DeepAI AI Chat
Log In Sign Up

Beyond Triplet Loss: Person Re-identification with Fine-grained Difference-aware Pairwise Loss

by   Cheng Yan, et al.

Person Re-IDentification (ReID) aims at re-identifying persons from different viewpoints across multiple cameras. Capturing the fine-grained appearance differences is often the key to accurate person ReID, because many identities can be differentiated only when looking into these fine-grained differences. However, most state-of-the-art person ReID approaches, typically driven by a triplet loss, fail to effectively learn the fine-grained features as they are focused more on differentiating large appearance differences. To address this issue, we introduce a novel pairwise loss function that enables ReID models to learn the fine-grained features by adaptively enforcing an exponential penalization on the images of small differences and a bounded penalization on the images of large differences. The proposed loss is generic and can be used as a plugin to replace the triplet loss to significantly enhance different types of state-of-the-art approaches. Experimental results on four benchmark datasets show that the proposed loss substantially outperforms a number of popular loss functions by large margins; and it also enables significantly improved data efficiency.


page 1

page 4

page 6

page 8

page 11


Incorporating Intra-Class Variance to Fine-Grained Visual Recognition

Fine-grained visual recognition aims to capture discriminative character...

Triplet Online Instance Matching Loss for Person Re-identification

Mining the shared features of same identity in different scene, and the ...

MixFace: Improving Face Verification Focusing on Fine-grained Conditions

The performance of face recognition has become saturated for public benc...

Unified Multifaceted Feature Learning for Person Re-Identification

Person re-identification (ReID) aims at re-identifying persons from diff...

Learning Incremental Triplet Margin for Person Re-identification

Person re-identification (ReID) aims to match people across multiple non...

In Defense of the Triplet Loss for Visual Recognition

We employ triplet loss as a space embedding regularizer to boost classif...

Learning Lexico-Functional Patterns for First-Person Affect

Informal first-person narratives are a unique resource for computational...