Beyond Triplet Loss: Person Re-Identification With Fine-Grained Difference-Aware Pairwise Loss
Autor: | Changhong Liu, Cheng Yan, Jun Zhou, Xiao Bai, Guansong Pang, Ning Xin, Lin Gu |
---|---|
Rok vydání: | 2022 |
Předmět: |
business.industry
Computer science Pattern recognition Image processing 02 engineering and technology Function (mathematics) Computer Science Applications Exponential function Data efficiency Bounded function Signal Processing 0202 electrical engineering electronic engineering information engineering Media Technology Key (cryptography) Benchmark (computing) 020201 artificial intelligence & image processing Pairwise comparison Artificial intelligence Electrical and Electronic Engineering business |
Zdroj: | IEEE Transactions on Multimedia. 24:1665-1677 |
ISSN: | 1941-0077 1520-9210 |
Popis: | 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. |
Databáze: | OpenAIRE |
Externí odkaz: |