تقرير
Region-Based Representations Revisited
| العنوان: | Region-Based Representations Revisited |
|---|---|
| المؤلفون: | Shlapentokh-Rothman, Michal, Blume, Ansel, Xiao, Yao, Wu, Yuqun, T V, Sethuraman, Tao, Heyi, Lee, Jae Yong, Torres, Wilfredo, Wang, Yu-Xiong, Hoiem, Derek |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition |
| الوصف: | We investigate whether region-based representations are effective for recognition. Regions were once a mainstay in recognition approaches, but pixel and patch-based features are now used almost exclusively. We show that recent class-agnostic segmenters like SAM can be effectively combined with strong unsupervised representations like DINOv2 and used for a wide variety of tasks, including semantic segmentation, object-based image retrieval, and multi-image analysis. Once the masks and features are extracted, these representations, even with linear decoders, enable competitive performance, making them well suited to applications that require custom queries. The compactness of the representation also makes it well-suited to video analysis and other problems requiring inference across many images. Comment: CVPR 2024 Camera Ready; website: https://regionreps.web.illinois.edu/ |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2402.02352 |
| رقم الأكسشن: | edsarx.2402.02352 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |