Search Results for author: Ke Yu

Found 28 papers, 18 papers with code

Concept-Guided Prompt Learning for Generalization in Vision-Language Models

no code implementations15 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.

Learning to Adapt CLIP for Few-Shot Monocular Depth Estimation

no code implementations2 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.

Monocular Depth Estimation

Two-Step Active Learning for Instance Segmentation with Uncertainty and Diversity Sampling

no code implementations28 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.

Active Learning Image Classification +3

Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat

1 code implementation7 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.

DrasCLR: A Self-supervised Framework of Learning Disease-related and Anatomy-specific Representation for 3D Medical Images

no code implementations21 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.

Anatomy Contrastive Learning +2

Beyond Distribution Shift: Spurious Features Through the Lens of Training Dynamics

1 code implementation18 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.

Hyperbolic Molecular Representation Learning for Drug Repositioning

no code implementations6 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.

molecular representation Representation Learning

Boosting the interpretability of clinical risk scores with intervention predictions

no code implementations6 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.

Anatomy-Guided Weakly-Supervised Abnormality Localization in Chest X-rays

1 code implementation25 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.

Anatomy Anomaly Detection

ReconfigISP: Reconfigurable Camera Image Processing Pipeline

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.

Image Restoration Neural Architecture Search +2

Can contrastive learning avoid shortcut solutions?

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.

Contrastive Learning

Context Matters: Graph-based Self-supervised Representation Learning for Medical Images

1 code implementation11 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.

Anatomy Representation Learning +1

Understanding Deformable Alignment in Video Super-Resolution

no code implementations15 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.

Optical Flow Estimation Video Super-Resolution

Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN

1 code implementation5 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.

Data Augmentation Domain Adaptation +4

Semi-Supervised Hierarchical Drug Embedding in Hyperbolic Space

1 code implementation1 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.

Clustering

EDVR: Video Restoration with Enhanced Deformable Convolutional Networks

11 code implementations7 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.

Deblurring Video Enhancement +2

Path-Restore: Learning Network Path Selection for Image Restoration

1 code implementation23 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.

Denoising Image Restoration +1

Deep Network Interpolation for Continuous Imagery Effect Transition

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.

Image Restoration Image-to-Image Translation +2

Improving On-policy Learning with Statistical Reward Accumulation

no code implementations7 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.

Atari Games

ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks

46 code implementations1 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).

Face Hallucination Generative Adversarial Network +2

Deep Convolution Networks for Compression Artifacts Reduction

2 code implementations9 Aug 2016 Ke Yu, Chao Dong, Chen Change Loy, Xiaoou Tang

Lossy compression introduces complex compression artifacts, particularly blocking artifacts, ringing effects and blurring.

Blocking Transfer Learning

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