papers

Publications (8)

cs.CV2025

COSTARR: Consolidated Open Set Technique with Attenuation for Robust Recognition

Ryan Rabinowitz, Steve Cruz, Walter Scheirer +1

Handling novelty remains a key challenge in visual recognition systems. Existing open-set recognition (OSR) methods rely on the familiarity hypothesis, detecting novelty by the abs…

cs.CV2024

COOOL: Challenge Of Out-Of-Label A Novel Benchmark for Autonomous Driving

Ali K. AlShami, Ananya Kalita, Ryan Rabinowitz +4

As the Computer Vision community rapidly develops and advances algorithms for autonomous driving systems, the goal of safer and more efficient autonomous transportation is becoming…

cs.LG2026

Adapting Feature Attenuation to NLP

Tianshuo Yang, Ryan Rabinowitz, Terrance E. Boult +1

Transformer classifiers such as BERT deliver impressive closed-set accuracy, yet they remain brittle when confronted with inputs from unseen categories--a common scenario for deplo…

cs.AI2026

AUTOPILOT VQA: Benchmarking Vision-Language Models for Incident-Centric Dashcam Understanding

Siddharth Damodharan, Radhika Gupta, Ali Alshami +2

Recent advances in Vision-Language Models, Large Language Models, and Multimodal Large Language Models have improved autonomous driving tasks such as scene understanding, decision…

cs.CV2025

2COOOL: 2nd Workshop on the Challenge Of Out-Of-Label Hazards in Autonomous Driving

Ali K. AlShami, Ryan Rabinowitz, Maged Shoman +9

As the computer vision community advances autonomous driving algorithms, integrating vision-based insights with sensor data remains essential for improving perception, decision mak…

cs.CV2025

GHOST: Gaussian Hypothesis Open-Set Technique

Ryan Rabinowitz, Steve Cruz, Manuel Günther +1

Evaluations of large-scale recognition methods typically focus on overall performance. While this approach is common, it often fails to provide insights into performance across ind…

cs.CV2022

Enhanced Performance of Pre-Trained Networks by Matched Augmentation Distributions

Touqeer Ahmad, Mohsen Jafarzadeh, Akshay Raj Dhamija +4

There exists a distribution discrepancy between training and testing, in the way images are fed to modern CNNs. Recent work tried to bridge this gap either by fine-tuning or re-tra…

cs.CV2025

SMART-Vision: Survey of Modern Action Recognition Techniques in Vision

Ali K. AlShami, Ryan Rabinowitz, Khang Lam +4

Human Action Recognition (HAR) is a challenging domain in computer vision, involving recognizing complex patterns by analyzing the spatiotemporal dynamics of individuals' movements…