With the increasing interest and rapid development of methods for Ultra-...
Existing knowledge distillation works for semantic segmentation mainly f...
Existing long-tailed classification (LT) methods only focus on tackling ...
Weakly supervised object detection (WSOD), which is an effective way to ...
The application of cross-dataset training in object detection tasks is
c...
Crowd counting aims to learn the crowd density distributions and estimat...
Adversarial training is the de facto most promising defense against
adve...
Despite their success for semantic segmentation, convolutional neural
ne...