Research map / Image generation / GANs
BinGAN: Learning Compact Binary Descriptors with a Regularized GAN
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add DMR to BinGAN without regularizers (ablation) | BinGAN · Brown | average FPR@95%: 36.21 -> 31.90 | Helped |
| Add BRE to BinGAN with DMR (ablation) | BinGAN · Brown | average FPR@95%: 31.90 -> 30.76 | Helped |
| Add BRE without DMR (ablation) | BinGAN without regularizers · Brown | average FPR@95%: 36.21 -> 35.53 | Helped |
| Use BinGAN instead of DBD-MQ | Brown · Brown | average FPR@95%: 38.59 -> 30.76 | Helped |
Closest papers by meaning
- Binary Generative Adversarial Networks for Image Retrieval (AAAI 2018 · similarity 0.90)
- Improving GAN with Neighbors Embedding and Gradient Matching (AAAI 2019 · similarity 0.88)
- Improving GAN Training via Binarized Representation Entropy (BRE) Regularization (ICLR 2018 · similarity 0.88)
- Stabilizing Training of Generative Adversarial Networks through Regularization (NeurIPS 2017 · similarity 0.88)
- On gradient regularizers for MMD GANs (NeurIPS 2018 · similarity 0.87)
- Improving Generalization and Stability of Generative Adversarial Networks (ICLR 2019 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.