Research map / Detection and segmentation / Open-set and few-shot detection
Tagger: Deep Unsupervised Perceptual Grouping
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 |
|---|---|---|---|
| Use TAG grouping with an FC model instead of FC Ladder | TextureMNIST2 with 50k labels · TextureMNIST2 test | top-2 classification error: 41.1 ± 0.2 -> 7.9 ± 0.3 | Helped |
| Use TAG grouping with an FC model instead of ConvNet | TextureMNIST2 with 50k labels · TextureMNIST2 test | top-2 classification error: 12.6 ± 0.4 -> 7.9 ± 0.3 | Helped |
| Use TAG grouping with an FC model instead of FC Ladder | TextureMNIST1 with 50k labels · TextureMNIST1 test | classification error: 7.2 ± 0.1 -> 4.0 ± 0.3 | Helped |
| Use TAG grouping with an FC model instead of ConvNet | TextureMNIST1 with 50k labels · TextureMNIST1 test | classification error: 3.9 ± 0.3 -> 4.0 ± 0.3 | No clear effect |
| Use TAG grouping with an FC model instead of FC Ladder | TextureMNIST1 with 1k labels · TextureMNIST1 test | classification error: 30.5 ± 0.5 -> 10.5 ± 0.9 | Helped |
| Use TAG grouping with an FC model instead of FC Ladder | TextureMNIST2 with 1k labels · TextureMNIST2 test | top-2 classification error: 68.5 ± 0.2 -> 24.9 ± 1.8 | Helped |
| Replace BatchNorm with LayerNorm (ablation) | Tagger · Shapes test | AMI: 0.79 ± 0.034 -> 0.97 ± 0.009 | Helped |
| Increase the number of inference iterations | Tagger · Shapes test | AMI: 0.58 -> 0.79 | Helped |
| Increase the number of inference iterations | Tagger · Shapes test | denoising cost: 0.094 -> 0.063 | Helped |
Closest papers by meaning
- Latent Noise Segmentation: How Neural Noise Leads to the Emergence of Segmentation and Grouping (ICML 2024 · similarity 0.88)
- Perceptual Group Tokenizer: Building Perception with Iterative Grouping (ICLR 2024 · similarity 0.87)
- Segment Anything without Supervision (NeurIPS 2024 · similarity 0.86)
- Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling (CVPR 2024 · similarity 0.86)
- Hierarchy-Agnostic Unsupervised Segmentation: Parsing Semantic Image Structure (NeurIPS 2024 · similarity 0.86)
- 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.