SHIFT15M: Fashion-specific dataset for set-to-set matching with several distribution shifts

  • arXiv
  • accepted at CVPR2023 workshop on CVAFD

This paper addresses the problem of set-to-set matching, which involves matching two different sets of items based on some criteria, especially in the case of high-dimensional items like images. Although neural networks have been applied to solve this problem, most machine learning-based approaches assume that the training and test data follow the same distribution, which is not always true in real-world scenarios. To address this limitation, we introduce SHIFT15M, a dataset that can be used to evaluate set-to-set matching models when the distribution of data changes between training and testing. We conduct benchmark experiments that demonstrate the performance drop of naive methods due to distribution shift. Additionally, we provide software to handle the SHIFT15M dataset in a simple manner, with the URL for the software to be made available after publication of this manuscript. We believe proposed SHIFT15M dataset provide a valuable resource for evaluating set-to-set matching models under the distribution shift.

PyTorch Lightning GANs

nocotan/pytorch-lightning-gans - GitHub

Collection of PyTorch Lightning implementations of Generative Adversarial Network varieties presented in research papers.

Awesome Information Geometry

nocotan/awesome-information-geometry - GitHub

This repo is a collection of AWESOME things about information geometry, including papers, code, etc. Feel free to star and fork.