9 papers
SpurCon: Weighted Supervised Contrastive Learning for Mitigating Spurious Cues in Medical Imaging
Shenhav Nadir, Meir Yossef Levi, Eyal Gofer +1
Despite the rapid progress of deep neural networks in visual recognition, their adoption in high-risk medical applications remains limited due to reliability and robustness concern…
A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIP
Hodaya Krakover, Meir Yossef Levi, Eyal Gofer +1
Adversarial attacks pose a challenge to the reliability of deep learning models, motivating effective detection methods. Existing techniques often rely on attack-specific assumptio…
InfoNCE Induces Gaussian Distribution
Roy Betser, Eyal Gofer, Meir Yossef Levi +1
Contrastive learning has become a cornerstone of modern representation learning, allowing training with massive unlabeled data for both task-specific and general (foundation) model…
The Universal Normal Embedding
Chen Tasker, Roy Betser, Eyal Gofer +2
Generative models and vision encoders have largely advanced on separate tracks, optimized for different goals and grounded in different mathematical principles. Yet, they share a f…
Training-free Detection of Generated Videos via Spatial-Temporal Likelihoods
Omer Ben Hayun, Roy Betser, Meir Yossef Levi +2
Following major advances in text and image generation, the video domain has surged, producing highly realistic and controllable sequences. Along with this progress, these models al…
Make it SING: Analyzing Semantic Invariants in Classifiers
Harel Yadid, Meir Yossef Levi, Roy Betser +1
All classifiers, including state-of-the-art vision models, possess invariants, partially rooted in the geometry of their linear mappings. These invariants, which reside in the null…