no code implementations • 13 Aug 2024 • Hongzhou Chen, Lianghua He, Yihang Liu, Longzhen Yang
To further explore the semantic consistency between visual and neural signals.
2 code implementations • 30 Jul 2024 • Changli Wu, Yihang Liu, Jiayi Ji, Yiwei Ma, Haowei Wang, Gen Luo, Henghui Ding, Xiaoshuai Sun, Rongrong Ji
3D Referring Expression Segmentation (3D-RES) is dedicated to segmenting a specific instance within a 3D space based on a natural language description.
no code implementations • 13 Dec 2023 • Yizhe Yang, Heyan Huang, Yihang Liu, Yang Gao
Knowledge-grounded dialogue is a task of generating an informative response based on both the dialogue history and external knowledge source.
no code implementations • 4 Dec 2023 • Yitao Peng, Lianghua He, Die Hu, Yihang Liu, Longzhen Yang, Shaohua Shang
Due to the unique multi-instance learning of medical images and the difficulty in identifying decision-making regions, many interpretability models that have been proposed still have problems of insufficient accuracy and interpretability in medical image disease diagnosis.
no code implementations • 12 Jan 2023 • Yitao Peng, Longzhen Yang, Yihang Liu, Lianghua He
Saliency methods generating visual explanatory maps representing the importance of image pixels for model classification is a popular technique for explaining neural network decisions.
no code implementations • 15 Oct 2022 • Yitao Peng, Yihang Liu, Longzhen Yang, Lianghua He
It decouples the inference and interpretation modules of a prototype-based network by avoiding the use of prototype activation to explain the network's decisions in order to simultaneously improve the accuracy and interpretability of the neural network.
no code implementations • 17 Jul 2022 • Yitao Peng, Longzhen Yang, Yihang Liu, Lianghua He
We applied the MDM method to the interpretable neural networks ProtoPNet and XProtoNet, which improved the performance of model in the explainable prototype search.
1 code implementation • 28 May 2022 • Longzhen Yang, Yihang Liu, Yitao Peng, Lianghua He
In this work, we will show that the inferior standard of accuracy draws from human annotations (leave-one-out) are not appropriate for machine-generated captions.