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.
no code implementations • 23 Apr 2024 • Jiahe Li, Jiawei Zhang, Xiao Bai, Jin Zheng, Xin Ning, Jun Zhou, Lin Gu
Leveraging the point-based Gaussian Splatting, facial motions can be represented in our method by applying smooth and continuous deformations to persistent Gaussian primitives, without requiring to learn the difficult appearance change like previous methods.
no code implementations • 14 Apr 2024 • Chih-Ling Chang, Fu-Jen Tsai, Zi-Ling Huang, Lin Gu, Chia-Wen Lin
Image dehazing faces challenges when dealing with hazy images in real-world scenarios.
1 code implementation • 14 Mar 2024 • Linwei Chen, Lin Gu, Ying Fu
While positively correlated with the proposed aliasing score, three types of hard pixels exhibit different patterns.
1 code implementation • 12 Mar 2024 • Jiawei Zhang, Jiahe Li, Lei Huang, Xiaohan Yu, Lin Gu, Jin Zheng, Xiao Bai
With advancements in domain generalized stereo matching networks, models pre-trained on synthetic data demonstrate strong robustness to unseen domains.
1 code implementation • 11 Mar 2024 • Jiahe Li, Jiawei Zhang, Xiao Bai, Jin Zheng, Xin Ning, Jun Zhou, Lin Gu
Our motivation stems from the highly efficient representation and surprising quality of the recent 3D Gaussian Splatting, despite it will encounter a geometry degradation when input views decrease.
1 code implementation • 8 Mar 2024 • Linwei Chen, Lin Gu, Ying Fu
Dilated convolution, which expands the receptive field by inserting gaps between its consecutive elements, is widely employed in computer vision.
no code implementations • 15 Dec 2023 • Kazuma Kobayashi, Yasuyuki Takamizawa, Mototaka Miyake, Sono Ito, Lin Gu, Tatsuya Nakatsuka, Yu Akagi, Tatsuya Harada, Yukihide Kanemitsu, Ryuji Hamamoto
We hypothesize that superior attention maps should align with the information that physicians focus on, potentially reducing prediction uncertainty and increasing model reliability.
1 code implementation • 14 Dec 2023 • Ziteng Cui, Lin Gu, Xiao Sun, Xianzheng Ma, Yu Qiao, Tatsuya Harada
The standard Neural Radiance Fields (NeRF) paradigm employs a viewer-centered methodology, entangling the aspects of illumination and material reflectance into emission solely from 3D points.
no code implementations • 6 Sep 2023 • Mengliang Zhang, Xinyue Hu, Lin Gu, Liangchen Liu, Kazuma Kobayashi, Tatsuya Harada, Ronald M. Summers, Yingying Zhu
In this paper, we re-extract disease labels from CXR reports to make them more realistic by considering disease severity and uncertainty in classification.
no code implementations • 17 Aug 2023 • Zhiming Wang, Lin Gu, Feng Lu
Our method also achieves an accuracy of 74. 84% on the task of recognizing low-resolution facial expressions, surpassing the current state-of-the-art FMD by 9. 48%.
1 code implementation • 22 Jul 2023 • Xinyue Hu, Lin Gu, Qiyuan An, Mengliang Zhang, Liangchen Liu, Kazuma Kobayashi, Tatsuya Harada, Ronald M. Summers, Yingying Zhu
Given a pair of main and reference images, this task attempts to answer several questions on both diseases and, more importantly, the differences between them.
1 code implementation • ICCV 2023 • Jiahe Li, Jiawei Zhang, Xiao Bai, Jun Zhou, Lin Gu
This paper presents ER-NeRF, a novel conditional Neural Radiance Fields (NeRF) based architecture for talking portrait synthesis that can concurrently achieve fast convergence, real-time rendering, and state-of-the-art performance with small model size.
1 code implementation • 10 Mar 2023 • Ziteng Cui, Lin Gu, Xiao Sun, Xianzheng Ma, Yu Qiao, Tatsuya Harada
Common capture low-light scenes are challenging for most computer vision techniques, including Neural Radiance Fields (NeRF).
1 code implementation • 7 Mar 2023 • Kazuma Kobayashi, Lin Gu, Ryuichiro Hataya, Takaaki Mizuno, Mototaka Miyake, Hirokazu Watanabe, Masamichi Takahashi, Yasuyuki Takamizawa, Yukihiro Yoshida, Satoshi Nakamura, Nobuji Kouno, Amina Bolatkan, Yusuke Kurose, Tatsuya Harada, Ryuji Hamamoto
As a result, our SBMIR system enabled users to overcome previous challenges, including image retrieval based on fine-grained image characteristics, image retrieval without example images, and image retrieval for isolated samples.
no code implementations • 19 Feb 2023 • Xinyue Hu, Lin Gu, Kazuma Kobayashi, Qiyuan An, Qingyu Chen, Zhiyong Lu, Chang Su, Tatsuya Harada, Yingying Zhu
Medical visual question answering (VQA) aims to answer clinically relevant questions regarding input medical images.
1 code implementation • ICCV 2023 • Shenghan Su, Lin Gu, Yue Yang, Zenghui Zhang, Tatsuya Harada
Besides, our colour quantisation method also offers an efficient quantisation method that effectively compresses the image storage while maintaining high performance in high-level recognition tasks such as classification and detection.
1 code implementation • 31 Oct 2022 • Ruichen Yao, Ziteng Cui, Xiaoxiao Li, Lin Gu
Fairness is a fundamental requirement for trustworthy and human-centered Artificial Intelligence (AI) system.
no code implementations • 13 Aug 2022 • Xinyue Hu, Lin Gu, Liangchen Liu, Ruijiang Li, Chang Su, Tatsuya Harada, Yingying Zhu
Existing video domain adaption (DA) methods need to store all temporal combinations of video frames or pair the source and target videos, which are memory cost expensive and can't scale up to long videos.
1 code implementation • 5 Aug 2022 • Ziteng Cui, Yingying Zhu, Lin Gu, Guo-Jun Qi, Xiaoxiao Li, Renrui Zhang, Zenghui Zhang, Tatsuya Harada
Image restoration algorithms such as super resolution (SR) are indispensable pre-processing modules for object detection in low quality images.
no code implementations • 4 Aug 2022 • Zhenqiang Li, Lin Gu, Weimin WANG, Ryosuke Nakamura, Yoichi Sato
Automated video-based assessment of surgical skills is a promising task in assisting young surgical trainees, especially in poor-resource areas.
1 code implementation • 30 May 2022 • Ziteng Cui, Kunchang Li, Lin Gu, Shenghan Su, Peng Gao, Zhengkai Jiang, Yu Qiao, Tatsuya Harada
Challenging illumination conditions (low-light, under-exposure and over-exposure) in the real world not only cast an unpleasant visual appearance but also taint the computer vision tasks.
Ranked #2 on Image Enhancement on Exposure-Errors
2 code implementations • ICCV 2021 • Ziteng Cui, Guo-Jun Qi, Lin Gu, ShaoDi You, Zenghui Zhang, Tatsuya Harada
To enhance object detection in a dark environment, we propose a novel multitask auto encoding transformation (MAET) model which is able to explore the intrinsic pattern behind illumination translation.
Ranked #1 on 2D Object Detection on ExDark
1 code implementation • CVPR 2022 • Jiawei Zhang, Xiang Wang, Xiao Bai, Chen Wang, Lei Huang, Yimin Chen, Lin Gu, Jun Zhou, Tatsuya Harada, Edwin R. Hancock
The stereo contrastive feature loss function explicitly constrains the consistency between learned features of matching pixel pairs which are observations of the same 3D points.
no code implementations • 18 Jan 2022 • Qiyuan An, Ruijiang Li, Lin Gu, Hao Zhang, Qingyu Chen, Zhiyong Lu, Fei Wang, Yingying Zhu
To evaluate our proposed method's utility and privacy loss, we apply our model on a medical report disease label classification task using two noisy challenging clinical text datasets.
no code implementations • 7 Jan 2022 • Ziteng Cui, Yingying Zhu, Lin Gu, Guo-Jun Qi, Xiaoxiao Li, Peng Gao, Zenghui Zhang, Tatsuya Harada
Image restoration algorithms such as super resolution (SR) are indispensable pre-processing modules for object detection in degraded images.
no code implementations • 2 Dec 2021 • Yifei HUANG, Xiaoxiao Li, Lijin Yang, Lin Gu, Yingying Zhu, Hirofumi Seo, Qiuming Meng, Tatsuya Harada, Yoichi Sato
Then we design a novel Auxiliary Attention Block (AAB) to allow information from SAN to be utilized by the backbone encoder to focus on selective areas.
1 code implementation • 1 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.
1 code implementation • 7 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.
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.
no code implementations • 22 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.
no code implementations • 16 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.
no code implementations • 22 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.
no code implementations • 24 Jul 2019 • Xingjun Ma, Yuhao Niu, Lin Gu, Yisen Wang, Yitian Zhao, James Bailey, Feng Lu
This raises safety concerns about the deployment of these systems in clinical settings.
1 code implementation • 6 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.
6 code implementations • 27 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.
Ranked #14 on Semantic Segmentation on PASCAL VOC 2012 test
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.
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.
no code implementations • 22 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.
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.