Related papers: Dynamic Clustering and Cluster Contrastive Learnin…
Unsupervised person re-ID is the task of identifying people on a target data set for which the ID labels are unavailable during training. In this paper, we propose to unify two trends in unsupervised person re-ID: clustering & fine-tuning…
Despite recent success, most contrastive self-supervised learning methods are domain-specific, relying heavily on data augmentation techniques that require knowledge about a particular domain, such as image cropping and rotation. To…
Graph contrastive learning (GCL) has been widely applied to text classification tasks due to its ability to generate self-supervised signals from unlabeled data, thus facilitating model training. However, existing GCL-based text…
Contrastive learning, a dominant self-supervised technique, emphasizes similarity in representations between augmentations of the same input and dissimilarity for different ones. Although low contrastive loss often correlates with high…
We present a discriminative clustering approach in which the feature representation can be learned from data and moreover leverage labeled data. Representation learning can give a similarity-based clustering method the ability to…
Unsupervised Deep Distance Metric Learning (UDML) aims to learn sample similarities in the embedding space from an unlabeled dataset. Traditional UDML methods usually use the triplet loss or pairwise loss which requires the mining of…
In the real world, long-tailed data distributions are prevalent, making it challenging for models to effectively learn and classify tail classes. However, we discover that in the field of drug chemistry, certain tail classes exhibit higher…
Existing contrastive learning methods rely on pairwise sample contrast $z_x^\top z_{x'}$ to learn data representations, but the learned features often lack clear interpretability from a human perspective. Theoretically, it lacks feature…
Contrastive learning (CL) methods effectively learn data representations in a self-supervision manner, where the encoder contrasts each positive sample over multiple negative samples via a one-vs-many softmax cross-entropy loss. By…
We introduce a novel self-supervised deep clustering approach tailored for unstructured data without requiring prior knowledge of the number of clusters, termed Adaptive Self-supervised Robust Clustering (ASRC). In particular, ASRC…
Deep clustering can optimize representations of instances (i.e., representation learning) and explore the inherent data distribution (i.e., clustering) simultaneously, which demonstrates a superior performance over conventional clustering…
For most unsupervised person re-identification (re-ID), people often adopt unsupervised domain adaptation (UDA) method. UDA often train on the labeled source dataset and evaluate on the target dataset, which often focuses on learning…
With various facial manipulation techniques arising, face forgery detection has drawn growing attention due to security concerns. Previous works always formulate face forgery detection as a classification problem based on cross-entropy…
Multi-view clustering has shown to be an effective method for analyzing underlying patterns in multi-view data. The performance of clustering can be improved by learning the consistency and complementarity between multi-view features,…
A persistent structural weakness in deep clustering is the disconnect between feature learning and cluster assignment. Most architectures invoke an external clustering step, typically k-means, to produce pseudo-labels that guide training,…
In this paper, we propose a one-stage online clustering method called Contrastive Clustering (CC) which explicitly performs the instance- and cluster-level contrastive learning. To be specific, for a given dataset, the positive and negative…
Label estimation is an important component in an unsupervised person re-identification (re-ID) system. This paper focuses on cross-camera label estimation, which can be subsequently used in feature learning to learn robust re-ID models.…
To facilitate the re-identification (re-ID) of individual animals, existing methods primarily focus on maximizing feature similarity within the same individual and enhancing distinctiveness between different individuals. However, most of…
Clustering-based methods, which alternate between the generation of pseudo labels and the optimization of the feature extraction network, play a dominant role in both unsupervised learning (USL) and unsupervised domain adaptive (UDA) person…
Graph-based collaborative filtering has been established as a prominent approach in recommendation systems, leveraging the inherent graph topology of user-item interactions to model high-order connectivity patterns and enhance…