arXiv Computer Vision
SAGE: Salient Factor Discovery and Generation with Visual Foundation Representations
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Machine Learning
Jul 8
Towards Interpretable Foundation Models for Retinal Fundus Images
arXiv:2603. 18846v3 Announce Type: replace-cross Abstract: Foundation models are used to extract transferable representations from large amounts of unlabeled data, typically via self-supervised learning (SSL).
arXiv Computer Vision
2d ago
Subtoken Vision Transformer for Fine-grained Recognition
arXiv:2607.09086v2 Announce Type: replace Abstract: We present Subtoken Vision Transformer (SubViT), a selective image tokenization method for fine-grained visual recognition. Standard Vision Transfo...
arXiv Machine Learning
Jul 24
Gradient Concentration, Not Weight Saliency, Explains Representation-Level Class Unlearning
arXiv:2607. 21353v1 Announce Type: new Abstract: Machine unlearning aims to remove the influence of specific training data while preserving model utility.
arXiv AI
Sep 2
ViTAMINS: An Empirical Study of Training Self-Supervised Vision Transformers with Synthetic Hard Negatives
ViTAMINS is a method that incorporates synthetic hard negatives into unsupervised vision transformer pretraining to enhance representation quality. The approach is evaluated on ImageNet and a range of downstream tasks—including transfer learning, image retrieval, copy detection, and image/video segmentation—showing significant performance gains. The synthetic negatives also lead to emergent properties, such as representations that encode explicit semantic information and act as strong classifiers, improving over baselines by up to 11.3%.
arXiv AI
Aug 24
StateSight: Benchmarking Latent Spatial-State Reconstruction in Vision-Language Models
StateSight is a new benchmark designed to isolate and evaluate the ability of vision‑language models to reconstruct latent spatial structure from a single image. It consists of three procedurally generated task families—cube‑net opposite‑face reasoning, occluded cube‑tower counting, and 4‑neighbor connected‑component counting—each with 300 deterministic prompts and exact‑match scoring. The benchmark also includes a companion dataset, StateSight‑Steps, with 900 image‑text examples and 3,600 intermediate visual states to aid analysis of reconstruction errors.
arXiv AI
Jun 12
Proto-LeakNet: Towards Signal-Leak Aware Attribution in Synthetic Human Face Imagery
arXiv:2511. 04260v3 Announce Type: replace-cross Abstract: The growing sophistication of synthetic image and deepfake generation models has turned source attribution and authenticity verification into a critical challenge for modern computer vision systems.