An Evaluation of Deep CNN Baselines for Scene-Independent Person Re-Identification

Abstract

In recent years, a variety of proposed methods based on deep convolutional neural networks (CNNs) have improved the state of the art for large-scale person re-identification (ReID). While a large number of optimizations and network improvements have been proposed, there has been relatively little evaluation of the influence of training data and baseline network architecture. In particular, it is usually assumed either that networks are trained on labeled data from the deployment location (scene-dependent), or else adapted with unlabeled data, both of which complicate system deployment. In this paper, we investigate the feasibility of achieving scene-independent person ReID by forming a large composite dataset for training. We present an in-depth comparison of several CNN baseline architectures for both scene-dependent and scene-independent ReID, across a range of training dataset sizes. We show that scene-independent ReID can produce leading-edge results, competitive with unsupervised domain adaption techniques. Finally, we introduce a new dataset for comparing within-camera and across-camera person ReID.

To be published in 2018 15th Conference on Computer and Robot Vision (CRV)

References in corpus (19)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
• In Defense of the Triplet Loss for Person Re-Identification
• Person Re-identification: Past, Present and Future
• Improving Person Re-identification by Attribute and Identity Learning
• A Discriminatively Learned CNN Embedding for Person Re-identification
• Random Erasing Data Augmentation
• Pedestrian Alignment Network for Large-scale Person Re-identification
• Deep Representation Learning with Part Loss for Person Re-Identification
• Person Re-Identification by Camera Correlation Aware Feature Augmentation
• Learning Deep Embeddings with Histogram Loss
• Deep Transfer Learning for Person Re-identification
• PersonNet: Person Re-identification with Deep Convolutional Neural Networks
• Looking Beyond Appearances: Synthetic Training Data for Deep CNNs in Re-identification
• Pose Invariant Embedding for Deep Person Re-identification
• Unsupervised Person Re-identification: Clustering and Fine-tuning
• SVDNet for Pedestrian Retrieval
• Person Re-Identification by Deep Joint Learning of Multi-Loss Classification