Towards Good Practices on Building Effective CNN Baseline Model for Person Re-identification

Abstract

Person re-identification is indeed a challenging visual recognition task due to the critical issues of human pose variation, human body occlusion, camera view variation, etc. To address this, most of the state-of-the-art approaches are proposed based on deep convolutional neural network (CNN), being leveraged by its strong feature learning power and classification boundary fitting capacity. Although the vital role towards person re-identification, how to build effective CNN baseline model has not been well studied yet. To answer this open question, we propose 3 good practices in this paper from the perspectives of adjusting CNN architecture and training procedure. In particular, they are adding batch normalization after the global pooling layer, executing identity categorization directly using only one fully-connected, and using Adam as optimizer. The extensive experiments on 3 widely-used benchmark datasets demonstrate that, our propositions essentially facilitate the CNN baseline model to achieve the state-of-the-art performance without any other high-level domain knowledge or low-level technical trick.

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Person Re-identification: Past, Present and Future
• Random Erasing Data Augmentation
• SVDNet for Pedestrian Retrieval
• Attention-Aware Compositional Network for Person Re-identification
• Camera Style Adaptation for Person Re-identification
• Divide and Fuse: A Re-ranking Approach for Person Re-identification

Cited by in corpus (6)

• 3D PersonVLAD: Learning Deep Global Representations for Video-based Person Re-identification
• Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training
• Unsupervised Few-shot Learning via Self-supervised Training
• Attention: A Big Surprise for Cross-Domain Person Re-Identification
• MAT: A simple yet strong baseline for identifying self-admitted technical debt
• Collaborative Attention Network for Person Re-identification