Research map / Label-efficient and robust learning / Recognition and long-tail
Hierarchical Concept Embedding & Pursuit for Interpretable Image Classification
Nghia Nguyen, Tianjiao Ding, René Vidal
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 |
|---|---|---|---|
| use hierarchical beam OMP instead of standard OMP (ablation) | HCEP · Synthetic hierarchy | support precision and recall | Improved |
| use HB-OMP instead of OMP/CBM/HNN | HCEP · CIFAR-100, ImageNette, ImageNet | support precision and recall | Improved |
| use HCEP with few shots per class | HCEP · ImageNet few-shot (12/25/50-shot) | classification accuracy | Improved |
| use HCEP vs baselines with full data | HCEP · CIFAR-100, ImageNette | classification accuracy | No clear effect |
| increase beam width from 1 to 32 (ablation) | HCEP · ImageNet 12-shot | support precision | Improved |
| replace CLIP with SigLIP (ablation) | HCEP · ImageNet | interpretability metrics | No clear effect |
Closest papers by meaning
- From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit (NeurIPS 2025 · similarity 0.89)
- Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE) (NeurIPS 2024 · similarity 0.87)
- Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures (NeurIPS 2026 · similarity 0.87)
- Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning (NeurIPS 2026 · similarity 0.86)
- ConceptBed: Evaluating Concept Learning Abilities of Text-to-Image Diffusion Models (AAAI 2024 · similarity 0.86)
- Cascaded Sparse Autoencoders LearnMulti-Level Visual Concepts in Multimodal LLMs (NeurIPS 2026 · similarity 0.86)
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.
