Search Results for author:
Found 15 papers, 6 papers with code
SkinCAP: A Multi-modal Dermatology Dataset Annotated with Rich Medical Captions
To address this gap and provide a meticulously annotated dermatology dataset with comprehensive natural language descriptions, we introduce SkinCAP: a multi-modal dermatology dataset annotated with rich medical captions.
Can We Treat Noisy Labels as Accurate?
Instead of focusing on label correction, EchoAlign treats noisy labels ($\tilde{Y}$) as accurate and modifies corresponding instance features ($X$) to achieve better alignment with $\tilde{Y}$.
Adapting Large Multimodal Models to Distribution Shifts: The Role of In-Context Learning
We find that the success of ICL heavily relies on the choice of demonstration, mirroring challenges seen in large language models but introducing unique complexities for LMMs facing distribution shifts.
HCVP: Leveraging Hierarchical Contrastive Visual Prompt for Domain Generalization
Domain Generalization (DG) endeavors to create machine learning models that excel in unseen scenarios by learning invariant features.
How Well Does GPT-4V(ision) Adapt to Distribution Shifts? A Preliminary Investigation
We further investigate its adaptability to controlled data perturbations and examine the efficacy of in-context learning as a tool to enhance its adaptation.
MHPL: Minimum Happy Points Learning for Active Source Free Domain Adaptation
Source free domain adaptation (SFDA) aims to transfer a trained source model to the unlabeled target domain without accessing the source data.
Topological Structure Learning for Weakly-Supervised Out-of-Distribution Detection
Based on limited ID labeled data and sufficient unlabeled data, we define a new setting called Weakly-Supervised Out-of-Distribution Detection (WSOOD).
Active Source Free Domain Adaptation
We then propose minimum happy points learning (MHPL) to actively explore and exploit MH points.
Exploring Domain-Invariant Parameters for Source Free Domain Adaptation
In contrast, we provide a fascinating insight: rather than attempting to learn domain-invariant representations, it is better to explore the domain-invariant parameters of the source model.
Safe-Student for Safe Deep Semi-Supervised Learning With Unseen-Class Unlabeled Data
To take advantage of these unseen-class data and ensure performance, we propose a safe SSL method called SAFE-STUDENT from the teacher-student view.
Learning to Rectify for Robust Learning with Noisy Labels
In this paper, we propose warped probabilistic inference (WarPI) to achieve adaptively rectifying the training procedure for the classification network within the meta-learning scenario.
Learning Transferable Parameters for Unsupervised Domain Adaptation
However, the learning processes of domain-invariant features and source hypothesis inevitably involve domain-specific information that would degrade the generalizability of UDA models on the target domain.
Unifying Neural Learning and Symbolic Reasoning for Spinal Medical Report Generation
In this paper, we propose the neural-symbolic learning (NSL) framework that performs human-like learning by unifying deep neural learning and symbolic logical reasoning for the spinal medical report generation.
Towards Accurate and Robust Domain Adaptation under Noisy Environments
In non-stationary environments, learning machines usually confront the domain adaptation scenario where the data distribution does change over time.
Robust Screening of COVID-19 from Chest X-ray via Discriminative Cost-Sensitive Learning
However, robust and accurate screening of COVID-19 from chest X-rays is still a globally recognized challenge because of two bottlenecks: 1) imaging features of COVID-19 share some similarities with other pneumonia on chest X-rays, and 2) the misdiagnosis rate of COVID-19 is very high, and the misdiagnosis cost is expensive.
