no code implementations • 27 Mar 2024 • Hanxiao Zhang, Yifan Zhou, Guo-Hua Wang, Jianxin Wu
In particular, the issue of sparse compression exists in traditional CNN few-shot methods, which can only produce very few compressed models of different model sizes.
1 code implementation • 2 Mar 2023 • Guo-Hua Wang, Jianxin Wu
For 22% latency reduction, it surpasses previous methods by on average 7 percentage points on ImageNet-1k.
1 code implementation • 10 Feb 2023 • Guo-Hua Wang, Jiahao Li, Bin Li, Yan Lu
Both mask decay and residual representation learning greatly improve the RD performance of our scalable encoder.
1 code implementation • 15 Jun 2022 • Guo-Hua Wang, Bin-Bin Gao, Chengjie Wang
And most segmentation networks can be adapted to solve the CD problems with our MTF module.
Ranked #1 on Change Detection on PCD
no code implementations • 18 Feb 2022 • Guo-Hua Wang, Jianxin Wu
However, they lack theoretical support and cannot explain why predictions are good candidates for pseudo-labels in the deep learning paradigm.
no code implementations • 17 Feb 2022 • Kun Yi, Guo-Hua Wang, Jianxin Wu
It is easy to collect a dataset with noisy labels, but such noise makes networks overfit seriously and accuracies drop dramatically.
1 code implementation • CVPR 2023 • Guo-Hua Wang, Jianxin Wu
Previous methods mainly adopt filter-level pruning to accelerate networks with scarce training samples.
3 code implementations • 3 Nov 2020 • Guo-Hua Wang, Yifan Ge, Jianxin Wu
We argue that the teacher should give more freedom to the student feature's magnitude, and let the student pay more attention on mimicking the feature direction.
Ranked #1 on Knowledge Distillation on MS COCO (mAP metric)
1 code implementation • 21 Jan 2020 • Dongyun Liang, Guo-Hua Wang, Jing Nie, Binxu Zhai, Xiusen Gu
We propose a system named ROIBase that normalizes the text by the Chinese hierarchical administrative divisions.
1 code implementation • 9 Aug 2019 • Guo-Hua Wang, Jianxin Wu
In this paper, we propose a principled end-to-end framework named deep decipher (D2) for SSL.
no code implementations • 14 May 2019 • Dongyun Liang, Guo-Hua Wang, Jing Nie
Given the collection of timestamped web documents related to the evolving topic, timeline summarization (TS) highlights its most important events in the form of relevant summaries to represent the development of a topic over time.