are derived from an intermediate convolutional layer corresponding to different areas of the image. This permits encoding of spatial information into the image representation. In this way, the framework is able to learn how to selectively focus on different parts of the image. At every time step the recognizer emits one character using a weighted combination of the convolutional fe…
Supervised learning of convolutional neural networks (CNNs) can require very large amounts of labeled data. Labeling thousands or millions of training examples can be extremely time consuming and costly. One direction towards addressing this problem is to create features from unlabeled data. In this paper we propose a new method for training a CNN, with no need for labeled instances. This method for unsupervised feature learning is then successfully applied to a challenging object recognition task. The proposed algorithm is relatively simple, but attains accuracy comparable to that of more sop…
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…
Object recognition in the presence of background clutter and distractors is a central problem both in neuroscience and in machine learning. However, the performance level of the models that are inspired by cortical mechanisms, including deep networks such as convolutional neural networks and deep belief networks, is shown to significantly decrease in the presence of noise and background objects [19, 24]. Here we develop a computational framework that is hierarchical, relies heavily on key properties of the visual cortex including mid-level feature selectivity in visual area V4 and Inferotempor…
Tencent PCG（腾讯平台与内容事业群）；National University of Singapore（新加坡国立大学）；Tencent Video（腾讯视频）；Tsinghua University（清华大学）
The traditional model upgrading paradigm for retrieval requires recomputing all gallery embeddings before deploying the new model (dubbed as "backfilling"), which is quite expensive and time-consuming considering billions of instances in industrial applications. BCT presents the first step towards backward-compatible model upgrades to get rid of backfilling. It is workable but leaves the new model in a dilemma between new feature discriminativeness and new-to-old compatibility due to the undifferentiated compatibility constraints. In this work, we propose Darwinian Model Upgrades (DMU), which …
This article addresses the problem of two- and higher dimensional pattern matching, i.e. the identification of instances of a template within a larger signal space, which is a form of registration. Unlike traditional correlation, we aim at obtaining more selective matchings by considering more strict comparisons of gray-level intensity. In order to achieve fast matching, a nonlinear thresholded version of the fast Fourier transform is applied to a gray-level decomposition of the original 2D image. The potential of the method is substantiated with respect to real data involving the selective id…
Arizona State University（亚利桑那州立大学）；School of Electrical, Computer and Energy Engineering（电气、计算机与能源工程学院）
The human visual system employs a selective attention mechanism to understand the visual world in an eficient manner. In this paper, we show how computational models of this mechanism can be exploited for the computer vision application of scene recognition. First, we consider saliency weighting and saliency pruning, and provide a comparison of the performance of different attention models in these approaches in terms of classification accuracy. Pruning can achieve a high degree of computational savings without significantly sacrificing classification accuracy. In saliency weighting, however, …
FER-YOLO-Mamba: Facial Expression Detection and Classification Based on Selective State Space
School of Information Science and Technology, Southwest Jiaotong University（西南交通大学信息科学与技术学院）；School of Electrical and Information Engineering, University of the Witwatersrand（金山大学电气与信息工程学院）
Semi-Supervised Facial Expression Recognition based on Dynamic Threshold and Negative Learning
University of Science and Technology of China（中国科学技术大学）；Jianghuai Advance Technology Center（江淮前沿技术协同创新中心）；Unisound AI Technology Co., Ltd（云知声智能科技股份有限公司）
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…
Revealing the Two Sides of Data Augmentation: An Asymmetric Distillation-based Win-Win Solution for Open-Set Recognition
School of Artificial Intelligence, Jilin University（吉林大学人工智能学院）；Institute of Computing Technology, CAS（中国科学院计算技术研究所）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Institute of Automation, CAS（中国科学院自动化研究所）；DIDI（滴滴）
The Chinese University of Hong Kong（香港中文大学）；Shanghai AI Lab（上海人工智能实验室）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Amazon AI（亚马逊人工智能）
Deep learning models have achieved excellent recognition results on large-scale video benchmarks. However, they perform poorly when applied to videos with rare scenes or objects, primarily due to the bias of existing video datasets. We tackle this problem from two different angles: algorithm and dataset. From the perspective of algorithms, we propose Spatial-aware Multi-Aspect Debiasing (SMAD), which incorporates both explicit debiasing with multi-aspect adversarial training and implicit debiasing with the spatial actionness reweighting module, to learn a more generic representation invariant …
Faculty of Computer and Information Science, University of Ljubljana（卢布尔雅那大学计算机与信息科学学院）；Faculty of Electrical Engineering, University of Ljubljana（卢布尔雅那大学电气工程学院）
Identity recognition from ear images is an active field of research within the biometric community. The ability to capture ear images from a distance and in a covert manner makes ear recognition technology an appealing choice for surveillance and security applications as well as related application domains. In contrast to other biometric modalities, where large datasets captured in uncontrolled settings are readily available, datasets of ear images are still limited in size and mostly of laboratory-like quality. As a consequence, ear recognition technology has not benefited yet from advances i…
Hong Kong University of Science and Technology（香港科技大学）；The Chinese University of Hong Kong（香港中文大学）；Stanford University（斯坦福大学）
The Imagenet Large Scale Visual Recognition Challenge (ILSVRC) is the one of the most important big data challenges to date. We participated in the object detection track of ILSVRC 2014 and received the fourth place among the 38 teams. We introduce in our object detection system a number of novel techniques in localization and recognition. For localization, initial candidate proposals are generated using selective search, and a novel bounding boxes regression method is used for better object localization. For recognition, to represent a candidate proposal, we adopt three features, namely, RCNN…
Rotating object detection has wide applications in aerial photographs, remote sensing images, UAVs, etc. At present, most of the rotating object detection datasets focus on the field of remote sensing, and these images are usually shot in high-altitude scenes. However, image datasets captured at low-altitude areas also should be concerned, such as drone-based datasets. So we present a low-altitude dronebased dataset, named UAV-ROD, aiming to promote the research and development in rotating object detection and UAV applications. The UAV-ROD consists of 1577 images and 30,090 instances of car ca…
Southeast University（东南大学）；South China University of Technology（华南理工大学）；University of Oulu（奥卢大学）；Nanjing University of Science and Technology（南京理工大学）
Cross-database micro-expression recognition (CDMER) is one of recently emerging and interesting problem in micro-expression analysis. CDMER is more challenging than the conventional micro-expression recognition (MER), because the training and testing samples in CDMER come from different micro-expression databases, resulting in the inconsistency of the feature distributions between the training and testing sets. In this paper, we contribute to this topic from three aspects. First, we establish a CDMER experimental evaluation protocol aiming to allow the researchers to conveniently work on this …
Deep Convolutional Neural Networks (CNNs) have been repeatedly proven to perform well on image classification tasks. Object detection methods, however, are still in need of significant improvements. In this paper, we propose a new framework called Ventral-Dorsal Networks (VDNets) which is inspired by the structure of the human visual system. Roughly, the visual input signal is analyzed along two separate neural streams, one in the temporal lobe and the other in the parietal lobe. The coarse functional distinction between these streams is between object recognition -- the "what" of the signal -…
QUT Centre for Robotics（昆士兰科技大学机器人中心）；School of Electrical Engineering and Robotics, QUT（昆士兰科技大学电气工程与机器人学院）；Queensland University of Technology (QUT)（昆士兰科技大学）
Visual Place Recognition (VPR) is the task of matching current visual imagery from a camera to images stored in a reference map of the environment. While initial VPR systems used simple direct image methods or hand-crafted visual features, recent work has focused on learning more powerful visual features and further improving performance through either some form of sequential matcher / filter or a hierarchical matching process. In both cases the performance of the initial single-image based system is still far from perfect, putting significant pressure on the sequence matching or (in the case …
University of Waterloo（滑铁卢大学）；DarwinAI Corp.（达尔文人工智能公司）
While significant advances in deep learning has resulted in state-of-the-art performance across a large number of complex visual perception tasks, the widespread deployment of deep neural networks for TinyML applications involving on-device, low-power image recognition remains a big challenge given the complexity of deep neural networks. In this study, we introduce AttendNets, low-precision, highly compact deep neural networks tailored for on-device image recognition. More specifically, AttendNets possess deep self-attention architectures based on visual attention condensers, which extends on …
One of the key challenges in machine learning is to design a computationally efficient multi-class classifier while maintaining the output accuracy and performance. In this paper, we present a tree-based classifier: Attention Tree (ATree) for large-scale image classification that uses recursive Adaboost training to construct a visual attention hierarchy. The proposed attention model is inspired from the biological 'selective tuning mechanism for cortical visual processing'. We exploit the inherent feature similarity across images in datasets to identify the input variability and use recursive …
Clemson University（克莱姆森大学）；University of Colorado Colorado Springs（科罗拉多大学科罗拉多斯普林斯分校）
Facial expressions convey massive information and play a crucial role in emotional expression. Deep neural network (DNN) accompanied by deep metric learning (DML) techniques boost the discriminative ability of the model in facial expression recognition (FER) applications. DNN, equipped with only classification loss functions such as Cross-Entropy cannot compact intra-class feature variation or separate inter-class feature distance as well as when it gets fortified by a DML supporting loss item. The triplet center loss (TCL) function is applied on all dimensions of the sample's embedding in the…
