10 papers
Locality-Attending Vision Transformer
Sina Hajimiri, Farzad Beizaee, Fereshteh Shakeri +3
Vision transformers have demonstrated remarkable success in classification by leveraging global self-attention to capture long-range dependencies. However, this same mechanism can…
Test-Time Adaptation of Vision-Language Models for Open-Vocabulary Semantic Segmentation
Mehrdad Noori, David Osowiechi, Gustavo Adolfo Vargas Hakim +6
Recently, test-time adaptation has attracted wide interest in the context of vision-language models for image classification. However, to the best of our knowledge, the problem is…
REFLECT: Rectified Flows for Efficient Brain Anomaly Correction Transport
Farzad Beizaee, Sina Hajimiri, Ismail Ben Ayed +3
Unsupervised anomaly detection (UAD) in brain imaging is crucial for identifying pathologies without the need for labeled data. However, accurately localizing anomalies remains cha…
MAD-AD: Masked Diffusion for Unsupervised Brain Anomaly Detection
Farzad Beizaee, Gregory Lodygensky, Christian Desrosiers +1
Unsupervised anomaly detection in brain images is crucial for identifying injuries and pathologies without access to labels. However, the accurate localization of anomalies in medi…
SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds
Ali Bahri, Moslem Yazdanpanah, Sahar Dastani +6
Test-Time Training (TTT) has emerged as a promising solution to address distribution shifts in 3D point cloud classification. However, existing methods often rely on computationall…
Correcting Deviations from Normality: A Reformulated Diffusion Model for Multi-Class Unsupervised Anomaly Detection
Farzad Beizaee, Gregory A. Lodygensky, Christian Desrosiers +1
Recent advances in diffusion models have spurred research into their application for Reconstruction-based unsupervised anomaly detection. However, these methods may struggle with m…