Sparse Label Smoothing Regularization for Person Re-Identification

Abstract

Person re-identification (re-id) is a cross-camera retrieval task which establishes a correspondence between images of a person from multiple cameras. Deep Learning methods have been successfully applied to this problem and have achieved impressive results. However, these methods require a large amount of labeled training data. Currently labeled datasets in person re-id are limited in their scale and manual acquisition of such large-scale datasets from surveillance cameras is a tedious and labor-intensive task. In this paper, we propose a framework that performs intelligent data augmentation and assigns partial smoothing label to generated data. Our approach first exploits the clustering property of existing person re-id datasets to create groups of similar objects that model cross-view variations. Each group is then used to generate realistic images through adversarial training. Our aim is to emphasize feature similarity between generated samples and the original samples. Finally, we assign a non-uniform label distribution to the generated samples and define a regularized loss function for training. The proposed approach tackles two problems (1) how to efficiently use the generated data and (2) how to address the over-smoothness problem found in current regularization methods. Extensive experiments on four larges cale datasets show that our regularization method significantly improves the Re-ID accuracy compared to existing methods.

13 pages, 6 figures

References in corpus (15)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• In Defense of the Triplet Loss for Person Re-Identification
• Generative Adversarial Text to Image Synthesis
• A Discriminatively Learned CNN Embedding for Person Re-identification
• Random Erasing Data Augmentation
• Deep Transfer Learning for Person Re-identification
• Looking Beyond Appearances: Synthetic Training Data for Deep CNNs in Re-identification
• Clustering with Deep Learning: Taxonomy and New Methods
• Harmonious Attention Network for Person Re-Identification
• Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)
• Re-ID done right: towards good practices for person re-identification
• HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis
• Deep Linear Discriminant Analysis on Fisher Networks: A Hybrid Architecture for Person Re-identification
• Deep Co-attention based Comparators For Relative Representation Learning in Person Re-identification