Please see the repositories of our group Vision-and-Sensing Lab at Github
ICML 2025: Whitened CLIP as a Likelihood Surrogate of Images and Captions
Roy Betser, Meir-Yossef Levi, Guy Gilboa Proceedings of the 42nd International Conference on Machine Learning (ICML), 2025 Likelihood approximations for images are not trivial to compute and can be useful in many applications. We examine the use of Contrastive Language-Image Pre-training (CLIP) to assess the likelihood of images and captions. We introduce \textit{Whitened CLIP}, a […]
ICML 2025: The Double-Ellipsoid Geometry of CLIP
Meir Yossef Levi, Guy Gilboa Proceedings of the 42nd International Conference on Machine Learning (ICML), 2025 Contrastive Language-Image Pre-Training (CLIP) is highly instrumental in machine learning applications within a large variety of domains. We investigate the geometry of this embedding, which is still not well understood, and show that text and image reside on linearly […]
ICLR 2025: Manifold Induced Biases for Zero-shot and Few-shot Detection of Generated Images
Jonathan Brokman · Amit Giloni · Omer Hofman · Roman Vainshtein · Hisashi Kojima · Guy Gilboa, ICLR 2025 Abatract: Distinguishing between real and AI-generated images, commonly referred to as ‘image detection’, presents a timely and significant challenge. Despite extensive research in the (semi-)supervised regime, zero-shot and few-shot solutions have only recently emerged as promising […]
3DV 2025: Robustifying Point Cloud Networks by Refocusing
Meir Yossef Levi, Guy Gilboa International Conference on 3D Vision 2025 Arxiv
DXAI: Explaining Classification by Image Decomposition
Elnatan Kadar, Guy Gilboa arxiv preprint We propose a new way to explain and to visualize neural network classification through a decomposition-based explainable AI (DXAI). Instead of providing an explanation heatmap, our method yields a decomposition of the image into class-agnostic and class-distinct parts, with respect to the data and chosen classifier. Following a fundamental […]
Critical Points ++: An Agile Point Cloud Importance Measure for Robust Classification, Adversarial Defense and Explainable AI
Yossef Meir Levi, Guy Gilboa The ability to cope accurately and fast with Out-Of-Distribution (OOD) samples is crucial in real-world safety demanding applications. In this work we first study the interplay between critical points of 3D point clouds and OOD samples. Our findings are that common corruptions and outliers are often interpreted as critical points. […]
EPiC: Ensemble of Partial Point Clouds for Robust Classification, ICCV 2023
Meir Yossef Levi, Guy Gilboa Accepted to ICCV 2023. Robust point cloud classification is crucial for real-world applications, as consumer-type 3D sensors often yield partial and noisy data, degraded by various artifacts. In this work we propose a general ensemble framework, based on partial point cloud sampling. Each ensemble member is exposed to only partial […]
BASiS: Batch Aligned Spectral Embedding Space, CVPR 2023
Or Streicher, Ido Cohen, Guy Gilboa; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 10396-10405 CVPR Repository Arxiv preprint Graph is a highly generic and diverse representation, suitable for almost any data processing problem. Spectral graph theory has been shown to provide powerful algorithms, backed by solid linear algebra […]
Graph Laplacian for Semi-Supervised Learning, accepted to SSVM-2023
Or Streicher, Guy Gilboa, accepted to SSVM 2023 (oral) 9th International Conference, SSVM 2023, Santa Margherita di Pula, Italy, May 21–25, 2023, Proceedings, Springer LNCS 14009, pp. 250-262, 2023. Springer conference proceedings Arxiv preprint Abatract Semi-supervised learning is highly useful in common scenarios where labeled data is scarce but unlabeled data is abundant. The graph […]
Spectral Total Variation
Matlab code for spectral total variation filtering for grayscale and color images. Here a band-stop example is shown (removing selected bands of textures). Code for grayscale Spectral TV Code for color Spectral TV Run: demo_ss_freq_tv_texture.m or demo_specTV_color_orange.m Ref: G. Gilboa, “A total variation spectral framework for scale and texture analysis.” SIAM Journal on Imaging Sciences 7.4 […]
HoRA 3D Robust Features
See full details here. Based on MSc thesis of Guy Berdugo G. Berdugo, ”3D Correspondences By Local Feature Matching”, M.Sc. Thesis, Technion, 2017.
DROT 3D Multiple Camera Still and Motion Dataset
See full details here. DROT is a depth dataset created to test depth restoration, rectification and upsampling methods. D. Rotman and G. Gilboa, “A depth restoration occlusionless temporal dataset,” in International Conference on 3D Vision (3DV). IEEE, 2016.
Non-local Diffusion
Matlab code for non-local diffusion for image denoising. Run: demo_nl_diff.m Refs: [1] Gilboa, Guy, and Stanley Osher. “Nonlocal linear image regularization and supervised segmentation.” Multiscale Modeling & Simulation 6.2 (2007): 595-630. [2] Gilboa, Guy, and Stanley Osher. “Nonlocal operators with applications to image processing.” Multiscale Modeling & Simulation 7.3 (2008): 1005-1028.