Papers Self-Supervised Learning
“Self-Supervised Learning” 태그가 달린 논문 5,929편 · 필터 해제
Surface-volume self-supervised representation learning of brain MRI for genetic discovery
Existing genome-wide association studies (GWAS) of brain imaging provide predefined or deep-learning-derived imaging phenotypes, yet these phenotypes come from either volumetric scans or cortical surface meshes, so each …
Self-Supervised LearningRepresentation LearningBeyond Decodability: Do Acoustic Factors Drive Predictions in Speech-Based Alzheimer's Assessment?
Speech-based Alzheimer's disease (AD) assessments increasingly rely on pretrained self-supervised learning (SSL) models that learn acoustic representations directly from raw audio, exposing the model to recording factors…
Self-Supervised LearningI Have a Stream: Making Self-Supervised Learning Work on Continuous Video
Self-supervised learning draws inspiration from infant visual development, yet standard training pipelines bear little resemblance to it: images are independently sampled and globally shuffled across epochs. We study sel…
Self-Supervised LearningEvolvingAvatar: Interactive 3D Head Generation That Adapts as Conversations Unfold
Interactive 3D head generation requires coordinated speaking and listening motion that responds to an evolving conversation. Existing generators use incoming observations as context but keep their parameters fixed, leavi…
Self-Supervised LearningTT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining
Comparisons in video self-supervised learning often evaluate complete training recipes rather than isolating the method itself: architecture, objective, data exposure, schedule, scale, and decoder capacity can all vary a…
Self-Supervised LearningTactile-JEPA: Topology-Aware Self-Supervised Representation Learning for Distributed Tactile Sensors
Tactile sensing is an essential modality for robots performing contact-rich, dexterous manipulation, particularly under visual occlusion. While pre-trained image encoders are standard in robot learning pipelines, tactile…
Self-Supervised LearningRepresentation LearningDistributed JEPA: A Self-Supervised Framework for Energy Forecasting
Traditional energy forecasting solutions rely on task-specific supervision and energy asset representations, limiting transferability and the ability to capture general temporal dynamics across heterogeneous assets. We a…
Self-Supervised LearningCLASH: Counterfactual Auditing of Lexical and Prosodic Reliance in Spoken Sarcasm Detection
Spoken sarcasm detectors may exploit lexical content, prosody, or their interaction, yet conventional evaluation cannot reveal which cues drive their predictions. We introduce CLASH (Controlled Lexical-Acoustic Separatio…
Self-Supervised LearningSarcasm DetectionWhich Pretext Task Transfers? Self-Supervised Pretraining Objectives for Lung Ultrasound
Self-supervised learning (SSL) can reduce the need for labelled medical images, but the choice of pretext objective remains unclear for lung ultrasound (LUS). Contrastive learning, masked reconstruction, and joint-embedd…
Self-Supervised LearningContrastive LearningSeven Sources of Physical AI Capability Formation
Capabilities relevant to Physical AI can arise from materially different formation histories, yet existing taxonomies organized by morphology, architecture, learning algorithm, task, or domain do not directly answer what…
Self-Supervised LearningAn Analysis of Self-supervised Pre-training with Dependent Samples
Self-supervised learning relies on so-called data augmentations $φ(x)$ of unlabeled datapoints $x$ --- for example, masking random pixels in an image $x$ --- that should leave the label of $x$ invariant and are often use…
Self-Supervised LearningLeveraging Imperfect Restoration for Data Availability Attack
The abundance of online data is at risk of unauthorized usage in training deep learning models. To counter this, various Data Availability Attacks (DAAs) have been devised to make data unlearnable for such models by subt…
Self-Supervised LearningSynergistic Information Disentanglement for Omni-modal Slide Representation Learning in Computational Pathology
In computational pathology (CPath), developing omni-modal self-supervised learning (SSL) models that integrate histology, genomics, and clinical reports enables transferable representation learning for whole slide images…
Self-Supervised LearningRepresentation LearningKnowledge Distillation During Mid-Training Favors Reasoning over Factual Recall
Logit-based knowledge distillation (KD) is used to train smaller language models (LMs) via supervision from stronger teachers, but whether its benefits are consistent across training stages remains unclear. Through contr…
Self-Supervised LearningKnowledge DistillationUncertainty of Vision Medical Foundation Models
Accurate uncertainty estimation is essential for machine learning systems de- ployed in high-stakes domains such as medicine. Traditional approaches primarily rely on probability outputs from trained models (point predic…
Self-Supervised LearningHALO: A Heterogeneity-Aware Language-Aligned IMU Foundation Model for Open-Set Human Activity Recognition
Human Activity Recognition (HAR) using inertial measurement units (IMUs) enables a wide range of applications, yet the field still lacks a unified model that can generalize across diverse subjects, devices, and activitie…
Human Activity RecognitionSelf-Supervised LearningContrastive LearningFIDA: Feature Instability-Driven Attack on Self-Supervised Facial Representation
Self-supervised learning (SSL) models are vulnerable to backdoor attacks. However, the systemic risks they pose in face representation have received little attention. The entanglement of identity features in self-supervi…
Self-Supervised LearningDomain-Specific Self-Supervised Representation Learning for Retinal Fundus Classification
Despite the growing number of public datasets, annotated medical images remain scarce. Supervised learning methods achieve strong performance on many benchmarks, however require large amounts of labeled data, which are c…
Diabetic Retinopathy GradingSelf-Supervised LearningRepresentation LearningDEFUSE: Generalizable Backdoor Defense for Self-Supervised Encoders with Generative Priors
Self-supervised learning (SSL) encoders are vulnerable to backdoor attacks, posing threats to both visual SSL encoders and vision-language encoders. Existing defenses are typically designed for only one of these paradigm…
Self-Supervised LearningAdapter-Based Few-Shot Continual Learning for Malicious Packet Recognition
The continual evolution of malware variants necessitates detection systems that can adapt to new threats without retraining from scratch. However, continually updating models on new data often leads to catastrophic forge…
Few-Shot Class-Incremental LearningSelf-Supervised LearningMalware ClassificationContinual Learning