2 citations · 4 across the 5 of their papers we have counts for
Showing 2023Show all
3 papers · 1 filter
cs.CV2023
Heterogeneous Generative Knowledge Distillation with Masked Image Modeling
Ziming Wang, Shumin Han, Xiaodi Wang +3
Small CNN-based models usually require transferring knowledge from a large model before they are deployed in computationally resource-limited edge devices. Masked image modeling (M…
cs.CV2023
GEM: Boost Simple Network for Glass Surface Segmentation via Vision Foundation Models
Jing Hao, Moyun Liu, Jinrong Yang +1
Detecting glass regions is a challenging task due to the inherent ambiguity in their transparency and reflective characteristics. Current solutions in this field remain rooted in c…
cs.CV2023
Language-aware Multiple Datasets Detection Pretraining for DETRs
Jing Hao, Song Chen, Xiaodi Wang +1
Pretraining on large-scale datasets can boost the performance of object detectors while the annotated datasets for object detection are hard to scale up due to the high labor cost.…