2 citations · 4 across the 4 of their papers we have counts for
4 papers
Learn from Balance: Rectifying Knowledge Transfer for Long-Tailed Scenarios
Xinlei Huang, Jialiang Tang, Xubin Zheng +3
Knowledge Distillation (KD) transfers knowledge from a large pre-trained teacher network to a compact and efficient student network, making it suitable for deployment on resource-l…
Salient Object Detection via Bounding-box Supervision
Mengqi He, Jing Zhang, Wenxin Yu
The success of fully supervised saliency detection models depends on a large number of pixel-wise labeling. In this paper, we work on bounding-box based weakly-supervised saliency…
A Comparative Analysis of Machine Learning and Grey Models
Gang He, Khwaja Mutahir Ahmad, Wenxin Yu +2
Artificial Intelligence (AI) has recently shown its capabilities for almost every field of life. Machine Learning, which is a subset of AI, is a `HOT' topic for researchers. Machin…
Revisiting the Loss Weight Adjustment in Object Detection
Wenxin Yu, Xueling Shen, Jiajie Hu +1
Object detection is a typical multi-task learning application, which optimizes classification and regression simultaneously. However, classification loss always dominates the multi…