no code implementations • 4 Mar 2024 • Feng Shuang, Wenbo He, Shaodong Li
To overcome these issues, we propose a 3D hand reconstruction network combining the benefits of model-based and model-free approaches to balance accuracy and physical plausibility for hand-object interaction scenario.
Ranked #3 on 3D Hand Pose Estimation on HO-3D
no code implementations • 6 Feb 2023 • Sajid Rahim, Kourosh Sabri, Anna Ells, Alan Wassyng, Mark Lawford, Linyang Chu, Wenbo He
This paper proposes the use of improved novel fundus preprocessing methods using pretrained transfer learning frameworks to create hybrid models to give higher diagnosis accuracy.
1 code implementation • 2 May 2022 • Yangdi Lu, Wenbo He
We look deeper into the memorization behavior in training with noisy labels and observe that the network outputs are reliable in the early stage.
no code implementations • 18 Aug 2021 • Yangdi Lu, Yang Bo, Wenbo He
Recent studies on the memorization effects of deep neural networks on noisy labels show that the networks first fit the correctly-labeled training samples before memorizing the mislabeled samples.
Ranked #28 on Image Classification on mini WebVision 1.0
no code implementations • 23 Mar 2021 • Yangdi Lu, Yang Bo, Wenbo He
We then update two networks simultaneously by selecting small-loss instances to minimize both unsupervised matching loss (i. e., measure the consistency of the two networks) and supervised classification loss (i. e. measure the classification performance).
no code implementations • 18 Mar 2021 • Yang Bo, Yangdi Lu, Wenbo He
Few-shot action recognition has attracted increasing attention due to the difficulty in acquiring the properly labelled training samples.