Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification
arXiv:1711.07027
Abstract
Person re-identification (re-ID) models trained on one domain often fail to generalize well to another. In our attempt, we present a "learning via translation" framework. In the baseline, we translate the labeled images from source to target domain in an unsupervised manner. We then train re-ID models with the translated images by supervised methods. Yet, being an essential part of this framework, unsupervised image-image translation suffers from the information loss of source-domain labels during translation. Our motivation is two-fold. First, for each image, the discriminative cues contained in its ID label should be maintained after translation. Second, given the fact that two domains have entirely different persons, a translated image should be dissimilar to any of the target IDs. To this end, we propose to preserve two types of unsupervised similarities, 1) self-similarity of an image before and after translation, and 2) domain-dissimilarity of a translated source image and a target image. Both constraints are implemented in the similarity preserving generative adversarial network (SPGAN) which consists of an Siamese network and a CycleGAN. Through domain adaptation experiment, we show that images generated by SPGAN are more suitable for domain adaptation and yield consistent and competitive re-ID accuracy on two large-scale datasets.
Accepted in CVPR 2018
References in corpus (12)
- Learning Transferable Features with Deep Adaptation Networks
- Unsupervised Domain Adaptation by Backpropagation
- Deep Domain Confusion: Maximizing for Domain Invariance
- Person Re-identification: Past, Present and Future
- Random Erasing Data Augmentation
- DualGAN: Unsupervised Dual Learning for Image-to-Image Translation
- Domain-Adversarial Neural Networks
- Fast Patch-based Style Transfer of Arbitrary Style
- SVDNet for Pedestrian Retrieval
- Demystifying Neural Style Transfer
- Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks
- One-Sided Unsupervised Domain Mapping