Papers Contrastive Learning
“Contrastive Learning” 태그가 달린 논문 8,167편 · 필터 해제
Learning from Failure: Leveraging Unreliable Predictions in Semi-Supervised Real-World Adverse Weather Removal
Adverse weather image restoration aims to recover images degraded by rain, haze, snow, and other weather-induced artifacts, thereby improving the robustness of outdoor vision systems. Existing unified restoration models …
Contrastive LearningImage RestorationCross-Lingual Alignment for Decoder-Only Models using MoE Routers
Cross-lingual contrastive learning has been a core component of multilingual encoder training, but the ability to explicitly align representations is not possible in decoder-only LLMs because of varying multilingual toke…
Cross-Lingual TransferContrastive LearningSentZero: An Enhanced Sentence-Centric Vision-Language Pretraining for Multi-Task Zero-Shot Chest X-Ray Analysis
Vision-language (VL) pretraining using paired chest X-ray (CXR) images and radiology reports has shown strong potential for medical image understanding. However, existing methods often remain dependent on task-specific f…
Zero-shot GeneralizationContrastive LearningType-IV Code Clone Detection via Layer-Wise Non-Contrastive Representation Learning
Software clones are fragments of code that are similar or functionally equivalent to each other. They pose significant challenges for maintenance, refactoring, and bug detection. Detecting Type-IV clones, which are seman…
Representation LearningContrastive LearningRegRet: Enhancing Region-Level Retrieval in Large Multimodal Models
Region-level retrieval aims to align user-specified image regions with relevant regions or textual descriptions, playing a crucial role in realworld applications such as e-commerce product search and RAG. Although recent…
Contrastive LearningEfficient Quantization-Aware Distillation with Cross-Modal Alignment for Edge Vision-Language Models
Large-scale vision-language models (VLM) such as CLIP enable strong open-vocabulary reasoning, yet deploying these capabilities on resource-constrained edge devices remains challenging. EdgeVL addresses this problem by d…
Contrastive LearningCounterfactual Reasoning for Robust Visual Question Answering
Modern Visual Question Answering (VQA) models often exploit spurious correlations in training data, leading to poor out-of-distribution (OOD) generalization due to language bias. Although counterfactual learning has show…
Visual Question AnsweringContrastive LearningVisual GroundingWhich 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 LearningReMoMask-2: Latent Retrieval-Augmented Masked Motion Generation
Text-to-motion (T2M) generation maps natural language to human joint movements, aiding gaming, VR, and robotics. Retrieval-Augmented Text-to-Motion (RAG-T2M) improves generation on complex descriptions by conditioning on…
Contrastive LearningDGCPath: Distribution-Aware Generative Contrastive Framework for Self-supervised Path Representation Learning -- Extended Version
Due to the proliferation of vehicle trajectory data enabled by advanced sensing technologies, path representation learning has become a pivotal task in intelligent transportation systems. Although existing self-supervise…
Representation LearningContrastive LearningSelf-Supervised Lexical Representation Learning for Fast, Large-Scale Phylogenetic Inference
Computational phylogenetics has become an essential tool in historical linguistics, yet its application at a global scale remains constrained by two factors: the labor-intensive manual annotation of cognacy judgments req…
Representation LearningContrastive LearningProCA: Progressive Contrastive Alignment for Robust EEG Visual Decoding
Electroencephalogram (EEG) visual decoding aims to recover visual semantics from non-invasive neural time-series signals, for which robust alignment between noisy neural responses and stable semantic representations is k…
Contrastive LearningEeg DecodingBeyond Homoscedasticity: Decoupled Uncertainty Optimization for Deep Imbalanced Regression
Deep Imbalanced Regression (DIR) is pervasive in continuous prediction tasks across diverse modalities, such as age estimation, depth prediction, and protein mutation activity prediction, where label-scarce tail samples …
Contrastive LearningActivity PredictionAge EstimationLatent-Aligned Reasoning for Multimodal Recommendation
Multimodal Vision-Language Models (VLMs) have demonstrated remarkable capabilities in cross-modal understanding, yet a fundamental challenge persists when applying them to recommendation: as representations propagate thr…
Multimodal RecommendationContrastive LearningCORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation
MLLM-based embedding models remain limited in compositional retrieval, often failing to distinguish scenes containing the same concepts but different attribute-object bindings. Yet the same backbone can resolve such dist…
Contrastive LearningBLARM: Animating 3D Objects from Video via Blending Latent Rigid Motion Primitives
We introduce BLARM, a feed-forward method for video-driven 3D mesh animation. Given a monocular video and a static object mesh, BLARM predicts a temporally coherent animated mesh whose motion follows the video. Rather th…
Contrastive LearningARC-CT: Anatomy-Routed Contrastive Vision-Language Learning for 3D Chest CT
Contrastive vision-language learning uses paired chest CT volumes and radiology reports to learn abnormality classifiers without manually annotated labels. However, two characteristics of chest CT challenge conventional …
Contrastive LearningGAAT: Geometry-Aware Alignment Transformer for Multimodal UAV Perception
Unmanned aerial vehicle (UAV) multimodal perception integrates visible (RGB), infrared (IR), synthetic aperture radar (SAR), and depth sensors for scene understanding under diverse conditions. However, differences in opt…
Contrastive LearningScene UnderstandingHALO: 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 LearningGraph-Based Pseudo-multimodal Contrastive Learning for 12-Lead ECG Representations
12-lead electrocardiogram (ECG) is a standard, non-invasive examination widely used for diagnosing coronary artery disease, where clinical interpretation relies on comparing waveform patterns across multiple leads. Howev…
Contrastive Learning