STFER uses LVLM-generated identity-consistent semantic text to drive visual token filtering and expert routing for improved any-time person re-identification under clothing changes and modality shifts.
Clothes-invariant feature learning by causal intervention for clothes-changing person re-identification
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
In cloth-changing person re-identification (CCReID), it is critical to learn clothes-invariant feature, which can provide discriminative ID features that remain robust against clothing changes. However, a spurious correlation currently limits existing ReID methods from effectively extracting these clothing-invariant features. This spurious correlation arises from clothing ownership: clothing is rarely shared across different identities, so models tend to memorize clothing cues for identity recognition, and this strategy generalizes poorly to unseen clothing. In this paper, we propose Causal Clothes-Invariant Learning (CCIL), which explicitly shifts CC-ReID from likelihood learning P (Y|X) to causal intervention learning P (Y|do(X)) to block the clothing shortcut. CCIL realizes this intervention through three modules: a Confounder Dictionary, an Intervention Module, and Disentangle Regularization. The causality-based modeling makes the entire model naturally clothes-invariant, effectively preventing the capture of spurious correlations in feature learning. Extensive experiments validate the effectiveness of CCIL. On PRCC and DeepChange datasets, CCIL achieves Rank-1 accuracies of 66.4% and 59.2%, outperforming state-of-the-art methods by 1.4 and 4.1 percentage points, respectively.
fields
cs.CV 4representative citing papers
DMDL debias modality cues at model and optimization levels via causal adjustment intervention and collaborative bias-free training to learn modality-invariant features for unsupervised VI-ReID.
AT-USTC, a 403k-image RGB/IR dataset covering six time-based ReID scenarios, and Uni-AT, a multi-scenario model, are proposed, with Uni-AT achieving 55.8% any-time Rank-1 on the new benchmark.
A survey of causal reasoning for video person re-identification that reviews DIR-ReID, identity-shuffle GANs, and causal transformers, but contains unverified performance claims.
citing papers explorer
-
Beyond Visual Cues: Semantic-Driven Token Filtering and Expert Routing for Anytime Person ReID
STFER uses LVLM-generated identity-consistent semantic text to drive visual token filtering and expert routing for improved any-time person re-identification under clothing changes and modality shifts.
-
Dual-level Modality Debiasing Learning for Unsupervised Visible-Infrared Person Re-Identification
DMDL debias modality cues at model and optimization levels via causal adjustment intervention and collaborative bias-free training to learn modality-invariant features for unsupervised VI-ReID.
-
Towards Anytime Retrieval: A Benchmark for Anytime Person Re-Identification
AT-USTC, a 403k-image RGB/IR dataset covering six time-based ReID scenarios, and Uni-AT, a multi-scenario model, are proposed, with Uni-AT achieving 55.8% any-time Rank-1 on the new benchmark.
-
Causality and "In-the-Wild" Video-Based Person Re-ID: A Survey
A survey of causal reasoning for video person re-identification that reviews DIR-ReID, identity-shuffle GANs, and causal transformers, but contains unverified performance claims.