Search Results for author: Lianghua He

Found 16 papers, 9 papers with code

FeaInfNet: Diagnosis in Medical Image with Feature-Driven Inference and Visual Explanations

no code implementations4 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.

Mutually Guided Few-shot Learning for Relational Triple Extraction

1 code implementation23 Jun 2023 Chengmei Yang, Shuai Jiang, Bowei He, Chen Ma, Lianghua He

Specifically, our method consists of an entity-guided relation proto-decoder to classify the relations firstly and a relation-guided entity proto-decoder to extract entities based on the classified relations.

Cross-Domain Few-Shot Knowledge Graphs +1

Explainability of Speech Recognition Transformers via Gradient-based Attention Visualization

1 code implementation IEEE Transactions on Multimedia 2023 Tianli Sun, Haonan Chen, Guosheng Hu, Lianghua He, Cairong Zhao

In addition, we demonstrate the utilization of visualization result in three ways: (1) We visualize attention with respect to connectionist temporal classification (CTC) loss to train an ASR model with adversarial attention erasing regularization, which effectively decreases the word error rate (WER) of the model and improves its generalization capability.

Hierarchical Dynamic Masks for Visual Explanation of Neural Networks

no code implementations12 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.

SCConv: Spatial and Channel Reconstruction Convolution for Feature Redundancy

1 code implementation CVPR 2023 Jiafeng Li, Ying Wen, Lianghua He

The proposed SCConv consists of two units: spatial reconstruction unit (SRU) and channel reconstruction unit (CRU).

Decoupling Deep Learning for Interpretable Image Recognition

no code implementations15 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.

Decision Making

MDM: Multiple Dynamic Masks for Visual Explanation of Neural Networks

no code implementations17 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.


Variational Transformer: A Framework Beyond the Trade-off between Accuracy and Diversity for Image Captioning

1 code implementation28 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.

Image Captioning Retrieval +1

Revitalize Region Feature for Democratizing Video-Language Pre-training of Retrieval

2 code implementations15 Mar 2022 Guanyu Cai, Yixiao Ge, Binjie Zhang, Alex Jinpeng Wang, Rui Yan, Xudong Lin, Ying Shan, Lianghua He, XiaoHu Qie, Jianping Wu, Mike Zheng Shou

Recent dominant methods for video-language pre-training (VLP) learn transferable representations from the raw pixels in an end-to-end manner to achieve advanced performance on downstream video-language retrieval.

Question Answering Retrieval +4

Unsupervised Adaptive Semantic Segmentation with Local Lipschitz Constraint

no code implementations27 May 2021 Guanyu Cai, Lianghua He

In the first stage, we propose the local Lipschitzness regularization as the objective function to align different domains by exploiting intra-domain knowledge, which explores a promising direction for non-adversarial adaptive semantic segmentation.

Segmentation Self-Learning +2

Ask&Confirm: Active Detail Enriching for Cross-Modal Retrieval with Partial Query

1 code implementation ICCV 2021 Guanyu Cai, Jun Zhang, Xinyang Jiang, Yifei Gong, Lianghua He, Fufu Yu, Pai Peng, Xiaowei Guo, Feiyue Huang, Xing Sun

However, the performance of existing methods suffers in real life since the user is likely to provide an incomplete description of an image, which often leads to results filled with false positives that fit the incomplete description.

Cross-Modal Retrieval Image Retrieval +1

Segmenting Medical MRI via Recurrent Decoding Cell

1 code implementation21 Nov 2019 Ying Wen, Kai Xie, Lianghua He

The encoder-decoder networks are commonly used in medical image segmentation due to their remarkable performance in hierarchical feature fusion.

Image Segmentation Medical Image Segmentation +1

Adaptive Routing Between Capsules

no code implementations19 Nov 2019 Qiang Ren, Shaohua Shang, Lianghua He

Capsule network is the most recent exciting advancement in the deep learning field and represents positional information by stacking features into vectors.

Learning Smooth Representation for Unsupervised Domain Adaptation

1 code implementation26 May 2019 Guanyu Cai, Lianghua He, Mengchu Zhou, Hesham Alhumade, Die Hu

When constructing a deep end-to-end model, to ensure the effectiveness and stability of unsupervised domain adaptation, three critical factors are considered in our proposed optimization strategy, i. e., the sample amount of a target domain, dimension and batchsize of samples.

Unsupervised Domain Adaptation

Virtual Conditional Generative Adversarial Networks

1 code implementation25 Jan 2019 Haifeng Shi, Guanyu Cai, Yuqin Wang, Shaohua Shang, Lianghua He

All the generative paths share the same decoder network while in each path the decoder network is fed with a concatenation of a different pre-computed amplified one-hot vector and the inputted Gaussian noise.

Clustering Conditional Image Generation

Cannot find the paper you are looking for? You can Submit a new open access paper.