Few-shot Learning (FSL) which aims to learn from few labeled training data is becoming a popular research topic, due to the expensive labeling cost in many real-world applications. One kind of successful FSL method learns to compare the testing (query) image and training (support) image by simply concatenating the features of two images and feeding it into the neural network. However, with few labeled data in each class, the neural network has difficulty in learning or comparing the local features of two images. Such simple image-level comparison may cause serious mis-classification. To solve this problem, we propose Augmented Bi-path Network (ABNet) for learning to compare both global and local features on multi-scales. Specifically, the salient patches are extracted and embedded as the local features for every image. Then, the model learns to augment the features for better robustness. Finally, the model learns to compare global and local features separately, i.e., in two paths, before merging the similarities. Extensive experiments show that the proposed ABNet outperforms the state-of-the-art methods. Both quantitative and visual ablation studies are provided to verify that the proposed modules lead to more precise comparison results.
Korea University（高丽大学）；NAVERWEBTOON Corp.（NAVERWEBTOON公司）
Despite recent advancements in deep learning-based automatic colorization, they are still limited when it comes to few-shot learning. Existing models require a significant amount of training data. To tackle this issue, we present a novel memory-augmented colorization model MemoPainter that can produce high-quality colorization with limited data. In particular, our model is able to capture rare instances and successfully colorize them. We also propose a novel threshold triplet loss that enables unsupervised training of memory networks without the need of class labels. Experiments show that our …
CLIP (Contrastive Language-Image Pre-Training) has shown remarkable zero-shot transfer capabilities in cross-modal correlation tasks such as visual classification and image retrieval. However, its performance in cross-modal generation tasks like zero-shot image captioning remains unsatisfied. In this work, we discuss that directly employing CLIP for zero-shot image captioning relies more on the textual modality in context and largely ignores the visual information, which we call \emph{contextual language prior}. To address this, we propose Cross-modal Language Models (CLMs) to facilitate unsup…
Zhejiang University（浙江大学）；Alibaba Group（阿里巴巴集团）；University of Sydney（悉尼大学）
In this paper, we introduce a selective zero-shot classification problem: how can the classifier avoid making dubious predictions? Existing attribute-based zero-shot classification methods are shown to work poorly in the selective classification scenario. We argue the under-complete human defined attribute vocabulary accounts for the poor performance. We propose a selective zero-shot classifier based on both the human defined and the automatically discovered residual attributes. The proposed classifier is constructed by firstly learning the defined and the residual attributes jointly. Then the…
Hefei University of Technology（合肥工业大学）；Zhengzhou University（郑州大学）；University of Science and Technology of China（中国科学技术大学）
Metric-based few-shot learning methods concentrate on learning transferable feature embedding that generalizes well from seen categories to unseen categories under the supervision of limited number of labelled instances. However, most of them treat each individual instance in the working context separately without considering its relationships with the others. In this work, we investigate a new metric-learning method, Memory-Augmented Relation Network (MRN), to explicitly exploit these relationships. In particular, for an instance, we choose the samples that are visually similar from the worki…
VisTa: Visual-contextual and Text-augmented Zero-shot Object-level OOD Detection
Huazhong University of Science and Technology（华中科技大学）；Wuhan National Laboratory for Optoelectronics（武汉光电国家研究中心）；Ping An Technology (Shenzhen) Co., Ltd（平安科技（深圳）有限公司）
TPCap: Unlocking Zero-Shot Image Captioning with Trigger-Augmented and Multi-Modal Purification Modules
Faculty of Information Engineering and Automation, Kunming University of Science and Technology（昆明理工大学信息工程与自动化学院）；Yunnan Key Laboratory of Computer Technologies Application（云南省计算机技术应用重点实验室）；Hongyun Honghe Group Honghe Cigarette Factory（红云红河集团红河卷烟厂）
Renmin University of China（中国人民大学）；University of Surrey（萨里大学）；Alibaba Group（阿里巴巴集团）
Most recent few-shot learning (FSL) methods are based on meta-learning with episodic training. In each meta-training episode, a discriminative feature embedding and/or classifier are first constructed from a support set in an inner loop, and then evaluated in an outer loop using a query set for model updating. This query set sample centered learning objective is however intrinsically limited in addressing the lack of training data problem in the support set. In this paper, a novel contrastive prototype learning with augmented embeddings (CPLAE) model is proposed to overcome this limitation. Fi…
Hierarchical Relation-augmented Representation Generalization for Few-shot Action Recognition
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）；Artificial Intelligence Industrial Technology Research Institute, Nanjing Institute of Technology（南京理工大学人工智能工业技术研究院）
ByteDance Inc（字节跳动公司）；National University of Singapore（新加坡国立大学）
While substantial progresses have been made in automated 2D portrait stylization, admirable 3D portrait stylization from a single user photo remains to be an unresolved challenge. One primary obstacle here is the lack of high quality stylized 3D training data. In this paper, we propose a novel framework \emph{AgileGAN3D} that can produce 3D artistically appealing and personalized portraits with detailed geometry. New stylization can be obtained with just a few (around 20) unpaired 2D exemplars. We achieve this by first leveraging existing 2D stylization capabilities, \emph{style prior creation…
TLAC: Two-stage LMM Augmented CLIP for Zero-Shot Classification
Information Technology University（信息科技大学）；University of Ontario Institute of Technology（Ontario Institute of Technology 大学）；Mohamed Bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学）
Tsinghua University（清华大学）；The University of Manchester（曼彻斯特大学）；Tencent（腾讯）
Visual Relation Detection (VRD) aims to detect relationships between objects for image understanding. Most existing VRD methods rely on thousands of training samples of each relationship to achieve satisfactory performance. Some recent papers tackle this problem by few-shot learning with elaborately designed pipelines and pre-trained word vectors. However, the performance of existing few-shot VRD models is severely hampered by the poor generalization capability, as they struggle to handle the vast semantic diversity of visual relationships. Nonetheless, humans have the ability to learn new rel…
Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learning
Huazhong University of Science and Technology (HUST)（华中科技大学）；Alibaba Group（阿里巴巴集团）；The University of Sydney（悉尼大学）；Mohamed bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学）；Australian National University（澳大利亚国立大学）；Linköping University（林雪平大学）
Sun Yat-sen University（中山大学）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education（教育部机器智能与先进计算重点实验室）；Huawei Technologies Co., Ltd.（华为技术有限公司）；Guangdong Province Key Laboratory of Information Security Technology（广东省信息安全技术重点实验室）
Under the domain shift, cross-domain few-shot object detection aims to adapt object detectors in the target domain with a few annotated target data. There exists two significant challenges: (1) Highly insufficient target domain data; (2) Potential over-adaptation and misleading caused by inappropriately amplified target samples without any restriction. To address these challenges, we propose an adaptive method consisting of two parts. First, we propose an adaptive optimization strategy to select augmented data similar to target samples rather than blindly increasing the amount. Specifically, w…
ARIANNA stands for pAth Recognition for Indoor Assisted Navigation with Augmented perception. It is a flexible and low cost navigation system for vi- sually impaired people. Arianna permits to navigate colored paths painted or sticked on the floor revealing their directions through vibrational feedback on commercial smartphones.
Dual-channel Prototype Network for few-shot Classification of Pathological Images
College of Medicine and Biological Information Engineering, Northeastern University（东北大学医学与生物信息工程学院）；School of Computer, National University of Defense Technology（国防科技大学计算机学院）
MEGVII Technology（旷视科技）；Tsinghua University（清华大学）；Hong Kong University of Science and Technology（香港科技大学）
We revisit the one-shot Neural Architecture Search (NAS) paradigm and analyze its advantages over existing NAS approaches. Existing one-shot method, however, is hard to train and not yet effective on large scale datasets like ImageNet. This work propose a Single Path One-Shot model to address the challenge in the training. Our central idea is to construct a simplified supernet, where all architectures are single paths so that weight co-adaption problem is alleviated. Training is performed by uniform path sampling. All architectures (and their weights) are trained fully and equally. Comprehensi…
Despite the great progress made by deep neural networks in the semantic segmentation task, traditional neural-networkbased methods typically suffer from a shortage of large amounts of pixel-level annotations. Recent progress in fewshot semantic segmentation tackles the issue by only a few pixel-level annotated examples. However, these few-shot approaches cannot easily be applied to multi-way or weak annotation settings. In this paper, we advance the few-shot segmentation paradigm towards a scenario where image-level annotations are available to help the training process of a few pixel-level an…
Panoptic segmentation, which is a novel task of unifying instance segmentation and semantic segmentation, has attracted a lot of attention lately. However, most of the previous methods are composed of multiple pathways with each pathway specialized to a designated segmentation task. In this paper, we propose to resolve panoptic segmentation in single-shot by integrating the execution flows. With the integrated pathway, a unified feature map called Panoptic-Feature is generated, which includes the information of both things and stuffs. Panoptic-Feature becomes more sophisticated by auxiliary pr…
The Chinese University of Hong Kong（香港中文大学）；Sun Yat-sen University（中山大学）；Huawei Singular Security Lab（华为奇安安全实验室）
Deep neural networks have achieved unprecedented success on diverse vision tasks. However, they are vulnerable to adversarial noise that is imperceptible to humans. This phenomenon negatively affects their deployment in real-world scenarios, especially security-related ones. To evaluate the robustness of a target model in practice, transfer-based attacks craft adversarial samples with a local model and have attracted increasing attention from researchers due to their high efficiency. The state-of-the-art transfer-based attacks are generally based on data augmentation, which typically augments …
Zero-shot recognition aims to accurately recognize objects of unseen classes by using a shared visual-semantic mapping between the image feature space and the semantic embedding space. This mapping is learned on training data of seen classes and is expected to have transfer ability to unseen classes. In this paper, we tackle this problem by exploiting the intrinsic relationship between the semantic space manifold and the transfer ability of visual-semantic mapping. We formalize their connection and cast zero-shot recognition as a joint optimization problem. Motivated by this, we propose a nove…
SaSi: A Self-augmented and Self-interpreted Deep Learning Approach for Few-shot Cryo-ET Particle Detection
National Institute of Technology, Tiruchirappalli（印度坦切尔普拉迪村国家理工学院）；University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）；Carnegie Mellon University（卡内基梅隆大学）
Beijing University of Posts and Telecommunications（北京邮电大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Science and Technology of China（中国科学技术大学）
Nowadays U-net-like FCNs predominate various biomedical image segmentation applications and attain promising performance, largely due to their elegant architectures, e.g., symmetric contracting and expansive paths as well as lateral skip-connections. It remains a research direction to devise novel architectures to further benefit the segmentation. In this paper, we develop an ACE-net that aims to enhance the feature representation and utilization by augmenting the contracting and expansive paths. In particular, we augment the paths by the recently proposed advanced techniques including ASPP, d…
Newly emerging variants of ransomware pose an ever-growing threat to computer systems governing every aspect of modern life through the handling and analysis of big data. While various recent security-based approaches have focused on detecting and classifying ransomware at the network or system level, easy-to-use post-infection ransomware classification for the lay user has not been attempted before. In this paper, we investigate the possibility of classifying the ransomware a system is infected with simply based on a screenshot of the splash screen or the ransom note captured using a consumer…
The University of Sydney（悉尼大学）；SenseTime Research（商汤科技研究院）；Tsinghua University（清华大学）
In one-shot weight sharing for NAS, the weights of each operation (at each layer) are supposed to be identical for all architectures (paths) in the supernet. However, this rules out the possibility of adjusting operation weights to cater for different paths, which limits the reliability of the evaluation results. In this paper, instead of counting on a single supernet, we introduce $K$-shot supernets and take their weights for each operation as a dictionary. The operation weight for each path is represented as a convex combination of items in a dictionary with a simplex code. This enables a ma…
SignRAG: A Retrieval-Augmented System for Scalable Zero-Shot Road Sign Recognition
Computer Engineering The Ohio State University（计算机工程 俄亥俄州立大学）；Applied Research Transportation Research Center Inc.（应用研究 交通运输研究中心公司）；Computer Engineering The Ohio State University Columbus, Ohio, USA（计算机工程 俄亥俄州立大学 哥伦布俄亥俄州）；Applied Research Transportation Research Center Inc. East Liberty, Ohio, USA（应用研究 交通运输研究中心公司 埃斯特利比 俄亥俄州）
RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition
Shanghai Jiao Tong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）；MThreads, Inc.（MThreads公司）；Nanyang Technological University（南洋理工大学）
This paper presents a novel deep learning architecture for word-level lipreading. Previous works suggest a potential for incorporating a pretrained deep 3D Convolutional Neural Networks as a front-end feature extractor. We introduce a SpotFast networks, a variant of the state-of-the-art SlowFast networks for action recognition, which utilizes a temporal window as a spot pathway and all frames as a fast pathway. We further incorporate memory augmented lateral transformers to learn sequential features for classification. We evaluate the proposed model on the LRW dataset. The experiments show tha…
University of Wisconsin–Madison（威斯康星大学麦迪逊分校）；Microsoft（微软）
Image-text contrastive learning models such as CLIP have demonstrated strong task transfer ability. The high generality and usability of these visual models is achieved via a web-scale data collection process to ensure broad concept coverage, followed by expensive pre-training to feed all the knowledge into model weights. Alternatively, we propose REACT, REtrieval-Augmented CusTomization, a framework to acquire the relevant web knowledge to build customized visual models for target domains. We retrieve the most relevant image-text pairs (~3% of CLIP pre-training data) from the web-scale databa…
