Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Ni, Zhenliang"'
Vanilla pixel-level classifiers for semantic segmentation are based on a certain paradigm, involving the inner product of fixed prototypes obtained from the training set and pixel features in the test image. This approach, however, encounters signifi
Externí odkaz:
http://arxiv.org/abs/2405.06525
Semantic segmentation is an important task for numerous applications but it is still quite challenging to achieve advanced performance with limited computational costs. In this paper, we present CGRSeg, an efficient yet competitive segmentation frame
Externí odkaz:
http://arxiv.org/abs/2405.06228
Knowledge distillation is an effective method for model compression. However, it is still a challenging topic to apply knowledge distillation to detection tasks. There are two key points resulting in poor distillation performance for detection tasks.
Externí odkaz:
http://arxiv.org/abs/2302.05637