Research map / Detection and segmentation / CNN features
Generative Hierarchical Learning of Sparse FRAME Models
Check 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 shiftable part-level deformations to sparse FRAME | Sparse FRAME · 12 clustering tasks | conditional purity: 0.928 -> 0.962 | Helped |
| add shiftable part-level deformations to sparse FRAME | Sparse FRAME · 12 clustering tasks | conditional entropy: 0.153 -> 0.083 | Helped |
| use hierarchical sparse FRAME instead of the baseline model | Animal face detection · Animal face detection (8 categories), average | object localization AUC: 0.785 -> 0.859 | Helped |
| use hierarchical sparse FRAME instead of the baseline model | Animal face detection · Animal face detection (8 categories), average | part localization AUC: 0.793 -> 0.868 | Helped |
| use hierarchical sparse FRAME instead of the baseline model | Animal face detection · Animal face detection (8 categories), average | key point localization AUC: 0.795 -> 0.867 | Helped |
| add moving parts to the hierarchical sparse FRAME model (ablation) | Hierarchical sparse FRAME · LHI-Animal-Faces, 20 categories, 5 clusters per category | classification accuracy: 70.62% -> 74.33% | Helped |
| add moving parts to the hierarchical sparse FRAME model (ablation) | Hierarchical sparse FRAME · LHI-Animal-Faces, 20 categories, 11 clusters per category | classification accuracy: 72.56% -> 75.83% | Helped |
Closest papers by meaning
- How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model (ICML 2024 · similarity 0.88)
- From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit (NeurIPS 2025 · similarity 0.84)
- A Unified Framework for Learning with Nonlinear Model Classes from Arbitrary Linear Samples (ICML 2024 · similarity 0.84)
- Generative Region-Language Pretraining for Open-Ended Object Detection (CVPR 2024 · similarity 0.84)
- Hierarchical Masked Autoregressive Models with Low-Resolution Token Pivots (ICML 2025 · similarity 0.83)
- SparseFormer: Sparse Visual Recognition via Limited Latent Tokens (ICLR 2024 · similarity 0.83)
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.