Learning the Relation between Similarity Loss and Clustering Loss in Self-Supervised Learning
Nanjing University（南京大学）；Southeast University（东南大学）；Purple Mountain Laboratories（紫金山实验室）；Amazon.com L.L.C.（亚马逊有限责任公司）；Alibaba Group（阿里巴巴集团）；The Hong Kong University of Science and Technology（香港科技大学）；Southern Methodist University（南卫理公会大学）
Jidong Ge, Yuxiang Liu, Jie Gui, Lanting Fang, Ming Lin, James Tin-Yau Kwok, LiGuo Huang, Bin Luo
备注：
This paper is accepted by IEEE Transactions on Image Processing
Self-supervised learning enables networks to learn discriminative features from massive data itself. Most state-of-the-art methods maximize the similarity between two augmentations of one image based on contrastive learning. By utilizing the consistency of two augmentations, the burden of manual annotations can be freed. Contrastive learning exploits instance-level information to learn robust features. However, the learned information is probably confined to different views of the same instance. In this paper, we attempt to leverage the similarity between two distinct images to boost representation in self-supervised learning. In contrast to instance-level information, the similarity between two distinct images may provide more useful information. Besides, we analyze the relation between similarity loss and feature-level cross-entropy loss. These two losses are essential for most deep learning methods. However, the relation between these two losses is not clear. Similarity loss helps obtain instance-level representation, while feature-level cross-entropy loss helps mine the similarity between two distinct images. We provide theoretical analyses and experiments to show that a suitable combination of these two losses can get state-of-the-art results. Code is available at https://github.com/guijiejie/ICCL.
The Hong Kong University of Science and Technology（香港科技大学）
A deep clustering model conceptually consists of a feature extractor that maps data points to a latent space, and a clustering head that groups data points into clusters in the latent space. Although the two components used to be trained jointly in an end-to-end fashion, recent works have proved it beneficial to train them separately in two stages. In the first stage, the feature extractor is trained via self-supervised learning, which enables the preservation of the cluster structures among the data points. To preserve the cluster structures even better, we propose to replace the first stage …
State Key Laboratory for Novel Software Technology, Nanjing University（南京大学现代软件技术国家重点实验室）；School of Information Technology and Electrical Engineering, The University of Queensland（昆士兰大学信息技术与电气工程学院）
Large scale agglomerative clustering is hindered by computational burdens. We propose a novel scheme where exact inter-instance distance calculation is replaced by the Hamming distance between Kernelized Locality-Sensitive Hashing (KLSH) hashed values. This results in a method that drastically decreases computation time. Additionally, we take advantage of certain labeled data points via distance metric learning to achieve a competitive precision and recall comparing to K-Means but in much less computation time.
Tel Aviv University（特拉维夫大学）；University of California, San Diego（加利福尼亚大学圣迭戈分校）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
The fuzzy or soft $k$-means objective is a popular generalization of the well-known $k$-means problem, extending the clustering capability of the $k$-means to datasets that are uncertain, vague, and otherwise hard to cluster. In this paper, we propose a semi-supervised active clustering framework, where the learner is allowed to interact with an oracle (domain expert), asking for the similarity between a certain set of chosen items. We study the query and computational complexities of clustering in this framework. We prove that having a few of such similarity queries enables one to get a polyn…
UT Austin（德克萨斯大学奥斯汀分校）；JD AI Research（京东人工智能研究院）；IBM Research（IBM研究院）；Amazon（亚马逊）
A considerable amount of clustering algorithms take instance-feature matrices as their inputs. As such, they cannot directly analyze time series data due to its temporal nature, usually unequal lengths, and complex properties. This is a great pity since many of these algorithms are effective, robust, efficient, and easy to use. In this paper, we bridge this gap by proposing an efficient representation learning framework that is able to convert a set of time series with various lengths to an instance-feature matrix. In particular, we guarantee that the pairwise similarities between time series …
Most dialogue systems in real world rely on predefined intents and answers for QA service, so discovering potential intents from large corpus previously is really important for building such dialogue services. Considering that most scenarios have few intents known already and most intents waiting to be discovered, we focus on semi-supervised text clustering and try to make the proposed method benefit from labeled samples for better overall clustering performance. In this paper, we propose Deep Contrastive Semi-supervised Clustering (DCSC), which aims to cluster text samples in a semi-supervise…
Shanghai University of Finance and Economics（上海财经大学）
Deep semi-supervised learning has been widely implemented in the real-world due to the rapid development of deep learning. Recently, attention has shifted to the approaches such as Mean-Teacher to penalize the inconsistency between two perturbed input sets. Although these methods may achieve positive results, they ignore the relationship information between data instances. To solve this problem, we propose a novel method named Metric Learning by Similarity Network (MLSN), which aims to learn a distance metric adaptively on different domains. By co-training with the classification network, simi…
Self-supervised speech representation learning has recently been a prosperous research topic. Many algorithms have been proposed for learning useful representations from large-scale unlabeled data, and their applications to a wide range of speech tasks have also been investigated. However, there has been little research focusing on understanding the properties of existing approaches. In this work, we aim to provide a comparative study of some of the most representative self-supervised algorithms. Specifically, we quantify the similarities between different self-supervised representations using…
LEO Innovation Lab（LEO创新实验室）；Herlev Hospital（赫尔勒夫医院）；Colentina Clinical Hospital（科伦蒂纳临床医院）
Psoriasis is a complex disease with many variations in genotype and phenotype. General advancements in medicine has further complicated both assessments and treatment for both physicians and dermatologist alike. Even with all of our technological progress we still primarily use the assessment tool Psoriasis Area and Severity Index (PASI) for severity assessments which was developed in the 1970s. In this study we evaluate a method involving digital images, a comparison web application and similarity clustering, developed to improve the assessment tool in terms of intra- and inter-observer varia…
Many similarity-based clustering methods work in two separate steps including similarity matrix computation and subsequent spectral clustering. However, similarity measurement is challenging because it is usually impacted by many factors, e.g., the choice of similarity metric, neighborhood size, scale of data, noise and outliers. Thus the learned similarity matrix is often not suitable, let alone optimal, for the subsequent clustering. In addition, nonlinear similarity often exists in many real world data which, however, has not been effectively considered by most existing methods. To tackle t…
National University of Singapore（新加坡国立大学）；A*STAR（新加坡科技研究局）；A*STAR Genome Institute of Singapore（新加坡科技研究局基因组研究所）；Bioinformatics Institute（生物信息学研究所）；Image Pervasive Access Lab (IPAL) CNRS UMI 2955（图像普适访问实验室（IPAL）法国国家科学研究中心联合研究单位2955）；Singapore Eye Research Institute（新加坡眼科研究所）
A weakly supervised learning based clustering framework is proposed in this paper. As the core of this framework, we introduce a novel multiple instance learning task based on a bag level label called unique class count ($ucc$), which is the number of unique classes among all instances inside the bag. In this task, no annotations on individual instances inside the bag are needed during training of the models. We mathematically prove that with a perfect $ucc$ classifier, perfect clustering of individual instances inside the bags is possible even when no annotations on individual instances are g…
Supervised pixel-based texture classification is usually performed in the feature space. We propose to perform this task in (dis)similarity space by introducing a new compression-based (dis)similarity measure. The proposed measure utilizes two dimensional MPEG-1 encoder, which takes into consideration the spatial locality and connectivity of pixels in the images. The proposed formulation has been carefully designed based on MPEG encoder functionality. To this end, by design, it solely uses P-frame coding to find the (dis)similarity among patches/images. We show that the proposed measure works …
Similarity scores in face recognition represent the proximity between pairs of images as computed by a matching algorithm. Given a large set of images and the proximities between all pairs, a similarity score space is defined. Cluster analysis was applied to the similarity score space to develop various taxonomies. Given the number of subjects in the dataset, we used hierarchical methods to aggregate images of the same subject. We also explored the hierarchy above and below the subject level, including clusters that reflect gender and ethnicity. Evidence supports the existence of clustering by…
University of Louisville（路易斯维尔大学）；Captricity, Inc.（Captricity公司）
In this paper, we propose a new text recognition model based on measuring the visual similarity of text and predicting the content of unlabeled texts. First a Siamese convolutional network is trained with deep supervision on a labeled training dataset. This network projects texts into a similarity manifold. The Deeply Supervised Siamese network learns visual similarity of texts. Then a K-nearest neighbor classifier is used to predict unlabeled text based on similarity distance to labeled texts. The performance of the model is evaluated on three datasets of machine-print and hand-written text c…
Bangladesh University of Business & Technology（孟加拉国商业与技术大学）；King Abdulaziz University（阿卜杜勒阿齐兹国王大学）
Clustering is widely used in unsupervised learning method that deals with unlabeled data. Deep clustering has become a popular study area that relates clustering with Deep Neural Network (DNN) architecture. Deep clustering method downsamples high dimensional data, which may also relate clustering loss. Deep clustering is also introduced in semi-supervised learning (SSL). Most SSL methods depend on pairwise constraint information, which is a matrix containing knowledge if data pairs can be in the same cluster or not. This paper introduces a novel embedding system named AutoEmbedder, that downsa…
Tokyo University of Agriculture and Technology（东京农工大学）
Toward a computer-assisted marking for descriptive math questions,this paper presents clustering of online handwritten mathematical expressions (OnHMEs) to help human markers to mark them efficiently and reliably. We propose a generative sequence similarity function for computing a similarity score of two OnHMEs based on a sequence-to-sequence OnHME recognizer. Each OnHME is represented by a similarity-based representation (SbR) vector. The SbR matrix is inputted to the k-means algorithm for clustering OnHMEs. Experiments are conducted on an answer dataset (Dset_Mix) of 200 OnHMEs mixed of rea…
Khulna University of Engineering & Technology（库尔纳工程技术大学）
Handwritten numerals of different languages have various characteristics. Similarities and dissimilarities of the languages can be measured by analyzing the extracted features of the numerals. Handwritten numeral datasets are available and accessible for many renowned languages of different regions. In this paper, several handwritten numeral datasets of different languages are collected. Then they are used to find the similarity among those written languages through determining and comparing the similitude of each handwritten numerals. This will help to find which languages have the same or ad…
University of Electronic Science and Technology of China（电子科技大学）；University of Pennsylvania（宾夕法尼亚大学）；Institute for Infocomm Research, A*Star（新加坡科技研究局资讯通信研究院）
Graph-based clustering has shown promising performance in many tasks. A key step of graph-based approach is the similarity graph construction. In general, learning graph in kernel space can enhance clustering accuracy due to the incorporation of nonlinearity. However, most existing kernel-based graph learning mechanisms is not similarity-preserving, hence leads to sub-optimal performance. To overcome this drawback, we propose a more discriminative graph learning method which can preserve the pairwise similarities between samples in an adaptive manner for the first time. Specifically, we requir…
Technische Hochschule Ingolstadt（英戈尔施塔特应用技术大学）；Royal Melbourne Institute of Technology（皇家墨尔本理工大学）
Traffic scenario categorisation is an essential component of automated driving, for e.\,g., in motion planning algorithms and their validation. Finding new relevant scenarios without handcrafted steps reduce the required resources for the development of autonomous driving dramatically. In this work, a method is proposed to address this challenge by introducing a clustering technique based on a novel data-adaptive similarity measure, called Random Forest Activation Pattern (RFAP) similarity. The RFAP similarity is generated using a tree encoding scheme in a Random Forest algorithm. The clusteri…
Sri Sathya Sai Institute of Higher Learning（斯里·萨提亚·赛高等教育学院）
Spectral Clustering(SC) is a prominent data clustering technique of recent times which has attracted much attention from researchers. It is a highly data-driven method and makes no strict assumptions on the structure of the data to be clustered. One of the central pieces of spectral clustering is the construction of an affinity matrix based on a similarity measure between data points. The way the similarity measure is defined between data points has a direct impact on the performance of the SC technique. Several attempts have been made in the direction of strengthening the pairwise similarity …
Xidian University（西安电子科技大学）；Tencent AI Healthcare（腾讯AI医疗）；Rensselaer Polytechnic Institute（伦斯勒理工学院）
We propose a self-supervised Gaussian ATtention network for image Clustering (GATCluster). Rather than extracting intermediate features first and then performing the traditional clustering algorithm, GATCluster directly outputs semantic cluster labels without further post-processing. Theoretically, we give a Label Feature Theorem to guarantee the learned features are one-hot encoded vectors, and the trivial solutions are avoided. To train the GATCluster in a completely unsupervised manner, we design four self-learning tasks with the constraints of transformation invariance, separability maximi…
Clustering is a difficult and widely-studied data mining task, with many varieties of clustering algorithms proposed in the literature. Nearly all algorithms use a similarity measure such as a distance metric (e.g. Euclidean distance) to decide which instances to assign to the same cluster. These similarity measures are generally pre-defined and cannot be easily tailored to the properties of a particular dataset, which leads to limitations in the quality and the interpretability of the clusters produced. In this paper, we propose a new approach to automatically evolving similarity functions fo…
Clustering using neural networks has recently demonstrated promising performance in machine learning and computer vision applications. However, the performance of current approaches is limited either by unsupervised learning or their dependence on large set of labeled data samples. In this paper, we propose ClusterNet that uses pairwise semantic constraints from very few labeled data samples (<5% of total data) and exploits the abundant unlabeled data to drive the clustering approach. We define a new loss function that uses pairwise semantic similarity between objects combined with constrained…
Sri Sathya Sai Institute of Higher Learning（斯里萨蒂亚赛高等研究院）
Spectral clustering has gained importance in recent years due to its ability to cluster complex data as it requires only pairwise similarity among data points with its ease of implementation. The central point in spectral clustering is the process of capturing pair-wise similarity. In the literature, many research techniques have been proposed for effective construction of affinity matrix with suitable pair- wise similarity. In this paper a general framework for capturing pairwise affinity using local features such as density, proximity and structural similarity is been proposed. Topological N…
Weakly supervised video anomaly detection (WSVAD) is a challenging task since only video-level labels are available for training. In previous studies, the discriminative power of the learned features is not strong enough, and the data imbalance resulting from the mini-batch training strategy is ignored. To address these two issues, we propose a novel WSVAD method based on cross-batch clustering guidance. To enhance the discriminative power of features, we propose a batch clustering based loss to encourage a clustering branch to generate distinct normal and abnormal clusters based on a batch of…
Insufficient capability of existing subspace clustering methods to handle data coming from nonlinear manifolds, data corruptions, and out-of-sample data hinders their applicability to address real-world clustering and classification problems. This paper proposes the robust formulation of the self-supervised convolutional subspace clustering network ($S^2$ConvSCN) that incorporates the fully connected (FC) layer and, thus, it is capable for handling out-of-sample data by classifying them using a softmax classifier. $S^2$ConvSCN clusters data coming from nonlinear manifolds by learning the linea…
We propose a Classification Via Clustering (CVC) algorithm which enables existing clustering methods to be efficiently employed in classification problems. In CVC, training and test data are co-clustered and class-cluster distributions are used to find the label of the test data. To determine an efficient number of clusters, a Semi-supervised Hierarchical Clustering (SHC) algorithm is proposed. Clusters are obtained by hierarchically applying two-way NCut by using signs of the Fiedler vector of the normalized graph Laplacian. To this end, a Direct Fiedler Vector Computation algorithm is propos…
Convolutional networks are at the center of best-in-class computer vision applications for a wide assortment of undertakings. Since 2014, a profound amount of work began to make better convolutional architectures, yielding generous additions in different benchmarks. Albeit expanded model size and computational cost will, in general, mean prompt quality increases for most undertakings but, the architectures now need to have some additional information to increase the performance. I show evidence that with the amalgamation of content-based image similarity and deep learning models, we can provid…
Facebook AI（Facebook 人工智能研究院）；King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学）
Visual and audio modalities are highly correlated, yet they contain different information. Their strong correlation makes it possible to predict the semantics of one from the other with good accuracy. Their intrinsic differences make cross-modal prediction a potentially more rewarding pretext task for self-supervised learning of video and audio representations compared to within-modality learning. Based on this intuition, we propose Cross-Modal Deep Clustering (XDC), a novel self-supervised method that leverages unsupervised clustering in one modality (e.g., audio) as a supervisory signal for …
Imperial College London（帝国理工学院）；Fudan University（复旦大学）
This paper presents a novel method for face clustering in videos using a video-centralised transformer. Previous works often employed contrastive learning to learn frame-level representation and used average pooling to aggregate the features along the temporal dimension. This approach may not fully capture the complicated video dynamics. In addition, despite the recent progress in video-based contrastive learning, few have attempted to learn a self-supervised clustering-friendly face representation that benefits the video face clustering task. To overcome these limitations, our method employs …
Columbia University（哥伦比亚大学）；Recognition Technologies, Inc.（识别技术公司）
Majority of speech signals across different scenarios are never available with well-defined audio segments containing only a single speaker. A typical conversation between two speakers consists of segments where their voices overlap, interrupt each other or halt their speech in between multiple sentences. Recent advancements in diarization technology leverage neural network-based approaches to improvise multiple subsystems of speaker diarization system comprising of extracting segment-wise embedding features and detecting changes in the speaker during conversation. However, to identify speaker…
Auto-Encoder based deep subspace clustering (DSC) is widely used in computer vision, motion segmentation and image processing. However, it suffers from the following three issues in the self-expressive matrix learning process: the first one is less useful information for learning self-expressive weights due to the simple reconstruction loss; the second one is that the construction of the self-expression layer associated with the sample size requires high-computational cost; and the last one is the limited connectivity of the existing regularization terms. In order to address these issues, in t…
This paper proposes integrating semantics-oriented similarity representation into RankingMatch, a recently proposed semi-supervised learning method. Our method, dubbed ReRankMatch, aims to deal with the case in which labeled and unlabeled data share non-overlapping categories. ReRankMatch encourages the model to produce the similar image representations for the samples likely belonging to the same class. We evaluate our method on various datasets such as CIFAR-10, CIFAR-100, SVHN, STL-10, and Tiny ImageNet. We obtain promising results (4.21% error rate on CIFAR-10 with 4000 labels, 22.32% erro…
Learning a good representation for space-time correspondence is the key for various computer vision tasks, including tracking object bounding boxes and performing video object pixel segmentation. To learn generalizable representation for correspondence in large-scale, a variety of self-supervised pretext tasks are proposed to explicitly perform object-level or patch-level similarity learning. Instead of following the previous literature, we propose to learn correspondence using Video Frame-level Similarity (VFS) learning, i.e, simply learning from comparing video frames. Our work is inspired b…
The University of Sydney（悉尼大学）；Med-X Research Institute, Shanghai Jiao Tong University（上海交通大学Med-X研究院）
The segmentation of medical images is a fundamental step in automated clinical decision support systems. Existing medical image segmentation methods based on supervised deep learning, however, remain problematic because of their reliance on large amounts of labelled training data. Although medical imaging data repositories continue to expand, there has not been a commensurate increase in the amount of annotated data. Hence, we propose a new spatial guided self-supervised clustering network (SGSCN) for medical image segmentation, where we introduce multiple loss functions designed to aid in gro…
In this paper, we introduce 3D-CSL, a compact pipeline for Near-Duplicate Video Retrieval (NDVR), and explore a novel self-supervised learning strategy for video similarity learning. Most previous methods only extract video spatial features from frames separately and then design kinds of complex mechanisms to learn the temporal correlations among frame features. However, parts of spatiotemporal dependencies have already been lost. To address this, our 3D-CSL extracts global spatiotemporal dependencies in videos end-to-end with a 3D transformer and find a good balance between efficiency and eff…
Baidu Research（百度研究院）；National Engineering Laboratory of Deep Learning Technology and Application（深度学习技术及应用国家工程实验室）
The clustering of autonomous driving scenario data can substantially benefit the autonomous driving validation and simulation systems by improving the simulation tests' completeness and fidelity. This article proposes a comprehensive data clustering framework for a large set of vehicle driving data. Existing algorithms utilize handcrafted features whose quality relies on the judgments of human experts. Additionally, the related feature compression methods are not scalable for a large data-set. Our approach thoroughly considers the traffic elements, including both in-traffic agent objects and m…
Beijing University of Posts and Telecommunications（北京邮电大学）；University of California, Berkeley（加州大学伯克利分校）；Shenzhen Research Institute of Big Data（深圳大数据研究院）；Peking University（北京大学）
Subspace clustering methods based on data self-expression have become very popular for learning from data that lie in a union of low-dimensional linear subspaces. However, the applicability of subspace clustering has been limited because practical visual data in raw form do not necessarily lie in such linear subspaces. On the other hand, while Convolutional Neural Network (ConvNet) has been demonstrated to be a powerful tool for extracting discriminative features from visual data, training such a ConvNet usually requires a large amount of labeled data, which are unavailable in subspace cluster…
Self-supervised methods have significantly closed the gap with end-to-end supervised learning for image classification. In the case of human action videos, however, where both appearance and motion are significant factors of variation, this gap remains significant. One of the key reasons for this is that sampling pairs of similar video clips, a required step for many self-supervised contrastive learning methods, is currently done conservatively to avoid false positives. A typical assumption is that similar clips only occur temporally close within a single video, leading to insufficient example…
University of Electronic Science and Technology of China（电子科技大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））
Auto-Encoder (AE)-based deep subspace clustering (DSC) methods have achieved impressive performance due to the powerful representation extracted using deep neural networks while prioritizing categorical separability. However, self-reconstruction loss of an AE ignores rich useful relation information and might lead to indiscriminative representation, which inevitably degrades the clustering performance. It is also challenging to learn high-level similarity without feeding semantic labels. Another unsolved problem facing DSC is the huge memory cost due to $n\times n$ similarity matrix, which is …
University of Electronic Science and Technology of China（电子科技大学）；Southern Illinois University（南伊利诺伊大学）；University of Kentucky（肯塔基大学）
Spectral clustering has found extensive use in many areas. Most traditional spectral clustering algorithms work in three separate steps: similarity graph construction; continuous labels learning; discretizing the learned labels by k-means clustering. Such common practice has two potential flaws, which may lead to severe information loss and performance degradation. First, predefined similarity graph might not be optimal for subsequent clustering. It is well-accepted that similarity graph highly affects the clustering results. To this end, we propose to automatically learn similarity informatio…
Subspace Clustering on Incomplete Data with Self-Supervised Contrastive Learning
Department of Electrical Engineering, Biostatistics（电气工程与生物统计学系）；Wisconsin Institute of Discovery（威斯康星发现研究所）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
Rensselaer Polytechnic Institute（伦斯勒理工学院）；Fudan University（复旦大学）；Shanghai Center for Brain Science and Brain-Inspired Technology（上海脑科学与类脑研究中心）
The similarity among samples and the discrepancy between clusters are two crucial aspects of image clustering. However, current deep clustering methods suffer from the inaccurate estimation of either feature similarity or semantic discrepancy. In this paper, we present a Semantic Pseudo-labeling-based Image ClustEring (SPICE) framework, which divides the clustering network into a feature model for measuring the instance-level similarity and a clustering head for identifying the cluster-level discrepancy. We design two semantics-aware pseudo-labeling algorithms, prototype pseudo-labeling, and r…
