Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Kwon, Hyeongjun"'
Enhancing Source-Free Domain Adaptive Object Detection with Low-confidence Pseudo Label Distillation
Source-Free domain adaptive Object Detection (SFOD) is a promising strategy for deploying trained detectors to new, unlabeled domains without accessing source data, addressing significant concerns around data privacy and efficiency. Most SFOD methods
Externí odkaz:
http://arxiv.org/abs/2407.13524
Visual scenes are naturally organized in a hierarchy, where a coarse semantic is recursively comprised of several fine details. Exploring such a visual hierarchy is crucial to recognize the complex relations of visual elements, leading to a comprehen
Externí odkaz:
http://arxiv.org/abs/2404.00974
Given the inevitability of domain shifts during inference in real-world applications, test-time adaptation (TTA) is essential for model adaptation after deployment. However, the real-world scenario of continuously changing target distributions presen
Externí odkaz:
http://arxiv.org/abs/2311.05858
Recent DETR-based video grounding models have made the model directly predict moment timestamps without any hand-crafted components, such as a pre-defined proposal or non-maximum suppression, by learning moment queries. However, their input-agnostic
Externí odkaz:
http://arxiv.org/abs/2308.06947
Recent progress in deterministic prompt learning has become a promising alternative to various downstream vision tasks, enabling models to learn powerful visual representations with the help of pre-trained vision-language models. However, this approa
Externí odkaz:
http://arxiv.org/abs/2304.00779
We address the problem of few-shot semantic segmentation (FSS), which aims to segment novel class objects in a target image with a few annotated samples. Though recent advances have been made by incorporating prototype-based metric learning, existing
Externí odkaz:
http://arxiv.org/abs/2111.04982