Research map / Vision-language and multimodal / Human and embodied modeling
Rounded or Streamlined Head? Bridging Concept Bottleneck Models and Attribute-Described Object Parts
Yang Liu, Jiajin Zhang, Yaojun Hu, Bingguang Hao, Xin Cao, Yingda Xia, Danyang Tu, Shi Gu, Ling Zhang
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 cost aggregation module (ablation) | OA-CBM · CUB-200 (patch token) | top-1 accuracy: 33.8 -> 63.2 | Improved |
| add hierarchical clustering on top of cost aggregation (ablation) | OA-CBM · PartAttrImageNet (Pred-All) | h-IoU: 12.9 -> 35.7 | Improved |
| add hierarchical clustering on top of cost aggregation (ablation) | OA-CBM · PartAttrCUB (Pred-All) | h-IoU: 6.6 -> 20.8 | Improved |
| add hierarchical clustering on top of cost aggregation (ablation) | OA-CBM · CUB-200 and CIFAR-100 classification | accuracy: 63.2 -> 63.3 (CUB); 96.2 -> 96.1 (CIFAR-100) | No clear effect |
| add hierarchical clustering on top of cost aggregation (ablation) | OA-CBM · FOOD-101 and FLOWER classification | accuracy: 87.7 -> 87.3 (FOOD-101); 92.8 -> 91.8 (FLOWER) | Hurt |
| add hierarchical clustering without cost aggregation (ablation) | OA-CBM · CUB-200 (patch token) | top-1 accuracy: 33.8 -> 0.01 | Hurt |
| add object-aware clustering for Pred-All grounding (ablation) | OA-CBM · Oracle-Obj/Oracle-All grounding | h-IoU: identical with and without (e.g. 51.4 vs 51.4) | No clear effect |
| replace CLIP text encoder with Llama3 and add part-attribute concepts | OA-CBM · ImageNet (CLS token) | top-1 accuracy: 78.7 -> 83.1 vs DOT-CBM | Improved |
| use patch-token concept scores instead of CLS-token scores | CBMs · classification | accuracy | Hurt |
| use patch-guided hybrid scoring (CLS x sigmoid(patch)) | OA-CBM · CUB-200 | top-1 accuracy: 63.3 -> 80.6 vs patch-token | Improved |
| evaluate grounding with attributes removed (part-only) | CLIP and DINO baselines · PartAttr datasets | mIoU | Hurt |
Closest papers by meaning
- Object-Centric Concept-Bottlenecks (NeurIPS 2025 · similarity 0.91)
- VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance (NeurIPS 2024 · similarity 0.89)
- Coarse-to-Fine Concept Bottleneck Models (NeurIPS 2024 · similarity 0.89)
- V2C-CBM: Building Concept Bottlenecks with Vision-to-Concept Tokenizer (AAAI 2025 · similarity 0.88)
- Concepts Worth Having: Refining VLM-Guided Concept Bottleneck Models with Minimal Annotations (NeurIPS 2026 · similarity 0.88)
- Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models (CVPR 2025 · similarity 0.88)
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.
