arXiv Machine Learning
DisParQ: Self-Supervised Part Concepts for Interpretable Vision Foundation Models
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Oct 2
Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes
arXiv:2610.02117v1 Announce Type: cross Abstract: On-policy self-distillation has recently emerged as an effective approach for improving language-model reasoning by supervising students with a froze...
arXiv Computer Vision
6d ago
RT-DETR-World: Transferring Rich LLM Semantics to Real-Time Open-Vocabulary Detection
arXiv:2610.09502v1 Announce Type: new Abstract: Open-vocabulary detection (OVD) recognizes categories unseen during training through textual category queries, yet achieving strong generalization with...
arXiv Computer Vision
Aug 28
SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models
SOCO is a new benchmark for Semantic Object Correspondence that introduces a taxonomy of correspondence types and provides consistent, functionally meaningful keypoint annotations across 100 categories and over 1M correspondence pairs. It also includes keypoint language descriptions, enabling evaluation of large vision‑language models and their fine‑grained part‑level understanding. Experiments show that vision foundation backbones encode strong semantic structure but transfer correspondences poorly across related categories, LVLMs excel at text‑prompted part localization but lag in visual‑reference matching, and correspondence performance predicts dense downstream tasks more strongly than ImageNet classification.
arXiv AI
Aug 24
CFM: Language-aligned Concept Foundation Model for Vision
The paper introduces CFM, a language‑aligned concept foundation model for vision that generates fine‑grained, human‑interpretable concepts with spatial grounding. By pairing CFM with a strong semantic foundation model, it provides explanations for downstream tasks such as classification, segmentation, and captioning. The authors also analyze local co‑occurrence of concepts to define relationships, improving concept naming and yielding richer explanations while maintaining competitive performance.
arXiv AI
Aug 11
Vision-Language Grounding as Bidirectional Concept Correspondence
arXiv:2608. 07886v1 Announce Type: cross Abstract: Vision-language grounding connects language to visual content, yet most existing formulations reduce grounding to a unidirectional localization problem: given a prespecified text phrase or category name, identify the corresponding image region.
Hugging Face Trending Papers
6d ago
RT-DETR-World: Transferring Rich LLM Semantics to Real-Time Open-Vocabulary Detection
Open-vocabulary detection (OVD) recognizes categories unseen during training through textual category queries, yet achieving strong generalization with real-time efficiency remains challenging. Beyond...