Related papers: Deep Intra-Image Contrastive Learning for Weakly S…

Deep neural networks perform poorly on heavily class-imbalanced datasets. Given the promising performance of contrastive learning, we propose Rebalanced Siamese Contrastive Mining (ResCom) to tackle imbalanced recognition. Based on the…

Different from general object detection, moving infrared small target detection faces huge challenges due to tiny target size and weak background contrast.Currently, most existing methods are fully-supervised, heavily relying on a large…

The acquisition of large-scale, precisely labeled datasets for person re-identification (ReID) poses a significant challenge. Weakly supervised ReID has begun to address this issue, although its performance lags behind fully supervised…

Weakly supervised text-based person retrieval seeks to retrieve images of a target person using textual descriptions, without relying on identity annotations and is more challenging and practical. The primary challenge is the intra-class…

Graph representation learning plays a vital role in processing graph-structured data. However, prior arts on graph representation learning heavily rely on labeling information. To overcome this problem, inspired by the recent success of…

Unsupervised object discovery (UOD) refers to the task of discriminating the whole region of objects from the background within a scene without relying on labeled datasets, which benefits the task of bounding-box-level localization and…

Unsupervised visual representation learning has gained much attention from the computer vision community because of the recent achievement of contrastive learning. Most of the existing contrastive learning frameworks adopt the instance…

Recent self-supervised contrastive learning methods greatly benefit from the Siamese structure that aims at minimizing distances between positive pairs. For high performance Siamese representation learning, one of the keys is to design good…

Robotic detection of people in crowded and/or cluttered human-centered environments including hospitals, long-term care, stores and airports is challenging as people can become occluded by other people or objects, and deform due to…

Person Re-Identification (ReID) requires comparing two images of person captured under different conditions. Existing work based on neural networks often computes the similarity of feature maps from one single convolutional layer. In this…

Person re-identification (ReID) under occlusions is a challenging problem in video surveillance. Most of existing person ReID methods take advantage of local features to deal with occlusions. However, these methods usually independently…

Most multi-view clustering methods are limited by shallow models without sound nonlinear information perception capability, or fail to effectively exploit complementary information hidden in different views. To tackle these issues, we…

Person re-identification is vital for monitoring and tracking crowd movement to enhance public security. However, re-identification in the presence of occlusion substantially reduces the performance of existing systems and is a challenging…

Contrastive learning is commonly used as a method of self-supervised learning with the "anchor" and "positive" being two random augmentations of a given input image, and the "negative" is the set of all other images. However, the…

A recent popular approach to out-of-distribution (OOD) detection is based on a self-supervised learning technique referred to as contrastive learning. There are two main variants of contrastive learning, namely instance and class…

Weakly supervised semantic segmentation (WSSS) aims at learning a semantic segmentation model with only image-level tags. Despite intensive research on deep learning approaches over a decade, there is still a significant performance gap…

Deep learning techniques have achieved great success in remote sensing image change detection. Most of them are supervised techniques, which usually require large amounts of training data and are limited to a particular application.…

This paper presents a novel semantic scene change detection scheme with only weak supervision. A straightforward approach for this task is to train a semantic change detection network directly from a large-scale dataset in an end-to-end…

Recent advances in self-supervised learning have attracted significant attention from both machine learning and neuroscience. This is primarily because self-supervised methods do not require annotated supervisory information, making them…

Siamese-network-based self-supervised learning (SSL) suffers from slow convergence and instability in training. To alleviate this, we propose a framework to exploit intermediate self-supervisions in each stage of deep nets, called the…