Search Results for author:
Found 34 papers, 19 papers with code
Rethinking Text-based Protein Understanding: Retrieval or LLM?
In recent years, protein-text models have gained significant attention for their potential in protein generation and understanding.
ACPs: Agent Collaboration Protocols for the Internet of Agents
To address this gap, we propose Agent Collaboration Protocols (ACPs), a comprehensive protocol suite for the IoA.
Learning and Current Prediction of PMSM Drive via Differential Neural Networks
Learning models for dynamical systems in continuous time is significant for understanding complex phenomena and making accurate predictions.
ICODE: Modeling Dynamical Systems with Extrinsic Input Information
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.
NODE-Adapter: Neural Ordinary Differential Equations for Better Vision-Language Reasoning
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.
Conceptual Codebook Learning for Vision-Language Models
We recognize that visual concepts, such as textures, shapes, and colors are naturally transferable across domains and play a crucial role in generalization tasks.
Concept-Guided Prompt Learning for Generalization in Vision-Language Models
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
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.
Two-Step Active Learning for Instance Segmentation with Uncertainty and Diversity Sampling
Training high-quality instance segmentation models requires an abundance of labeled images with instance masks and classifications, which is often expensive to procure.
Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat
ML model design either starts with an interpretable model or a Blackbox and explains it post hoc.
Improving Text Matching in E-Commerce Search with A Rationalizable, Intervenable and Fast Entity-Based Relevance Model
We also show that pretraining the QE module with auto-generated QE data from user logs can further improve the overall performance.
Distilling BlackBox to Interpretable models for Efficient Transfer Learning
Building generalizable AI models is one of the primary challenges in the healthcare domain.
DrasCLR: A Self-supervised Framework of Learning Disease-related and Anatomy-specific Representation for 3D Medical Images
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.
Tackling Shortcut Learning in Deep Neural Networks: An Iterative Approach with Interpretable Models
The FOLs from the finetuned-BB-derived MoIE verify the elimination of the shortcut.
Beyond Distribution Shift: Spurious Features Through the Lens of Training Dynamics
(3) We empirically show that the harmful spurious features can be detected by observing the learning dynamics of the DNN's early layers.
Context-aware Self-supervised Learning for Medical Images Using Graph Neural Network
We use graph neural networks to incorporate the relationship between different anatomical regions.
Boosting the interpretability of clinical risk scores with intervention predictions
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.
Hyperbolic Molecular Representation Learning for Drug Repositioning
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.
Anatomy-Guided Weakly-Supervised Abnormality Localization in Chest X-rays
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.
ReconfigISP: Reconfigurable Camera Image Processing Pipeline
Image Signal Processor (ISP) is a crucial component in digital cameras that transforms sensor signals into images for us to perceive and understand.
Can contrastive learning avoid shortcut solutions?
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.
Context Matters: Graph-based Self-supervised Representation Learning for Medical Images
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.
BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond
Video super-resolution (VSR) approaches tend to have more components than the image counterparts as they need to exploit the additional temporal dimension.
Understanding Deformable Alignment in Video Super-Resolution
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.
Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN
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.
Semi-Supervised Hierarchical Drug Embedding in Hyperbolic Space
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.
EDVR: Video Restoration with Enhanced Deformable Convolutional Networks
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
Path-Restore: Learning Network Path Selection for Image Restoration
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.
Deep Network Interpolation for Continuous Imagery Effect Transition
Deep convolutional neural network has demonstrated its capability of learning a deterministic mapping for the desired imagery effect.
Improving On-policy Learning with Statistical Reward Accumulation
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.
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
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
Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning
We investigate a novel approach for image restoration by reinforcement learning.
Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform
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
Deep Convolution Networks for Compression Artifacts Reduction
Lossy compression introduces complex compression artifacts, particularly blocking artifacts, ringing effects and blurring.
