Contrastive Language Image Pre-training (CLIP) has recently demonstrated success across various tasks due to superior feature representation empowered by image-text contrastive learning. However, the instance discrimination method used by CLIP can hardly encode the semantic structure of training data. To handle this limitation, cluster discrimination has been proposed through iterative cluster assignment and classification. Nevertheless, most cluster discrimination approaches only define a single pseudo-label for each image, neglecting multi-label signals in the image. In this paper, we propose a novel Multi-Label Cluster Discrimination method named MLCD to enhance representation learning. In the clustering step, we first cluster the large-scale LAION-400M dataset into one million centers based on off-the-shelf embedding features. Considering that natural images frequently contain multiple visual objects or attributes, we select the multiple closest centers as auxiliary class labels. In the discrimination step, we design a novel multi-label classification loss, which elegantly separates losses from positive classes and negative classes, and alleviates ambiguity on decision boundary. We validate the proposed multi-label cluster discrimination method with experiments on different scales of models and pre-training datasets. Experimental results show that our method achieves state-of-the-art performance on multiple downstream tasks including linear probe, zero-shot classification, and image-text retrieval. Code and models have been released at https://github.com/deepglint/unicom .
UC San Diego（加州大学圣迭戈分校）；Facebook AI Research（脸书人工智能研究院）
We present a self-supervised learning approach to learn audio-visual representations from video and audio. Our method uses contrastive learning for cross-modal discrimination of video from audio and vice-versa. We show that optimizing for cross-modal discrimination, rather than within-modal discrimination, is important to learn good representations from video and audio. With this simple but powerful insight, our method achieves highly competitive performance when finetuned on action recognition tasks. Furthermore, while recent work in contrastive learning defines positive and negative samples …
UC San Diego（加州大学圣迭戈分校）；Facebook AI Research（Facebook人工智能研究院）
We present a self-supervised learning method to learn audio and video representations. Prior work uses the natural correspondence between audio and video to define a standard cross-modal instance discrimination task, where a model is trained to match representations from the two modalities. However, the standard approach introduces two sources of training noise. First, audio-visual correspondences often produce faulty positives since the audio and video signals can be uninformative of each other. To limit the detrimental impact of faulty positives, we optimize a weighted contrastive learning l…
University of Chinese Academy of Sciences（中国科学院大学）
This paper proposes a novel model, named Continuity-Discrimination Convolutional Neural Network (CD-CNN), for visual object tracking. Existing state-of-the-art tracking methods do not deal with temporal relationship in video sequences, which leads to imperfect feature representations. To address this problem, CD-CNN models temporal appearance continuity based on the idea of temporal slowness. Mathematically, we prove that, by introducing temporal appearance continuity into tracking, the upper bound of target appearance representation error can be sufficiently small with high probability. Furth…
Google（谷歌公司）；University of Bristol（布里斯托尔大学）；The University of Hong Kong（香港大学）
This paper studies the problem of novel category discovery on single- and multi-modal data with labels from different but relevant categories. We present a generic, end-to-end framework to jointly learn a reliable representation and assign clusters to unlabelled data. To avoid over-fitting the learnt embedding to labelled data, we take inspiration from self-supervised representation learning by noise-contrastive estimation and extend it to jointly handle labelled and unlabelled data. In particular, we propose using category discrimination on labelled data and cross-modal discrimination on mult…
The ability to discriminate between large and small quantities is a core aspect of basic numerical competence in both humans and animals. In this work, we examine the extent to which the state-of-the-art neural networks designed for vision exhibit this basic ability. Motivated by studies in animal and infant numerical cognition, we use the numerical bisection procedure to test number discrimination in different families of neural architectures. Our results suggest that vision-specific inductive biases are helpful in numerosity discrimination, as models with such biases have lowest test errors …
Alibaba Group（阿里巴巴集团）；School of Engineering and Technology, University of Washington（华盛顿大学工程与技术学院）
Cluster discrimination is an effective pretext task for unsupervised representation learning, which often consists of two phases: clustering and discrimination. Clustering is to assign each instance a pseudo label that will be used to learn representations in discrimination. The main challenge resides in clustering since prevalent clustering methods (e.g., k-means) have to run in a batch mode. Besides, there can be a trivial solution consisting of a dominating cluster. To address these challenges, we first investigate the objective of clustering-based representation learning. Based on this, we…
Current video representations heavily rely on learning from manually annotated video datasets which are time-consuming and expensive to acquire. We observe videos are naturally accompanied by abundant text information such as YouTube titles and Instagram captions. In this paper, we leverage this visual-textual connection to learn spatiotemporal features in an efficient weakly-supervised manner. We present a general cross-modal pair discrimination (CPD) framework to capture this correlation between a video and its associated text. Specifically, we adopt noise-contrastive estimation to tackle th…
Centre Universitaire Condorcet（孔多塞大学中心）；Université de Bourgogne（勃艮第大学）
Diabetic retinopathy (DR) and age related macular degeneration (ARMD) are among the major causes of visual impairment worldwide. DR is mainly characterized by red spots, namely microaneurysms and bright lesions, specifically exudates whereas ARMD is mainly identified by tiny yellow or white deposits called drusen. Since exudates might be the only manifestation of the early diabetic retinopathy, there is an increase demand for automatic retinopathy diagnosis. Exudates and drusen may share similar appearances, thus discriminating between them is of interest to enhance screening performance. In t…
Deep learning-based object detectors have shown remarkable improvements. However, supervised learning-based methods perform poorly when the train data and the test data have different distributions. To address the issue, domain adaptation transfers knowledge from the label-sufficient domain (source domain) to the label-scarce domain (target domain). Self-training is one of the powerful ways to achieve domain adaptation since it helps class-wise domain adaptation. Unfortunately, a naive approach that utilizes pseudo-labels as ground-truth degenerates the performance due to incorrect pseudo-labe…
The instance discrimination paradigm has become dominant in unsupervised learning. It always adopts a teacher-student framework, in which the teacher provides embedded knowledge as a supervision signal for the student. The student learns meaningful representations by enforcing instance spatial consistency with the views from the teacher. However, the outputs of the teacher can vary dramatically on the same instance during different training stages, introducing unexpected noise and leading to catastrophic forgetting caused by inconsistent objectives. In this paper, we first integrate instance t…
Cross-dataset transportability of pediatric chest X-ray deep learning across three countries: discrimination, calibration, operating-point failure, and limited-label recovery
American International University-Bangladesh (AIUB)（美国国际大学孟加拉分校）
University of Science Technology of China（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）
The greatest challenge facing visual object tracking is the simultaneous requirements on robustness and discrimination power. In this paper, we propose a SiamFC-based tracker, named SPM-Tracker, to tackle this challenge. The basic idea is to address the two requirements in two separate matching stages. Robustness is strengthened in the coarse matching (CM) stage through generalized training while discrimination power is enhanced in the fine matching (FM) stage through a distance learning network. The two stages are connected in series as the input proposals of the FM stage are generated by the…
Semantic Positive Pairs for Enhancing Visual Representation Learning of Instance Discrimination Methods
Department of Computing Science University of Aberdeen, UK（计算科学系大学爱丁堡大学，英国）；Department of Computing Science & Interdisciplinary Centre for Data and AI University of Aberdeen, UK（计算科学系与数据和人工智能交叉研究中心大学爱丁堡大学，英国）
Shandong University（山东大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Illinois Institute of Technology（伊利诺伊理工学院）
Several studies have recently pointed that existing Visual Question Answering (VQA) models heavily suffer from the language prior problem, which refers to capturing superficial statistical correlations between the question type and the answer whereas ignoring the image contents. Numerous efforts have been dedicated to strengthen the image dependency by creating the delicate models or introducing the extra visual annotations. However, these methods cannot sufficiently explore how the visual cues explicitly affect the learned answer representation, which is vital for language reliance alleviatio…
Reinforced Label Denoising for Weakly-Supervised Audio-Visual Video Parsing
Shandong University（山东大学）；Qilu University of Technology (Shandong Academy of Sciences)（齐鲁工业大学（山东省科学院））；Shandong Computer Science Center (National Supercomputer Center in Jinan)（山东省计算中心（国家超级计算济南中心））
Visual data such as images and videos contain a rich source of structured semantic labels as well as a wide range of interacting components. Visual content could be assigned with fine-grained labels describing major components, coarse-grained labels depicting high level abstractions, or a set of labels revealing attributes. Such categorization over different, interacting layers of labels evinces the potential for a graph-based encoding of label information. In this paper, we exploit this rich structure for performing graph-based inference in label space for a number of tasks: multi-label image…
Ca’ Foscari University of Venice（威尼斯卡福斯卡里大学）；International School for Advanced Studies (SISSA)（国际高等研究学院（SISSA））
For most animal species, quick and reliable identification of visual objects is critical for survival. This applies also to rodents, which, in recent years, have become increasingly popular models of visual functions. For this reason in this work we analyzed how various properties of visual objects are represented in rat primary visual cortex (V1). The analysis has been carried out through supervised (classification) and unsupervised (clustering) learning methods. We assessed quantitatively the discrimination capabilities of V1 neurons by demonstrating how photometric properties (luminosity an…
SenseTime Research（商汤科技研究院）；Rice University（莱斯大学）；The Chinese University of Hong Kong（香港中文大学）；Shanghai Jiao Tong University（上海交通大学）
Webly supervised learning becomes attractive recently for its efficiency in data expansion without expensive human labeling. However, adopting search queries or hashtags as web labels of images for training brings massive noise that degrades the performance of DNNs. Especially, due to the semantic confusion of query words, the images retrieved by one query may contain tremendous images belonging to other concepts. For example, searching `tiger cat' on Flickr will return a dominating number of tiger images rather than the cat images. These realistic noisy samples usually have clear visual seman…
Monash University（莫纳什大学）；University of Adelaide（阿德莱德大学）
We present LAVA, a simple yet effective method for multi-domain visual transfer learning with limited data. LAVA builds on a few recent innovations to enable adapting to partially labelled datasets with class and domain shifts. First, LAVA learns self-supervised visual representations on the source dataset and ground them using class label semantics to overcome transfer collapse problems associated with supervised pretraining. Secondly, LAVA maximises the gains from unlabelled target data via a novel method which uses multi-crop augmentations to obtain highly robust pseudo-labels. By combining…
University of California, Los Angeles（加州大学洛杉矶分校）；Adobe Research（奥多比研究院）
Visual-semantic embedding models have been recently proposed and shown to be effective for image classification and zero-shot learning, by mapping images into a continuous semantic label space. Although several approaches have been proposed for single-label embedding tasks, handling images with multiple labels (which is a more general setting) still remains an open problem, mainly due to the complex underlying corresponding relationship between image and its labels. In this work, we present Multi-Instance visual-semantic Embedding model (MIE) for embedding images associated with either single …
Dynamic Visual-semantic Alignment for Zero-shot Learning with Ambiguous Labels
College of Computer Science and Technology（计算机科学与技术学院）；School of Computer Science（计算机科学学院）；Key Laboratory of Computing Power Network and Information Security, Ministry of Education（教育部计算能力网络与信息安全重点实验室）；Shandong Computer Science Center（山东计算机科学中心）；Qilu University of Technology (Shandong Academy of Sciences)（齐鲁工业大学（山东科学院））
School of Computer Science, Wuhan University, Wuhan, Hubei, China（中国湖北省武汉市武汉大学计算机学院）；School of Information Engineering, Hubei University for Nationalities, Enshi, Hubei, China（中国湖北省恩施市湖北民族学院信息工程学院）
In this paper, we propose a novel way to interpret text information by extracting visual feature presentation from multiple high-resolution and photo-realistic synthetic images generated by Text-to-image Generative Adversarial Network (GAN) to improve the performance of image labeling. Firstly, we design a stacked Generative Multi-Adversarial Network (GMAN), StackGMAN++, a modified version of the current state-of-the-art Text-to-image GAN, StackGAN++, to generate multiple synthetic images with various prior noises conditioned on a text. And then we extract deep visual features from the generat…
Czech Technical University in Prague（捷克技术大学）；IBM Research Zürich（IBM苏黎世研究院）
Labeling images for visual segmentation is a time-consuming task which can be costly, particularly in application domains where labels have to be provided by specialized expert annotators, such as civil engineering. In this paper, we propose to use attribution methods to harness the valuable interactions between expert annotators and the data to be annotated in the case of defect segmentation for visual inspection of civil infrastructures. Concretely, a classifier is trained to detect defects and coupled with an attribution-based method and adversarial climbing to generate and refine segmentat…
School of Computer Science and Engineering Northwestern Polytechnical University（西北工业大学计算机学院）
Recently a category of tracking methods based on "tracking-by-detection" is widely used in visual tracking problem. Most of these methods update the classifier online using the samples generated by the tracker to handle the appearance changes. However, the self-updating scheme makes these methods suffer from drifting problem because of the incorrect labels of weak classifiers in training samples. In this paper, we split the class labels into true labels and noise labels and model them by sparse representation. A novel dynamic classifier selection method, robust to noisy training data, is propo…
SenseTime Research（商汤科技研究院）；Development Research Institute of Guangzhou Smart City（广州智慧城市发展研究院）；Nanyang Technological University（南洋理工大学）；Peng Cheng Laboratory（鹏城实验室）
Self-supervised learning (SSL) holds promise in leveraging large amounts of unlabeled data. However, the success of popular SSL methods has limited on single-centric-object images like those in ImageNet and ignores the correlation among the scene and instances, as well as the semantic difference of instances in the scene. To address the above problems, we propose a Unified Self-supervised Visual Pre-training (UniVIP), a novel self-supervised framework to learn versatile visual representations on either single-centric-object or non-iconic dataset. The framework takes into account the representa…
AFiRe: Anatomy-Driven Self-Supervised Learning for Fine-Grained Representation in Radiographic Images
School of Computer Science and Technology, Tongji University（同济大学计算机科学与技术学院）；Shanghai Eye Diseases Prevention and Treatment Center, Shanghai Eye Hospital（上海市眼病防治中心、上海眼科医院）；School of Communication and Electronic Engineering, East China Normal University（华东师范大学通信与电子工程学院）
National Taiwan University（国立台湾大学）；Carnegie Mellon University（卡内基梅隆大学）
In this paper, we propose the joint learning attention and recurrent neural network (RNN) models for multi-label classification. While approaches based on the use of either model exist (e.g., for the task of image captioning), training such existing network architectures typically require pre-defined label sequences. For multi-label classification, it would be desirable to have a robust inference process, so that the prediction error would not propagate and thus affect the performance. Our proposed model uniquely integrates attention and Long Short Term Memory (LSTM) models, which not only add…
Sensetime Research（商汤科技研究院）；The Hong Kong Polytechnic University（香港理工大学）
Video highlight detection is a crucial yet challenging problem that aims to identify the interesting moments in untrimmed videos. The key to this task lies in effective video representations that jointly pursue two goals, \textit{i.e.}, cross-modal representation learning and fine-grained feature discrimination. In this paper, these two challenges are tackled by not only enriching intra-modality and cross-modality relations for representation modeling but also shaping the features in a discriminative manner. Our proposed method mainly leverages the intra-modality encoding and cross-modality co…
This paper deals with a method for generating realistic labeled masses. Recently, there have been many attempts to apply deep learning to various bio-image computing fields including computer-aided detection and diagnosis. In order to learn deep network model to be well-behaved in bio-image computing fields, a lot of labeled data is required. However, in many bioimaging fields, the large-size of labeled dataset is scarcely available. Although a few researches have been dedicated to solving this problem through generative model, there are some problems as follows: 1) The generated bio-image doe…
University of Science and Technology of China（中国科学技术大学）；Huawei Inc.（华为公司）
Recently, contrastive learning has largely advanced the progress of unsupervised visual representation learning. Pre-trained on ImageNet, some self-supervised algorithms reported higher transfer learning performance compared to fully-supervised methods, seeming to deliver the message that human labels hardly contribute to learning transferrable visual features. In this paper, we defend the usefulness of semantic labels but point out that fully-supervised and self-supervised methods are pursuing different kinds of features. To alleviate this issue, we present a new algorithm named Supervised Co…
This work introduces verb-only representations for both recognition and retrieval of visual actions, in video. Current methods neglect legitimate semantic ambiguities between verbs, instead choosing unambiguous subsets of verbs along with objects to disambiguate the actions. We instead propose multiple verb-only labels, which we learn through hard or soft assignment as a regression. This enables learning a much larger vocabulary of verbs, including contextual overlaps of these verbs. We collect multi-verb annotations for three action video datasets and evaluate the verb-only labelling represen…
Tufts University（塔夫茨大学）；City University of Hong Kong（香港城市大学）；Wake Forest University（维克森林大学）
Hyperspectral images encode rich structure that can be exploited for material discrimination by machine learning algorithms. This article introduces the Active Diffusion and VCA-Assisted Image Segmentation (ADVIS) for active material discrimination. ADVIS selects high-purity, high-density pixels that are far in diffusion distance (a data-dependent metric) from other high-purity, high-density pixels in the hyperspectral image. The ground truth labels of these pixels are queried and propagated to the rest of the image. The ADVIS active learning algorithm is shown to strongly outperform its fully…
Equal Opportunity and Fairness are receiving increasing attention in artificial intelligence. Stereotyping is another source of discrimination, which yet has been unstudied in literature. GAN-made faces would be exposed to such discrimination, if they are classified by human perception. It is possible to eliminate the human impact on fictitious faces classification task by the use of statistical approaches. We present a novel approach through penalized regression to label stereotype-free GAN-generated synthetic unlabeled images. The proposed approach aids labeling new data (fictitious output i…
Hefei University of Technology（合肥工业大学）；Hefei Comprehensive National Science Center（合肥综合性国家科学中心）；Shanghai AI Lab（上海人工智能实验室）
Audio-Visual Video Parsing is a task to predict the events that occur in video segments for each modality. It often performs in a weakly supervised manner, where only video event labels are provided, i.e., the modalities and the timestamps of the labels are unknown. Due to the lack of densely annotated labels, recent work attempts to leverage pseudo labels to enrich the supervision. A commonly used strategy is to generate pseudo labels by categorizing the known event labels for each modality. However, the labels are still limited to the video level, and the temporal boundaries of event timesta…
Arizona State University（亚利桑那州立大学）；Mayo Clinic（梅奥诊所）
Recently, self-supervised instance discrimination methods have achieved significant success in learning visual representations from unlabeled photographic images. However, given the marked differences between photographic and medical images, the efficacy of instance-based objectives, focusing on learning the most discriminative global features in the image (i.e., wheels in bicycle), remains unknown in medical imaging. Our preliminary analysis showed that high global similarity of medical images in terms of anatomy hampers instance discrimination methods for capturing a set of distinct features…
Given data with label noise (i.e., incorrect data), deep neural networks would gradually memorize the label noise and impair model performance. To relieve this issue, curriculum learning is proposed to improve model performance and generalization by ordering training samples in a meaningful (e.g., easy to hard) sequence. Previous work takes incorrect samples as generic hard ones without discriminating between hard samples (i.e., hard samples in correct data) and incorrect samples. Indeed, a model should learn from hard samples to promote generalization rather than overfit to incorrect ones. In…
In this study, we propose a novel method to measure bottom-up saliency maps of natural images. In order to eliminate the influence of top-down signals, backward masking is used to make stimuli (natural images) subjectively invisible to subjects, however, the bottom-up saliency can still orient the subjects attention. To measure this orientation/attention effect, we adopt the cueing effect paradigm by deploying discrimination tasks at each location of an image, and measure the discrimination performance variation across the image as the attentional effect of the bottom-up saliency. Such attenti…
Visual sentiment analysis has received increasing attention in recent years. However, the dataset's quality is a concern because the sentiment labels are crowd-sourcing, subjective, and prone to mistakes, and poses a severe threat to the data-driven models, especially the deep neural networks. The deep models would generalize poorly on the testing cases when trained to over-fit the training samples with noisy sentiment labels. Inspired by the recent progress on learning with noisy labels, we propose a robust learning method to perform robust visual sentiment analysis. Our method relies on exte…
Advancing Weakly-Supervised Audio-Visual Video Parsing via Segment-wise Pseudo Labeling
Hefei University of Technology（合肥工业大学）；Shanghai AI Laboratory（上海人工智能实验室）；Hefei Comprehensive National Science Center（合肥综合性国家科学中心）；Anhui Zhonghuitong Technology Co., Ltd.（安徽中汇通科技有限公司）
The current evaluation protocol of long-tailed visual recognition trains the classification model on the long-tailed source label distribution and evaluates its performance on the uniform target label distribution. Such protocol has questionable practicality since the target may also be long-tailed. Therefore, we formulate long-tailed visual recognition as a label shift problem where the target and source label distributions are different. One of the significant hurdles in dealing with the label shift problem is the entanglement between the source label distribution and the model prediction. I…
Children learn to build a visual representation of the world from unsupervised exploration and we hypothesize that a key part of this learning ability is the use of self-generated navigational information as a similarity label to drive a learning objective for self-supervised learning. The goal of this work is to exploit navigational information in a visual environment to provide performance in training that exceeds the state-of-the-art self-supervised training. Here, we show that using spatial and temporal information in the pretraining stage of contrastive learning can improve the performanc…
University of Science and Technology of China（中国科学技术大学）
Generalized Zero-Shot Learning (GZSL) targets recognizing new categories by learning transferable image representations. Existing methods find that, by aligning image representations with corresponding semantic labels, the semantic-aligned representations can be transferred to unseen categories. However, supervised by only seen category labels, the learned semantic knowledge is highly task-specific, which makes image representations biased towards seen categories. In this paper, we propose a novel Dual-Contrastive Embedding Network (DCEN) that simultaneously learns task-specific and task-indep…
Automatic extraction of medical conditions from free-text radiology reports is critical for supervising computer vision models to interpret medical images. In this work, we show that radiologists labeling reports significantly disagree with radiologists labeling corresponding chest X-ray images, which reduces the quality of report labels as proxies for image labels. We develop and evaluate methods to produce labels from radiology reports that have better agreement with radiologists labeling images. Our best performing method, called VisualCheXbert, uses a biomedically-pretrained BERT model to …
Object detection plays an important role in current solutions to vision and language tasks like image captioning and visual question answering. However, popular models like Faster R-CNN rely on a costly process of annotating ground-truths for both the bounding boxes and their corresponding semantic labels, making it less amenable as a primitive task for transfer learning. In this paper, we examine the effect of decoupling box proposal and featurization for down-stream tasks. The key insight is that this allows us to leverage a large amount of labeled annotations that were previously unavailabl…
