Research map / Vision-language and multimodal / Human and embodied modeling
CFM: Language-aligned Concept Foundation Model for Vision
Kai Wittenmayer, Sukrut Rao, Amin Parchami-Araghi, Bernt Schiele, Jonas Fischer
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 |
|---|---|---|---|
| increase SAE dictionary size from 4k to 16k (ablation) | CFM · ImageNet / Places365 linear probe | accuracy: ImageNet 78.2 -> 78.6; Places 55.5 -> 56.0 | Improved |
| increase SAE dictionary size from 4k to 16k (ablation) | CFM · C2-Score | C2-Score: 0.488 -> 0.418 | Hurt |
| dictionary size 8k versus 4k and 16k (ablation) | CFM · Open-vocab segmentation avg | mIoU: 41.1 (4k), 41.3 (8k), 40.8 (16k) | Mixed |
| add AnyUp pixel-level upsampling of concept activations (ablation) | CFM · Open-vocab segmentation avg | mIoU: 41.3 -> 41.9 | Improved |
| replace opaque CLIP-DINOiser with interpretable CFM concept layer | open-vocab segmentation · Open-vocab segmentation avg | mIoU: 41.4 -> 41.3 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MaskCLIP — MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining (CVPR 2023) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Language Model as Visual Explainer (NeurIPS 2024 · similarity 0.89)
- ConceptBed: Evaluating Concept Learning Abilities of Text-to-Image Diffusion Models (AAAI 2024 · similarity 0.89)
- Explaining Domain Shifts in Language: Concept Erasing for Interpretable Image Classification (CVPR 2025 · similarity 0.88)
- Bridging the gap to real-world language-grounded visual concept learning (NeurIPS 2025 · similarity 0.88)
- Synthesize Diagnose and Optimize: Towards Fine-Grained Vision-Language Understanding (CVPR 2024 · similarity 0.88)
- Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: A Comprehensive Evaluation (ICLR 2026 · 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.
