1 code implementation • 26 May 2025 • Juntong Wu, Zijing Liu, He Cao, Hao Li, Bin Feng, Zishan Shu, Ke Yu, Li Yuan, Yu Li
In recent years, protein-text models have gained significant attention for their potential in protein generation and understanding.
no code implementations • 18 May 2025 • Jun Liu, Ke Yu, Keliang Chen, Ke Li, Yuxinyue Qian, Xiaolian Guo, Haozhe Song, Yinming Li
To address this gap, we propose Agent Collaboration Protocols (ACPs), a comprehensive protocol suite for the IoA.
no code implementations • 12 Dec 2024 • Wenjie Mei, Xiaorui Wang, Yanrong Lu, Ke Yu, Shihua Li
Learning models for dynamical systems in continuous time is significant for understanding complex phenomena and making accurate predictions.
no code implementations • 21 Nov 2024 • Zhaoyi Li, Wenjie Mei, Ke Yu, Yang Bai, Shihua Li
This work offers a valuable class of neural ODE models for understanding physical systems with explicit external input information, with potential promising applications in fields such as physics and robotics.
no code implementations • 11 Jul 2024 • Yi Zhang, Chun-Wun Cheng, Ke Yu, Zhihai He, Carola-Bibiane Schönlieb, Angelica I. Aviles-Rivero
To fully leverage both visual and textual modalities and estimate class prototypes more effectively and accurately, we divide our method into two stages: cross-modal prototype construction and cross-modal prototype optimization using neural ordinary differential equations.
no code implementations • 2 Jul 2024 • Yi Zhang, Ke Yu, Siqi Wu, Zhihai He
We recognize that visual concepts, such as textures, shapes, and colors are naturally transferable across domains and play a crucial role in generalization tasks.
no code implementations • 15 Jan 2024 • Yi Zhang, Ce Zhang, Ke Yu, Yushun Tang, Zhihai He
However, for generalization tasks, the current fine-tuning methods for CLIP, such as CoOp and CoCoOp, demonstrate relatively low performance on some fine-grained datasets.
no code implementations • 2 Nov 2023 • Xueting Hu, Ce Zhang, Yi Zhang, Bowen Hai, Ke Yu, Zhihai He
When CLIP is used for depth estimation tasks, the patches, divided from the input images, can be combined with a series of semantic descriptions of the depth information to obtain similarity results.
no code implementations • 28 Sep 2023 • Ke Yu, Stephen Albro, Giulia Desalvo, Suraj Kothawade, Abdullah Rashwan, Sasan Tavakkol, Kayhan Batmanghelich, Xiaoqi Yin
Training high-quality instance segmentation models requires an abundance of labeled images with instance masks and classifications, which is often expensive to procure.
1 code implementation • 7 Jul 2023 • Shantanu Ghosh, Ke Yu, Forough Arabshahi, Kayhan Batmanghelich
ML model design either starts with an interpretable model or a Blackbox and explains it post hoc.
no code implementations • 1 Jul 2023 • Jiong Cai, Yong Jiang, Yue Zhang, Chengyue Jiang, Ke Yu, Jianhui Ji, Rong Xiao, Haihong Tang, Tao Wang, Zhongqiang Huang, Pengjun Xie, Fei Huang, Kewei Tu
We also show that pretraining the QE module with auto-generated QE data from user logs can further improve the overall performance.
1 code implementation • 26 May 2023 • Shantanu Ghosh, Ke Yu, Kayhan Batmanghelich
Building generalizable AI models is one of the primary challenges in the healthcare domain.
no code implementations • 21 Feb 2023 • Ke Yu, Li Sun, Junxiang Chen, Max Reynolds, Tigmanshu Chaudhary, Kayhan Batmanghelich
Extensive experiments on large-scale computer tomography (CT) datasets of lung images show that our method improves the performance of many downstream prediction and segmentation tasks.
1 code implementation • 20 Feb 2023 • Shantanu Ghosh, Ke Yu, Forough Arabshahi, Kayhan Batmanghelich
The FOLs from the finetuned-BB-derived MoIE verify the elimination of the shortcut.
1 code implementation • 18 Feb 2023 • Nihal Murali, Aahlad Puli, Ke Yu, Rajesh Ranganath, Kayhan Batmanghelich
(3) We empirically show that the harmful spurious features can be detected by observing the learning dynamics of the DNN's early layers.
no code implementations • 6 Jul 2022 • Li Sun, Ke Yu, Kayhan Batmanghelich
We use graph neural networks to incorporate the relationship between different anatomical regions.
no code implementations • 6 Jul 2022 • Eric Loreaux, Ke Yu, Jonas Kemp, Martin Seneviratne, Christina Chen, Subhrajit Roy, Ivan Protsyuk, Natalie Harris, Alexander D'Amour, Steve Yadlowsky, Ming-Jun Chen
We propose a joint model of intervention policy and adverse event risk as a means to explicitly communicate the model's assumptions about future interventions.
no code implementations • 6 Jul 2022 • Ke Yu, Shyam Visweswaran, Kayhan Batmanghelich
We use the Variational Auto-Encoder (VAE) framework to encode the chemical structures of molecules and use the drug-drug similarity information obtained from the hierarchy to induce the clustering of drugs in hyperbolic space.
1 code implementation • 25 Jun 2022 • Ke Yu, Shantanu Ghosh, Zhexiong Liu, Christopher Deible, Kayhan Batmanghelich
The critical component in our framework is an anatomy-guided attention module that aids the downstream observation network in focusing on the relevant anatomical regions generated by the anatomy network.
1 code implementation • ICCV 2021 • Ke Yu, Zexian Li, Yue Peng, Chen Change Loy, Jinwei Gu
Image Signal Processor (ISP) is a crucial component in digital cameras that transforms sensor signals into images for us to perceive and understand.
1 code implementation • NeurIPS 2021 • Joshua Robinson, Li Sun, Ke Yu, Kayhan Batmanghelich, Stefanie Jegelka, Suvrit Sra
However, we observe that the contrastive loss does not always sufficiently guide which features are extracted, a behavior that can negatively impact the performance on downstream tasks via "shortcuts", i. e., by inadvertently suppressing important predictive features.
1 code implementation • 11 Dec 2020 • Li Sun, Ke Yu, Kayhan Batmanghelich
Experiments on large-scale Computer Tomography (CT) datasets of lung images show that our approach compares favorably to baseline methods that do not account for the context.
6 code implementations • CVPR 2021 • Kelvin C. K. Chan, Xintao Wang, Ke Yu, Chao Dong, Chen Change Loy
Video super-resolution (VSR) approaches tend to have more components than the image counterparts as they need to exploit the additional temporal dimension.
no code implementations • 15 Sep 2020 • Kelvin C. K. Chan, Xintao Wang, Ke Yu, Chao Dong, Chen Change Loy
Aside from the contributions to deformable alignment, our formulation inspires a more flexible approach to introduce offset diversity to flow-based alignment, improving its performance.
1 code implementation • 5 Aug 2020 • Li Sun, Junxiang Chen, Yanwu Xu, Mingming Gong, Ke Yu, Kayhan Batmanghelich
During training, we adopt a hierarchical structure that simultaneously generates a low-resolution version of the image and a randomly selected sub-volume of the high-resolution image.
1 code implementation • 1 Jun 2020 • Ke Yu, Shyam Visweswaran, Kayhan Batmanghelich
We use the Variational Auto-Encoder (VAE) framework to encode the chemical structures of molecules and use the knowledge-based drug-drug similarity to induce the clustering of drugs in hyperbolic space.
11 code implementations • 7 May 2019 • Xintao Wang, Kelvin C. K. Chan, Ke Yu, Chao Dong, Chen Change Loy
In this work, we propose a novel Video Restoration framework with Enhanced Deformable networks, termed EDVR, to address these challenges.
Ranked #2 on
Deblurring
on REDS
1 code implementation • 23 Apr 2019 • Ke Yu, Xintao Wang, Chao Dong, Xiaoou Tang, Chen Change Loy
To leverage this, we propose Path-Restore, a multi-path CNN with a pathfinder that can dynamically select an appropriate route for each image region.
2 code implementations • CVPR 2019 • Xintao Wang, Ke Yu, Chao Dong, Xiaoou Tang, Chen Change Loy
Deep convolutional neural network has demonstrated its capability of learning a deterministic mapping for the desired imagery effect.
no code implementations • 7 Sep 2018 • Yubin Deng, Ke Yu, Dahua Lin, Xiaoou Tang, Chen Change Loy
Most methods in deep-RL achieve good results via the maximization of the reward signal provided by the environment, typically in the form of discounted cumulative returns.
46 code implementations • 1 Sep 2018 • Xintao Wang, Ke Yu, Shixiang Wu, Jinjin Gu, Yihao Liu, Chao Dong, Chen Change Loy, Yu Qiao, Xiaoou Tang
To further enhance the visual quality, we thoroughly study three key components of SRGAN - network architecture, adversarial loss and perceptual loss, and improve each of them to derive an Enhanced SRGAN (ESRGAN).
Ranked #2 on
Face Hallucination
on FFHQ 512 x 512 - 16x upscaling
2 code implementations • CVPR 2018 • Ke Yu, Chao Dong, Liang Lin, Chen Change Loy
We investigate a novel approach for image restoration by reinforcement learning.
4 code implementations • CVPR 2018 • Xintao Wang, Ke Yu, Chao Dong, Chen Change Loy
In this paper, we show that it is possible to recover textures faithful to semantic classes.
Ranked #62 on
Image Super-Resolution
on BSD100 - 4x upscaling
2 code implementations • 9 Aug 2016 • Ke Yu, Chao Dong, Chen Change Loy, Xiaoou Tang
Lossy compression introduces complex compression artifacts, particularly blocking artifacts, ringing effects and blurring.