Search papers, labs, and topics across Lattice.
This paper introduces the Adaptive Neighbor Feature Interaction (ANFI) method for person re-identification, addressing the limitations of existing neighbor-based approaches that rely solely on affinity relations. By incorporating both affinity and discrepancy relations, ANFI effectively mitigates the negative impact of noisy neighbors through sample-wise adaptive weighting and a novel neighborhood similarity metric. Extensive experiments across multiple settings reveal that ANFI outperforms traditional methods, enhancing robustness in challenging scenarios where noise is prevalent.
Relying only on affinity can lead to failures in noisy environments, but ANFI's dual approach to neighbor interactions significantly boosts robustness in person re-ID tasks.
In person re-identification, neighbor-based methods have achieved significant success by interacting with neighbor samples to obtain more robust representations. However, existing methods rely only on affinity relations, causing their success to depend heavily on the reliability of selected neighbors. We find that affinity-only interaction often fails in challenging scenarios due to the inevitable presence of noisy neighbors. To enable effective interactions under noisy neighborhoods, we revisit neighbor-based methods under distinct reliability conditions and propose a novel Adaptive Neighbor Feature Interaction (ANFI) method. The core idea of ANFI is to account for negative effects from noisy neighbors, allowing samples to remain distinguishable from false positive neighbors. Unlike existing methods, ANFI models not only affinity relations but also discrepancy relations, and employs sample-wise adaptive weighting for these two types of relations. Given that capturing negative effects from noisy neighbors differs significantly from traditional relation learning, we derive discrepancy relations from a new neighborhood similarity, which provides more information than pairwise similarity. In addition, we propose Noisy Relation Supervision (NRS) to train ANFI, gradually injecting robustness to noisy relations into the model. Extensive experiments conducted under standard, cross-modal, and cross-domain settings, including comparisons with neighbor-based methods and re-ranking methods, demonstrate the superiority of our method across various neighbor distributions.
