[논문 리뷰] Bag of Tricks and A Strong Baseline for Deep Person Re-identification

Hao Luo, Youzhi Gu외 3명|arXiv (Cornell University)|2019. 03. 17.

Video Surveillance and Tracking Methods참고 문헌 27인용 수 121

한 줄 요약

본 논문은 person re-identification을 위한 강력한 글로벌 피처 기반선 구축을 위해 일련의 학습 트릭을 모으고 평가하며, Market1501에서 ResNet50을 사용해 최첨단 결과를 달성하고 BNNeck 및 기타 개선을 활용해 DukeMTMC-reID에서도 경쟁력 있는 성능을 보인다.

ABSTRACT

This paper explores a simple and efficient baseline for person re-identification (ReID). Person re-identification (ReID) with deep neural networks has made progress and achieved high performance in recent years. However, many state-of-the-arts methods design complex network structure and concatenate multi-branch features. In the literature, some effective training tricks are briefly appeared in several papers or source codes. This paper will collect and evaluate these effective training tricks in person ReID. By combining these tricks together, the model achieves 94.5% rank-1 and 85.9% mAP on Market1501 with only using global features. Our codes and models are available at https://github.com/michuanhaohao/reid-strong-baseline.

연구 동기 및 목표

• Survey and consolidate effective training tricks used in person ReID.
• Build a strong, simple baseline based on global features without extra local-branch features.
• Quantitatively evaluate the impact of each trick on standard datasets.
• Provide a reference for fair comparison and practical baseline for industry applications.

제안 방법

• Adopts a standard ResNet50 baseline with a global feature extractor.
• Introduces six tricks: warmup learning rate, Random Erasing Augmentation (REA), label smoothing, last-stride modification (stride=1), BNNeck, and center loss.
• Designs BNNeck to separate ID loss and triplet loss optimization by using a BN layer after feature extraction.
• Evaluates effects of tricks through ablation on Market1501 and DukeMTMC-reID, including cross-domain tests.
• Compares to state-of-the-art methods using only global features.
• Explores supplementary factors like batch size and image size on performance.

실험 결과

연구 질문

• RQ1 What is the performance gain from each training trick when added to a standard ReID baseline?
• RQ2 Can a strong baseline using only global features outperform methods that rely on multiple local features?
• RQ3 How do image size and batch size influence ReID performance, and how does BNNeck affect optimization dynamics?
• RQ4 Do training tricks transfer well across-domain (cross-domain) ReID scenarios?

주요 결과

모델	r = 1	mAP	r = 1	mAP
Baseline-S	87.7	74.0	79.7	63.7
+warmup	88.7	75.2	80.6	65.1
+REA	91.3	79.3	81.5	68.3
+LS	91.4	80.3	82.4	69.3
+stride=1	92.0	81.7	82.6	70.6
+BNNeck	94.1	85.7	86.2	75.9
+center loss	94.5	85.9	86.4	76.4

• A strong baseline with the six tricks achieves 94.5% rank-1 and 85.9% mAP on Market1501 using only global features.
• BNNeck provides the largest single-model improvement, especially on DukeMTMC-reID.
• Cross-domain results show warmup, label smoothing, and BNNeck significantly boost performance, while Random Erasing can hurt cross-domain performance.
• Compared to many state-of-the-art methods, global-feature baselines with these tricks can match or exceed performance, and with re-ranking (RK) can reach higher mAP and rank-1 scores.
• Increasing batch size and exploring image size have nuanced effects, with larger batch sizes generally helping hard-positive/negative mining and image size showing comparable performance across tested configurations.