Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
Foundation Model Priors Enhance Object Focus in Feature Space for Source-Free Object Detection
Sairam VCR, Rishabh Lalla, Aveen Dayal +4
Current state-of-the-art approaches in Source-Free Object Detection (SFOD) typically rely on Mean-Teacher self-labeling. However, domain shift often reduces the detector's ability…
cs.CV2024
On Evaluation of Vision Datasets and Models using Human Competency Frameworks
Rahul Ramachandran, Tejal Kulkarni, Charchit Sharma +2
Evaluating models and datasets in computer vision remains a challenging task, with most leaderboards relying solely on accuracy. While accuracy is a popular metric for model evalua…