Related papers: Revisiting Multi-Granularity Representation via Gr…
Graph representation learning has emerged as a powerful tool for preserving graph topology when mapping nodes to vector representations, enabling various downstream tasks such as node classification and community detection. However, most…
Person re-identification (re-id) aims to match the same person from images taken across multiple cameras. Most existing person re-id methods generally require a large amount of identity labeled data to act as discriminative guideline for…
This paper is concerned with contrastive learning (CL) for low-level image restoration and enhancement tasks. We propose a new label-efficient learning paradigm based on residuals, residual contrastive learning (RCL), and derive an…
The key challenge of unsupervised vehicle re-identification (Re-ID) is learning discriminative features from unlabelled vehicle images. Numerous methods using domain adaptation have achieved outstanding performance, but those methods still…
To tackle the challenge of vehicle re-identification (Re-ID) in complex lighting environments and diverse scenes, multi-spectral sources like visible and infrared information are taken into consideration due to their excellent complementary…
Unsupervised person re-identification (ReID) aims to train a feature extractor for identity retrieval without exploiting identity labels. Due to the blind trust in imperfect clustering results, the learning is inevitably misled by…
Existing public person Re-Identification~(ReID) datasets are small in modern terms because of labeling difficulty. Although unlabeled surveillance video is abundant and relatively easy to obtain, it is unclear how to leverage these footage…
Graph representation learning has attracted a surge of interest recently, whose target at learning discriminant embedding for each node in the graph. Most of these representation methods focus on supervised learning and heavily depend on…
Tremendous breakthroughs have been developed in Semi-Supervised Semantic Segmentation (S4) through contrastive learning. However, due to limited annotations, the guidance on unlabeled images is generated by the model itself, which…
Graph contrastive learning (GCL) has garnered significant attention recently since it learns complex structural information from graphs through self-supervised learning manner. However, prevalent GCL models may suffer from performance…
Although unsupervised person re-identification (Re-ID) has drawn increasing research attention recently, it remains challenging to learn discriminative features without annotations across disjoint camera views. In this paper, we address the…
This work focuses on unsupervised representation learning in person re-identification (ReID). Recent self-supervised contrastive learning methods learn invariance by maximizing the representation similarity between two augmented views of a…
Recently, graph-based semi-supervised learning and pseudo-labeling have gained attention due to their effectiveness in reducing the need for extensive data annotations. Pseudo-labeling uses predictions from unlabeled data to improve model…
Since annotating medical images for segmentation tasks commonly incurs expensive costs, it is highly desirable to design an annotation-efficient method to alleviate the annotation burden. Recently, contrastive learning has exhibited a great…
Despite their consistent performance improvements, cross-modal retrieval models (e.g., CLIP) show degraded performances with retrieving keys composed of fused image-text modality (e.g., Wikipedia pages with both images and text). To address…
Unsupervised cross-domain person re-identification (Re-ID) aims to adapt the information from the labelled source domain to an unlabelled target domain. Due to the lack of supervision in the target domain, it is crucial to identify the…
Vehicle re-identification (Re-ID) has become a popular research topic owing to its practicability in intelligent transportation systems. Vehicle Re-ID suffers the numerous challenges caused by drastic variation in illumination, occlusions,…
Person re-identification (re-ID) requires one to match images of the same person across camera views. As a more challenging task, semi-supervised re-ID tackles the problem that only a number of identities in training data are fully labeled,…
Generalizable vehicle re-identification (ReID) seeks to develop models that can adapt to unknown target domains without the need for additional fine-tuning or retraining. Previous works have mainly focused on extracting domain-invariant…
Person re-identification (re-ID) via 3D skeletons is an important emerging topic with many merits. Existing solutions rarely explore valuable body-component relations in skeletal structure or motion, and they typically lack the ability to…