CT-Lite combines Feature Attention Style Transfer (FAST) and Structured Factorized Projections (SFP) with contrastive learning to reach AUROC within 5-7% of uncompressed baselines on compressed CT volumes across three datasets while using far fewer parameters.
hub
A simple framework for contrastive learning of visual representations,
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
hub tools
representative citing papers
HealthPoint represents clinical events as points in a 4D space (content, time, modality, case) and applies low-rank relational attention to achieve state-of-the-art mortality prediction from multi-level incomplete multimodal EHRs.
CBEN provides paired optical-radar images with cloud occlusion, revealing 23-33 point AP drops in clear-sky trained models and 17-29 point relative gains when models are trained on cloudy data.
RAG-HAR combines retrieval-augmented generation with LLMs to deliver state-of-the-art human activity recognition across six benchmarks without any model training or fine-tuning.
SolarCHIP contrastively pretrains CNN and Vision Transformer backbones on SDO AIA-HMI data with multi-granularity objectives, achieving SOTA on cross-modal translation and flare classification especially in low-resource settings.
A framework learns to map seed music embeddings to mood-adjusted targets using proxy sampling and a joint objective, outperforming baselines in preserving non-mood attributes on two datasets.
Proposes TA2CL framework that uses temporal asynchronous alignment in contrastive learning to improve cross-subject EEG emotion classification, reporting 64.5% accuracy on 9-class FACED, 79.5% binary on FACED, 86.4% on SEED and 70.1% on SEED-V.
Tabular representation learning for network intrusion detection exhibits strong dataset-model dependency, with supervised methods outperforming unsupervised anomaly detection and limited but possible cross-dataset generalization.
SCHK-HTC uses sibling contrastive learning plus hierarchical prompt tuning to improve discrimination between confusable sibling classes in few-shot hierarchical text classification.
A multi-view evidential framework combines semantic and reasoning information to improve accuracy and provide trustworthy uncertainty estimates for mental health prediction on text data.
citing papers explorer
-
Learning from Compressed CT: Feature Attention Style Transfer and Structured Factorized Projections for Resource-Efficient Medical Image Analysis
CT-Lite combines Feature Attention Style Transfer (FAST) and Structured Factorized Projections (SFP) with contrastive learning to reach AUROC within 5-7% of uncompressed baselines on compressed CT volumes across three datasets while using far fewer parameters.
-
A Clinical Point Cloud Paradigm for In-Hospital Mortality Prediction from Multi-Level Incomplete Multimodal EHRs
HealthPoint represents clinical events as points in a 4D space (content, time, modality, case) and applies low-rank relational attention to achieve state-of-the-art mortality prediction from multi-level incomplete multimodal EHRs.
-
CBEN -- A Multimodal Machine Learning Dataset for Cloud Robust Remote Sensing Image Understanding
CBEN provides paired optical-radar images with cloud occlusion, revealing 23-33 point AP drops in clear-sky trained models and 17-29 point relative gains when models are trained on cloudy data.
-
RAG-HAR: Retrieval Augmented Generation-based Human Activity Recognition
RAG-HAR combines retrieval-augmented generation with LLMs to deliver state-of-the-art human activity recognition across six benchmarks without any model training or fine-tuning.
-
Contrastive Heliophysical Image Pretraining for Solar Dynamics Observatory Records
SolarCHIP contrastively pretrains CNN and Vision Transformer backbones on SDO AIA-HMI data with multi-granularity objectives, achieving SOTA on cross-modal translation and flare classification especially in low-resource settings.
-
Controllable Embedding Transformation for Mood-Guided Music Retrieval
A framework learns to map seed music embeddings to mood-adjusted targets using proxy sampling and a joint objective, outperforming baselines in preserving non-mood attributes on two datasets.
-
Cross-Subject EEG Emotion Recognition Based on Temporal Asynchronous Alignment Contrastive Learning
Proposes TA2CL framework that uses temporal asynchronous alignment in contrastive learning to improve cross-subject EEG emotion classification, reporting 64.5% accuracy on 9-class FACED, 79.5% binary on FACED, 86.4% on SEED and 70.1% on SEED-V.
-
Evaluating Tabular Representation Learning for Network Intrusion Detection
Tabular representation learning for network intrusion detection exhibits strong dataset-model dependency, with supervised methods outperforming unsupervised anomaly detection and limited but possible cross-dataset generalization.
-
SCHK-HTC: Sibling Contrastive Learning with Hierarchical Knowledge-Aware Prompt Tuning for Hierarchical Text Classification
SCHK-HTC uses sibling contrastive learning plus hierarchical prompt tuning to improve discrimination between confusable sibling classes in few-shot hierarchical text classification.
-
Beyond Semantics: An Evidential Reasoning-Aware Multi-View Learning Framework for Trustworthy Mental Health Prediction
A multi-view evidential framework combines semantic and reasoning information to improve accuracy and provide trustworthy uncertainty estimates for mental health prediction on text data.