Semantics-Aligned Representation Learning for Person Re-identification
arXiv:1905.13143
Abstract
Person re-identification (reID) aims to match person images to retrieve the ones with the same identity. This is a challenging task, as the images to be matched are generally semantically misaligned due to the diversity of human poses and capture viewpoints, incompleteness of the visible bodies (due to occlusion), etc. In this paper, we propose a framework that drives the reID network to learn semantics-aligned feature representation through delicate supervision designs. Specifically, we build a Semantics Aligning Network (SAN) which consists of a base network as encoder (SA-Enc) for re-ID, and a decoder (SA-Dec) for reconstructing/regressing the densely semantics aligned full texture image. We jointly train the SAN under the supervisions of person re-identification and aligned texture generation. Moreover, at the decoder, besides the reconstruction loss, we add Triplet ReID constraints over the feature maps as the perceptual losses. The decoder is discarded in the inference and thus our scheme is computationally efficient. Ablation studies demonstrate the effectiveness of our design. We achieve the state-of-the-art performances on the benchmark datasets CUHK03, Market1501, MSMT17, and the partial person reID dataset Partial REID. Code for our proposed method is available at: https://github.com/microsoft/Semantics-Aligned-Representation-Learning-for-Person-Re-identification.
arXiv commentThirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20), code has been released
References in corpus (18)
- Adam: A Method for Stochastic Optimization
- Learning from Synthetic Humans
- Improving Person Re-identification by Attribute and Identity Learning
- Random Erasing Data Augmentation
- Deep Representation Learning with Part Loss for Person Re-Identification
- AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
- GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
- FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification
- Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro
- Pose Invariant Embedding for Deep Person Re-identification
- Re-ID done right: towards good practices for person re-identification
- Recognizing Partial Biometric Patterns
- Attention-Aware Compositional Network for Person Re-identification
- Deep-Person: Learning Discriminative Deep Features for Person Re-Identification
- A Siamese Long Short-Term Memory Architecture for Human Re-Identification
- MaskReID: A Mask Based Deep Ranking Neural Network for Person Re-identification
- DenseBody: Directly Regressing Dense 3D Human Pose and Shape From a Single Color Image
- Re-Identification Supervised Texture Generation