Research map / Detection and segmentation / Open-set and few-shot detection
Unsupervised Object Segmentation by Redrawing
Mickaël Chen, Thierry Artières, Ludovic Denoyer
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 information conservation loss (decode z from redrawn image) (ablation) | ReDO · training stability | non-trivial segmentation | Improved |
| redraw only a single region per iteration instead of all regions (ablation) | ReDO · training | meaningful masks | Improved |
| use Pyramid Pooling Module in mask network instead of standard residual network (ablation) | ReDO mask network · segmentation | mask quality | Improved |
| orthogonal initialization gain 0.8 vs 0.2 or 1.4 (ablation) | ReDO · training | success of training | Mixed |
| use self-attention in D and G (ablation) | ReDO · segmentation | mask quality | No clear effect |
| different ratio of discriminator to generator updates (ablation) | ReDO · training | mask quality | No clear effect |
| unsupervised ReDO vs supervised model with same architecture | supervised F · LFW | accuracy/IoU: 92% accuracy and 79% IoU matched by supervised with 50-60 labels | Mixed |
| train on fused Flowers+LFW without labels using Flowers hyperparameters | ReDO · Flowers+LFW | IoU: accuracy 0.856, IoU 0.691 | No clear effect |
Closest papers by meaning
- Object Segmentation Without Labels with Large-Scale Generative Models (ICML 2021 · similarity 0.87)
- Promising or Elusive? Unsupervised Object Segmentation from Real-world Single Images (NeurIPS 2022 · similarity 0.86)
- Benchmarking and Analysis of Unsupervised Object Segmentation from Real-World Single Images (IJCV 2024 · similarity 0.86)
- Learning to Segment via Cut-and-Paste (ECCV 2018 · similarity 0.85)
- Unsupervised Segmentation Incorporating Shape Prior via Generative Adversarial Networks (ICCV 2021 · similarity 0.85)
- unMORE: Unsupervised Multi-Object Segmentation via Center-Boundary Reasoning (ICML 2025 · similarity 0.85)
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.
