ANFI: Rethinking Neighbor Feature Interaction in Person Re-ID

In person re-identix001Ccation, neighbor-based methods haveachieved signix001Ccant success by interacting with neighbor samples to ob-tain more robust representations. However, existing methods rely onlyon ax001Enity relations, causing their success to depend heavily on the re-liability of selected neighbors. We x001Cnd that ax001Enity-only interaction of-ten fails in challenging scenarios due to the inevitable presence of noisyneighbors. To enable ex001Bective interactions under noisy neighborhoods, werevisit neighbor-based methods under distinct reliability conditions andpropose a novel Adaptive Neighbor Feature Interaction (ANFI)method. The core idea of ANFI is to account for negative ex001Bects fromnoisy neighbors, allowing samples to remain distinguishable from falsepositive neighbors. Unlike existing methods, ANFI models not only ax001En-ity relations but also discrepancy relations, and employs sample-wiseadaptive weighting for these two types of relations. Given that capturingnegative ex001Bects from noisy neighbors dix001Bers signix001Ccantly from traditionalrelation learning, we derive discrepancy relations from a new neighbor-hood similarity, which provides more information than pairwise sim-ilarity. In addition, we propose Noisy Relation Supervision (NRS)to train ANFI, gradually injecting robustness to noisy relations into themodel. Extensive experiments conducted under standard, cross-modal,and cross-domain settings, including comparisons with neighbor-basedmethods and re-ranking methods, demonstrate the superiority of ourmethod across various neighbor distributions.