Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Ji, Kangye"'
Segment Anything Model (SAM) struggles with segmenting objects in the open world, especially across diverse and dynamic domains. Continual segmentation (CS) is a potential technique to solve this issue, but a significant obstacle is the intractable b
Externí odkaz:
http://arxiv.org/abs/2412.05012
Continual learning(CL) is a useful technique to acquire dynamic knowledge continually. Although powerful cloud platforms can fully exert the ability of CL,e.g., customized recommendation systems, similar personalized requirements for edge devices are
Externí odkaz:
http://arxiv.org/abs/2407.10545
Sample selection is the most straightforward technique to combat label noise, aiming to distinguish mislabeled samples during training and avoid the degradation of the robustness of the model. In the workflow, $\textit{selecting possibly clean data}$
Externí odkaz:
http://arxiv.org/abs/2405.17137