Related papers: Style Variable and Irrelevant Learning for General…

In the current person Re-identification (ReID) methods, most domain generalization works focus on dealing with style differences between domains while largely ignoring unpredictable camera view change, which we identify as another major…

Multi-modal object Re-Identification (ReID) aims to exploit complementary information from different modalities to retrieve specific objects. However, existing methods often rely on hard token filtering or simple fusion strategies, which…

This paper considers the out-of-distribution (OOD) generalization problem under the setting that both style distribution shift and spurious features exist and domain labels are missing. This setting frequently arises in real-world…

Existing person re-identification (re-ID) research mainly focuses on pedestrian identity matching across cameras in adjacent areas. However, in reality, it is inevitable to face the problem of pedestrian identity matching across…

With the goal of directly generalizing trained model to unseen target domains, domain generalization (DG), a newly proposed learning paradigm, has attracted considerable attention. Previous DG models usually require a sufficient quantity of…

Visible-infrared person re-identification (VI-ReID) is a task of matching the same individuals across the visible and infrared modalities. Its main challenge lies in the modality gap caused by cameras operating on different spectra.…

Although existing person re-identification (Re-ID) methods have shown impressive accuracy, most of them usually suffer from poor generalization on unseen target domain. Thus, generalizable person Re-ID has recently drawn increasing…

Since human-labeled samples are free for the target set, unsupervised person re-identification (Re-ID) has attracted much attention in recent years, by additionally exploiting the source set. However, due to the differences on camera…

Visible-infrared person re-identification (ReID) aims to recognize a same person of interest across a network of RGB and IR cameras. Some deep learning (DL) models have directly incorporated both modalities to discriminate persons in a…

Large-scale foundation models like CLIP have shown strong zero-shot generalization but struggle with domain shifts, limiting their adaptability. In our work, we introduce \textsc{StyLIP}, a novel domain-agnostic prompt learning strategy for…

Class Incremental Learning (CIL) is challenging due to catastrophic forgetting. On top of that, Exemplar-free Class Incremental Learning is even more challenging due to forbidden access to previous task data. Recent exemplar-free CIL…

Deep learning models in medical image analysis often struggle with generalizability across domains and demographic groups due to data heterogeneity and scarcity. Traditional augmentation improves robustness, but fails under substantial…

Domain generalization (DG) intends to train a model on multiple source domains to ensure that it can generalize well to an arbitrary unseen target domain. The acquisition of domain-invariant representations is pivotal for DG as they possess…

State-of-the-art deep neural networks are still struggling to address the catastrophic forgetting problem in continual learning. In this paper, we propose one simple paradigm (named as S-Prompting) and two concrete approaches to highly…

Machine Unlearning is essential for large generative models (VAEs, DDPMs) to comply with the right to be forgotten and prevent undesired content generation without costly retraining. Existing approaches, such as Static-lambda SISS for…

Person Re-identification (ReID) is a critical computer vision task which aims to match the same person in images or video sequences. Most current works focus on settings where the resolution of images is kept the same. However, the…

Person re-identification (ReID) aims to retrieve images of a target person from the gallery set, with wide applications in medical rehabilitation and public security. However, traditional person ReID models are typically uni-modal,…

User identity linkage, which aims to link identities of a natural person across different social platforms, has attracted increasing research interest recently. Existing approaches usually first embed the identities as deterministic vectors…

Face anti-spoofing (FAS) based on domain generalization (DG) has been recently studied to improve the generalization on unseen scenarios. Previous methods typically rely on domain labels to align the distribution of each domain for learning…

Existing disentangled-based methods for generalizable person re-identification aim at directly disentangling person representations into domain-relevant interference and identity-relevant feature. However, they ignore that some crucial…