Search Results for author: Lin Gu

Found 14 papers, 5 papers with code

Feature Normalized Knowledge Distillation for Image Classification

1 code implementation ECCV 2020 Kunran Xu, Lai Rui, Yishi Li, Lin Gu

From this perspective, we systematically analyze the distillation mechanism and demonstrate that the L2-norm of the feature in penultimate layer would be too large under the influence of label noise, and the temperature T in KD could be regarded as a correction factor for L2-norm to suppress the impact of noise.

Classification General Classification +2

Explainable Diabetic Retinopathy Detection and Retinal Image Generation

1 code implementation1 Jul 2021 Yuhao Niu, Lin Gu, Yitian Zhao, Feng Lu

Though deep learning has shown successful performance in classifying the label and severity stage of certain diseases, most of them give few explanations on how to make predictions.

Data Augmentation Diabetic Retinopathy Detection +2

Estimating and Improving Fairness with Adversarial Learning

no code implementations7 Mar 2021 Xiaoxiao Li, Ziteng Cui, Yifan Wu, Lin Gu, Tatsuya Harada

To tackle this issue, we propose an adversarial multi-task training strategy to simultaneously mitigate and detect bias in the deep learning-based medical image analysis system.

Fairness

Goal-Oriented Gaze Estimation for Zero-Shot Learning

1 code implementation CVPR 2021 Yang Liu, Lei Zhou, Xiao Bai, Yifei HUANG, Lin Gu, Jun Zhou, Tatsuya Harada

Therefore, we introduce a novel goal-oriented gaze estimation module (GEM) to improve the discriminative attribute localization based on the class-level attributes for ZSL.

Gaze Estimation Generalized Zero-Shot Learning

Beyond Triplet Loss: Person Re-identification with Fine-grained Difference-aware Pairwise Loss

no code implementations22 Sep 2020 Cheng Yan, Guansong Pang, Xiao Bai, Jun Zhou, Lin Gu

The proposed loss is generic and can be used as a plugin to replace the triplet loss to significantly enhance different types of state-of-the-art approaches.

Person Re-Identification

Information Bottleneck Constrained Latent Bidirectional Embedding for Zero-Shot Learning

1 code implementation16 Sep 2020 Yang Liu, Lei Zhou, Xiao Bai, Lin Gu, Tatsuya Harada, Jun Zhou

Though many ZSL methods rely on a direct mapping between the visual and the semantic space, the calibration deviation and hubness problem limit the generalization capability to unseen classes.

Zero-Shot Learning

Fixed Pattern Noise Reduction for Infrared Images Based on Cascade Residual Attention CNN

no code implementations22 Oct 2019 Juntao Guan, Rui Lai, Ai Xiong, Zesheng Liu, Lin Gu

Existing fixed pattern noise reduction (FPNR) methods are easily affected by the motion state of the scene and working condition of the image sensor, which leads to over smooth effects, ghosting artifacts as well as slow convergence rate.

Pathological Evidence Exploration in Deep Retinal Image Diagnosis

no code implementations6 Dec 2018 Yuhao Niu, Lin Gu, Feng Lu, Feifan Lv, Zongji Wang, Imari Sato, Zijian Zhang, Yangyan Xiao, Xunzhang Dai, Tingting Cheng

Inspired by Koch's Postulates, a well-known strategy in medical research to identify the property of pathogen, we define a pathological descriptor that can be extracted from the activated neurons of a diabetic retinopathy detector.

Medical Diagnosis

ShelfNet for Fast Semantic Segmentation

4 code implementations27 Nov 2018 Juntang Zhuang, Junlin Yang, Lin Gu, Nicha Dvornek

Compared with real-time segmentation models such as BiSeNet, our model achieves higher accuracy at comparable speed on the Cityscapes Dataset, enabling the application in speed-demanding tasks such as street-scene understanding for autonomous driving.

Autonomous Driving Real-Time Semantic Segmentation +1

Deeply Learned Filter Response Functions for Hyperspectral Reconstruction

no code implementations CVPR 2018 Shijie Nie, Lin Gu, Yinqiang Zheng, Antony Lam, Nobutaka Ono, Imari Sato

More interestingly, by considering physical restrictions in the design process, we are able to realize the deeply learned spectral response functions by using modern film filter production technologies, and thus construct data-inspired multispectral cameras for snapshot hyperspectral imaging.

From RGB to Spectrum for Natural Scenes via Manifold-Based Mapping

no code implementations ICCV 2017 Yan Jia, Yinqiang Zheng, Lin Gu, Art Subpa-Asa, Antony Lam, Yoichi Sato, Imari Sato

Spectral analysis of natural scenes can provide much more detailed information about the scene than an ordinary RGB camera.

Dimensionality Reduction

Virtual Blood Vessels in Complex Background using Stereo X-ray Images

no code implementations22 Sep 2017 Qiuyu Chen, Ryoma Bise, Lin Gu, Yinqiang Zheng, Imari Sato, Jenq-Neng Hwang, Nobuaki Imanishi, Sadakazu Aiso

We propose a fully automatic system to reconstruct and visualize 3D blood vessels in Augmented Reality (AR) system from stereo X-ray images with bones and body fat.

Stereo Matching Stereo Matching Hand

Learning to Boost Filamentary Structure Segmentation

no code implementations ICCV 2015 Lin Gu, Li Cheng

Step one of our approach centers on a data-driven latent classification tree model to detect the filamentary fragments.

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