Multi-label zero-shot learning extends conventional single-label zero-shot learning to a more realistic scenario that aims at recognizing multiple unseen labels of classes for each input sample. Existing works usually exploit attention mechanism to generate the correlation among different labels. However, most of them are usually biased on several major classes while neglect most of the minor classes with the same importance in input samples, and may thus result in overly diffused attention maps that cannot sufficiently cover minor classes. We argue that disregarding the connection between major and minor classes, i.e., correspond to the global and local information, respectively, is the cause of the problem. In this paper, we propose a novel framework of unbiased multi-label zero-shot learning, by considering various class-specific regions to calibrate the training process of the classifier. Specifically, Pyramid Feature Attention (PFA) is proposed to build the correlation between global and local information of samples to balance the presence of each class. Meanwhile, for the generated semantic representations of input samples, we propose Semantic Attention (SA) to strengthen the element-wise correlation among these vectors, which can encourage the coordinated representation of them. Extensive experiments on the large-scale multi-label zero-shot benchmarks NUS-WIDE and Open-Image demonstrate that the proposed method surpasses other representative methods by significant margins.
Recent years have witnessed many exciting achievements for object detection using deep learning techniques. Despite achieving significant progresses, most existing detectors are designed to detect objects with relatively low-quality prediction of locations, i.e., often trained with the threshold of Intersection over Union (IoU) set to 0.5 by default, which can yield low-quality or even noisy detections. It remains an open challenge for how to devise and train a high-quality detector that can achieve more precise localization (i.e., IoU$>$0.5) without sacrificing the detection performance. In t…
Nanjing University of Science and Technology（南京理工大学）
Pixel-level semantic segmentation is a challenging task with a huge amount of computation, especially if the size of input is large. In the segmentation model, apart from the feature extraction, the extra decoder structure is often employed to recover spatial information. In this paper, we put forward a method for single-shot segmentation in a feature residual pyramid network (RPNet), which learns the main and residuals of segmentation by decomposing the label at different levels of residual blocks. Specifically speaking, we use the residual features to learn the edges and details, and the ide…
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）；Horizon Robotics, Inc（地平线机器人公司）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）
Recently, proposal-free instance segmentation has received increasing attention due to its concise and efficient pipeline. Generally, proposal-free methods generate instance-agnostic semantic segmentation labels and instance-aware features to group pixels into different object instances. However, previous methods mostly employ separate modules for these two sub-tasks and require multiple passes for inference. We argue that treating these two sub-tasks separately is suboptimal. In fact, employing multiple separate modules significantly reduces the potential for application. The mutual benefits …
Feature pyramids are widely exploited by both the state-of-the-art one-stage object detectors (e.g., DSSD, RetinaNet, RefineDet) and the two-stage object detectors (e.g., Mask R-CNN, DetNet) to alleviate the problem arising from scale variation across object instances. Although these object detectors with feature pyramids achieve encouraging results, they have some limitations due to that they only simply construct the feature pyramid according to the inherent multi-scale, pyramidal architecture of the backbones which are actually designed for object classification task. Newly, in this work, w…
Shanghai Jiao Tong University（上海交通大学）；École de technologie supérieure, Université du Québec（魁北克大学高等技术学院）；Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；INRIA（法国国家信息与自动化研究所）；CNRS（法国国家科学研究中心）；Grenoble INP（格勒诺布尔理工学院）
Small-object detection is a challenging problem. In the last few years, the convolution neural networks methods have been achieved considerable progress. However, the current detectors struggle with effective features extraction for small-scale objects. To address this challenge, we propose image pyramid single-shot detector (IPSSD). In IPSSD, single-shot detector is adopted combined with an image pyramid network to extract semantically strong features for generating candidate regions. The proposed network can enhance the small-scale features from a feature pyramid network. We evaluated the pe…
National Chiao Tung University（国立交通大学）；Academia Sinica（中央研究院）；United Arab Emirates University（阿拉伯联合酋长国大学）
State-of-the-art (SoTA) models have improved the accuracy of object detection with a large margin via a FP (feature pyramid). FP is a top-down aggregation to collect semantically strong features to improve scale invariance in both two-stage and one-stage detectors. However, this top-down pathway cannot preserve accurate object positions due to the shift-effect of pooling. Thus, the advantage of FP to improve detection accuracy will disappear when more layers are used. The original FP lacks a bottom-up pathway to offset the lost information from lower-layer feature maps. It performs well in lar…
Tianjin University（天津大学）；Inception Institute of Artificial Intelligence（起源人工智能研究院）
Due to the advantages of real-time detection and improved performance, single-shot detectors have gained great attention recently. To solve the complex scale variations, single-shot detectors make scale-aware predictions based on multiple pyramid layers. However, the features in the pyramid are not scale-aware enough, which limits the detection performance. Two common problems in single-shot detectors caused by object scale variations can be observed: (1) small objects are easily missed; (2) the salient part of a large object is sometimes detected as an object. With this observation, we propos…
Pyramid Self-Contrastive Learning for Single-shot Test-time Ultrasound Image Denoising
Department of Electrical and Computer Engineering, The University of Hong Kong（香港大学电子与计算机工程系）；Department of Biomedical Engineering, Duke University（达特茅斯大学生物医学工程系）
Noah’s Ark Lab, Huawei Technologies（华为技术有限公司诺亚方舟实验室）；University of Toronto（多伦多大学）
Recent advances in high refresh rate displays as well as the increased interest in high rate of slow motion and frame up-conversion fuel the demand for efficient and cost-effective multi-frame video interpolation solutions. To that regard, inserting multiple frames between consecutive video frames are of paramount importance for the consumer electronics industry. State-of-the-art methods are iterative solutions interpolating one frame at the time. They introduce temporal inconsistencies and clearly noticeable visual artifacts. Departing from the state-of-the-art, this work introduces a true mu…
University of Electronic Science and Technology of China（电子科技大学）；Southwestern University of Finance and Economics（西南财经大学）
Semantic segmentation, which aims to acquire a detailed understanding of images, is an essential issue in computer vision. However, in practical scenarios, new categories that are different from the categories in training usually appear. Since it is impractical to collect labeled data for all categories, how to conduct zero-shot learning in semantic segmentation establishes an important problem. Although the attribute embedding of categories can promote effective knowledge transfer across different categories, the prediction of segmentation network reveals obvious bias to seen categories. In t…
Geometry-Aware Cross-Height Channel Knowledge Map Prediction for UAV-Assisted Communications With Uncertainty-Guided 3D Sensing
National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China (UESTC)（电子科技大学无线通信国家重点实验室）；SDAIA-KFUPM Joint Research Centre of AI, King Fahd University of Petroleum and Minerals（沙特数据和人工智能局-法赫德国王石油矿产大学人工智能联合研究中心）；School of Science, Technology and Engineering, University of the Sunshine Coast（阳光海岸大学科学技术与工程学院）；Anhui Science and Technology University（安徽科技学院）；College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications（南京邮电大学通信与信息工程学院）
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Arizona State University（亚利桑那州立大学）；Alibaba Group（阿里巴巴集团）
Most existing Zero-Shot Learning (ZSL) methods have the strong bias problem, in which instances of unseen (target) classes tend to be categorized as one of the seen (source) classes. So they yield poor performance after being deployed in the generalized ZSL settings. In this paper, we propose a straightforward yet effective method named Quasi-Fully Supervised Learning (QFSL) to alleviate the bias problem. Our method follows the way of transductive learning, which assumes that both the labeled source images and unlabeled target images are available for training. In the semantic embedding space,…
Robust 3D Face Alignment with Multi-Path Neural Architecture Search
Institute of Deep Learning (IDL)（深度学习研究所（IDL））；Southeast University（东南大学）；Computer Vision Technology Institution（计算机视觉技术研究所）；Baidu（百度）；Baidu Research（百度研究院）
University of California, Santa Barbara（加州大学圣巴巴拉分校）；University of Maryland, College Park（马里兰大学帕克分校）
Recognizing instances at different scales simultaneously is a fundamental challenge in visual detection problems. While spatial multi-scale modeling has been well studied in object detection, how to effectively apply a multi-scale architecture to temporal models for activity detection is still under-explored. In this paper, we identify three unique challenges that need to be specifically handled for temporal activity detection compared to its spatial counterpart. To address all these issues, we propose Dynamic Temporal Pyramid Network (DTPN), a new activity detection framework with a multi-sca…
Huazhong University of Science and Technology（华中科技大学）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）
Currently, one-stage frameworks have been widely applied for temporal action detection, but they still suffer from the challenge that the action instances span a wide range of time. The reason is that these one-stage detectors, e.g., Single Shot Multi-Box Detector (SSD), extract temporal features only applying a single-level layer for each head, which is not discriminative enough to perform classification and regression. In this paper, we propose a Multi-Level Temporal Pyramid Network (MLTPN) to improve the discrimination of the features. Specially, we first fuse the features from multiple lay…
Pohang University of Science and Technology (POSTECH)（浦项科技大学）
Few-shot semantic segmentation aims at learning to segment a target object from a query image using only a few annotated support images of the target class. This challenging task requires to understand diverse levels of visual cues and analyze fine-grained correspondence relations between the query and the support images. To address the problem, we propose Hypercorrelation Squeeze Networks (HSNet) that leverages multi-level feature correlation and efficient 4D convolutions. It extracts diverse features from different levels of intermediate convolutional layers and constructs a collection of 4D…
Few-shot object detection (FSOD) helps detectors adapt to unseen classes with few training instances, and is useful when manual annotation is time-consuming or data acquisition is limited. Unlike previous attempts that exploit few-shot classification techniques to facilitate FSOD, this work highlights the necessity of handling the problem of scale variations, which is challenging due to the unique sample distribution. To this end, we propose a Multi-scale Positive Sample Refinement (MPSR) approach to enrich object scales in FSOD. It generates multi-scale positive samples as object pyramids and…
One-stage object detectors such as SSD or YOLO already have shown promising accuracy with small memory footprint and fast speed. However, it is widely recognized that one-stage detectors have difficulty in detecting small objects while they are competitive with two-stage methods on large objects. In this paper, we investigate how to alleviate this problem starting from the SSD framework. Due to their pyramidal design, the lower layer that is responsible for small objects lacks strong semantics(e.g contextual information). We address this problem by introducing a feature combining module that s…
Carnegie Mellon University（卡内基梅隆大学）；Microsoft Research Asia（微软亚洲研究院）
One-shot object detection aims at detecting novel objects according to merely one given instance. With extreme data scarcity, current approaches explore various feature fusions to obtain directly transferable meta-knowledge. Yet, their performances are often unsatisfactory. In this paper, we attribute this to inappropriate correlation methods that misalign query-support semantics by overlooking spatial structures and scale variances. Upon analysis, we leverage the attention mechanism and propose a simple but effective architecture named Semantic-aligned Fusion Transformer (SaFT) to resolve the…
Hanyang University（汉阳大学）；Korea Advanced Institute of Science and Technology（韩国科学技术院）
Convolutional neural network (CNN) has led to significant progress in object detection. In order to detect the objects in various sizes, the object detectors often exploit the hierarchy of the multi-scale feature maps called feature pyramid, which is readily obtained by the CNN architecture. However, the performance of these object detectors is limited since the bottom-level feature maps, which experience fewer convolutional layers, lack the semantic information needed to capture the characteristics of the small objects. In order to address such problem, various methods have been proposed to i…
CSIRO-Data61（澳大利亚联邦科学与工业研究组织-Data61）；Australian National University（澳大利亚国立大学）
Advances in the design of multi-spectral cameras have led to great interests in a wide range of applications, from astronomy to autonomous driving. However, such cameras inherently suffer from a trade-off between the spatial and spectral resolution. In this paper, we propose to address this limitation by introducing a novel method to carry out super-resolution on raw mosaic images, multi-spectral or RGB Bayer, captured by modern real-time single-shot mosaic sensors. To this end, we design a deep super-resolution architecture that benefits from a sequential feature pyramid along the depth of th…
Pontifical Catholic University of Rio de Janeiro（里约热内卢天主教大学）；Leopoldo Américo Miguez de Mello Research and Development Center (Cenpes), Petrobras（巴西石油公司莱奥波尔多·亚美利哥·米格斯·德梅洛研发中心（Cenpes））
Deep learning-based models, such as convolutional neural networks, have advanced various segments of computer vision. However, this technology is rarely applied to seismic shot gather noise localization problem. This letter presents an investigation on the effectiveness of a multi-scale feature-fusion-based network for seismic shot-gather noise localization. Herein, we describe the following: (1) the construction of a real-world dataset of seismic noise localization based on 6,500 seismograms; (2) a multi-scale feature-fusion-based detector that uses the MobileNet combined with the Feature Pyr…
University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Florida State University（佛罗里达州立大学）
Generalized compositional zero-shot learning means to learn composed concepts of attribute-object pairs in a zero-shot fashion, where a model is trained on a set of seen concepts and tested on a combined set of seen and unseen concepts. This task is very challenging because of not only the gap between seen and unseen concepts but also the contextual dependency between attributes and objects. This paper introduces a new approach, termed translational concept embedding, to solve these two difficulties in a unified framework. It models the effect of applying an attribute to an object as adding a …
Attention-Enhanced Prototypical Learning for Few-Shot Infrastructure Defect Segmentation
Canizaro Livingston Gulf States Center for Environmental Informatics, the University of New Orleans（Canizaro Livingston Gulf States Center for Environmental Informatics，新奥尔良大学）；Graz University of Technology（格拉茨技术大学）；US Army Corps of Engineers, Engineer Research and Development Center（美国陆军工程兵团，工程研究与发展中心）
Tsinghua University（清华大学）；Tencent YouTu Lab（腾讯优图实验室）；University College London（伦敦大学学院）
Few-shot semantic segmentation aims to segment novel-class objects in a given query image with only a few labeled support images. Most advanced solutions exploit a metric learning framework that performs segmentation through matching each query feature to a learned class-specific prototype. However, this framework suffers from biased classification due to incomplete feature comparisons. To address this issue, we present an adaptive prototype representation by introducing class-specific and class-agnostic prototypes and thus construct complete sample pairs for learning semantic alignment with q…
Seoul National University（首尔大学）；Seoul National University Hospital（首尔大学医院）；Seoul National University College of Medicine（首尔大学医学院）；Institute of Radiation Medicine, Seoul National University Medical Research Center（首尔大学医学研究中心放射医学研究所）
We present a focal liver lesion detection model leveraged by custom-designed multi-phase computed tomography (CT) volumes, which reflects real-world clinical lesion detection practice using a Single Shot MultiBox Detector (SSD). We show that grouped convolutions effectively harness richer information of the multi-phase data for the object detection model, while a naive application of SSD suffers from a generalization gap. We trained and evaluated the modified SSD model and recently proposed variants with our CT dataset of 64 subjects by five-fold cross validation. Our model achieved a 53.3% av…
DeepMind（深度思维）；MIT（麻省理工学院）；University of Oxford（牛津大学）
The core problem in zero-shot open vocabulary detection is how to align visual and text features, so that the detector performs well on unseen classes. Previous approaches train the feature pyramid and detection head from scratch, which breaks the vision-text feature alignment established during pretraining, and struggles to prevent the language model from forgetting unseen classes. We propose three methods to alleviate these issues. Firstly, a simple scheme is used to augment the text embeddings which prevents overfitting to a small number of classes seen during training, while simultaneously…
University of Science and Technology of China（中国科学技术大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Zero-Shot Learning (ZSL) seeks to recognize a sample from either seen or unseen domain by projecting the image data and semantic labels into a joint embedding space. However, most existing methods directly adapt a well-trained projection from one domain to another, thereby ignoring the serious bias problem caused by domain differences. To address this issue, we propose a novel Domain-Specific Embedding Network (DSEN) that can apply specific projections to different domains for unbiased embedding, as well as several domain constraints. In contrast to previous methods, the DSEN decomposes the do…
Adaptive Multi-Scale Correlation Meta-Network for Few-Shot Remote Sensing Image Classification
School of Computer Science, UPES, Dehradun, 248007, Uttarakhand, India.（UPES计算机科学学院）；School of Computer Science and Engineering, Galgotias University, India.（加尔各答大学计算机科学与工程学院）；Computer Science and Information Systems, BITS Pilani, Pilani Rajasthan, India.（比什努学院计算机科学与信息系统）
University of New South Wales（新南威尔士大学）；University of Technology Sydney（悉尼科技大学）
Zero-shot learning (ZSL) refers to the problem of learning to classify instances from the novel classes (unseen) that are absent in the training set (seen). Most ZSL methods infer the correlation between visual features and attributes to train the classifier for unseen classes. However, such models may have a strong bias towards seen classes during training. Meta-learning has been introduced to mitigate the basis, but meta-ZSL methods are inapplicable when tasks used for training are sampled from diverse distributions. In this regard, we propose a novel Task-aligned Generative Meta-learning mo…
Jiangnan University（江南大学）；University of New South Wales（新南威尔士大学）；Australian Artificial Intelligence Institute, University of Technology Sydney（悉尼科技大学澳大利亚人工智能研究所）；Zhejiang University（浙江大学）
The task of Compositional Zero-Shot Learning (CZSL) is to recognize images of novel state-object compositions that are absent during the training stage. Previous methods of learning compositional embedding have shown effectiveness in closed-world CZSL. However, in Open-World CZSL (OW-CZSL), their performance tends to degrade significantly due to the large cardinality of possible compositions. Some recent works separately predict simple primitives (i.e., states and objects) to reduce cardinality. However, they consider simple primitives as independent probability distributions, ignoring the hea…
Attribute-Aware Representation Rectification for Generalized Zero-Shot Learning
The Hong Kong Polytechnic University（香港理工大学）；Hong Kong Polytechnic University Shenzhen Research Institute（香港理工大学深圳研究院）；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）
School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）；Inception Institute of Artificial Intelligence（Inception人工智能研究院）；School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）
One-shot semantic image segmentation aims to segment the object regions for the novel class with only one annotated image. Recent works adopt the episodic training strategy to mimic the expected situation at testing time. However, these existing approaches simulate the test conditions too strictly during the training process, and thus cannot make full use of the given label information. Besides, these approaches mainly focus on the foreground-background target class segmentation setting. They only utilize binary mask labels for training. In this paper, we propose to leverage the multi-class la…
How Far Are Surgeons from Surgical World Models? A Pilot Study on Zero-shot Surgical Video Generation with Expert Assessment
Yale University（耶鲁大学）；University of Nottingham（诺丁汉大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Department of Neurosurgery, The First Hospital, Shanxi Medical University（山西医科大学第一医院神经外科部）；Department of Gastrointestinal Surgery, The Second Qilu Hospital, Shandong University（山东大学第二齐鲁医院胃肠外科部）；Technical University of Munich（慕尼黑技术大学）；University of Rochester（罗切斯特大学）
DVLA-RL++: Dual-Level Vision-Language Alignment with Reinforcement Learning Gating for Few-Shot Learning
School of Software, Shandong University（山东大学软件学院）；Shenzhen Loop Area Institute（深圳河套学院）；School of Computer and Artificial Intelligence, Shandong University of Finance and Economics（山东财经大学计算机与人工智能学院）；School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）计算机科学与技术学院）
