Weakly Supervised Person Re-ID: Differentiable Graphical Learning and A New Benchmark

Abstract

Person re-identification (Re-ID) benefits greatly from the accurate annotations of existing datasets (e.g., CUHK03 [1] and Market-1501 [2]), which are quite expensive because each image in these datasets has to be assigned with a proper label. In this work, we ease the annotation of Re-ID by replacing the accurate annotation with inaccurate annotation, i.e., we group the images into bags in terms of time and assign a bag-level label for each bag. This greatly reduces the annotation effort and leads to the creation of a large-scale Re-ID benchmark called SYSU-30$k$. The new benchmark contains $30k$ individuals, which is about $20$ times larger than CUHK03 ($1.3k$ individuals) and Market-1501 ($1.5k$ individuals), and $30$ times larger than ImageNet ($1k$ categories). It sums up to 29,606,918 images. Learning a Re-ID model with bag-level annotation is called the weakly supervised Re-ID problem. To solve this problem, we introduce a differentiable graphical model to capture the dependencies from all images in a bag and generate a reliable pseudo label for each person image. The pseudo label is further used to supervise the learning of the Re-ID model. When compared with the fully supervised Re-ID models, our method achieves state-of-the-art performance on SYSU-30$k$ and other datasets. The code, dataset, and pretrained model will be available at \url{https://github.com/wanggrun/SYSU-30k}.

arXiv commentAccepted by TNNLS 2020

References in corpus (17)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• In Defense of the Triplet Loss for Person Re-Identification
• Person Re-identification: Past, Present and Future
• A Discriminatively Learned CNN Embedding for Person Re-identification
• Random Erasing Data Augmentation
• Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning
• GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
• Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
• Unsupervised Person Re-identification by Deep Asymmetric Metric Embedding
• Cross-Domain Visual Matching via Generalized Similarity Measure and Feature Learning
• BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
• Re-ranking Person Re-identification with k-reciprocal Encoding
• Weakly- and Semi-Supervised Object Detection with Expectation-Maximization Algorithm
• Segmentation from Natural Language Expressions
• M2M-GAN: Many-to-Many Generative Adversarial Transfer Learning for Person Re-Identification
• Occluded Person Re-identification
• Discovering Underlying Person Structure Pattern with Relative Local Distance for Person Re-identification

Cited by in corpus (2)

• Learning Person Re-identification Models from Videos with Weak Supervision
• Weakly Supervised Tracklet Person Re-Identification by Deep Feature-wise Mutual Learning