paper-with-me

Papers Contrastive Learning

“Contrastive Learning” 태그가 달린 논문 8,164편 · 필터 해제

Type-IV Code Clone Detection via Layer-Wise Non-Contrastive Representation Learning

2026-09-15 · Luciano Marchezan, Kevin Delcourt, Eugene Syriani, Houari Sahraoui arxiv

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 Learning

RegRet: Enhancing Region-Level Retrieval in Large Multimodal Models

2026-09-15 · Xun Liang, Honghui Yang, Weihang Pan, Ruisi Zhao 외 arxiv

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 Learning

Efficient Quantization-Aware Distillation with Cross-Modal Alignment for Edge Vision-Language Models

2026-09-15 · Jinwoo Jeon, GyuYeop Do, Yubin Lim, Nam-Joon Kim 외 arxiv

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 Learning

Counterfactual Reasoning for Robust Visual Question Answering

2026-09-15 · Truong-Binh Duong, Thanh-Ngan Tran, Ngoc-Thao Nguyen, Bac Le arxiv

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 Grounding

Which Pretext Task Transfers? Self-Supervised Pretraining Objectives for Lung Ultrasound

2026-09-15 · Moein Heidari, Junbo Rao, Jai Choraria, Wenjin Chen 외 arxiv

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 Learning

ReMoMask-2: Latent Retrieval-Augmented Masked Motion Generation

2026-09-08 · Yiran Wang, Zeyu Zhang, Ling Shao, Hao Tang hf

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 Learning

DGCPath: Distribution-Aware Generative Contrastive Framework for Self-supervised Path Representation Learning -- Extended Version

2026-09-07 · Sean Bin Yang, Hao Miao, Zongyi Xu, Jilin Hu 외 arxiv

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 Learning

Self-Supervised Lexical Representation Learning for Fast, Large-Scale Phylogenetic Inference

2026-09-04 · Tim Wientzek arxiv

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 Learning

ProCA: Progressive Contrastive Alignment for Robust EEG Visual Decoding

2026-09-04 · Kanglei Zhou, Chunyan Lan, Dongyang Li, Jun Zhu 외 arxiv

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 Decoding

Beyond Homoscedasticity: Decoupled Uncertainty Optimization for Deep Imbalanced Regression

2026-09-04 · Juncheng Zhou, Jiaxi Lu, Weijing Zeng, Zhong Li 외 arxiv

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 Estimation

Latent-Aligned Reasoning for Multimodal Recommendation

2026-09-04 · Jiarui Jin, Anyang Ji arxiv

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 Learning

CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation

2026-09-03 · Tingyu Song, Mingxin Li, Yanzhao Zhang, Dingkun Long 외 hf

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 Learning

BLARM: Animating 3D Objects from Video via Blending Latent Rigid Motion Primitives

2026-08-31 · Pradyumn Goyal, Yizhak Ben-Shabat, Hsueh-Ti Derek Liu, Haomiao Jiang 외 hf

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 Learning

ARC-CT: Anatomy-Routed Contrastive Vision-Language Learning for 3D Chest CT

2026-08-28 · Huseyin Umut Isik, Mehmet Alp Ozaydin, Sila Kurugol, Şeyda Ertekin arxiv

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 Learning

GAAT: Geometry-Aware Alignment Transformer for Multimodal UAV Perception

2026-08-28 · Jingpu Yang, Debin Tang, Yilin Sun, Fengxian Ji 외 arxiv

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 Understanding

HALO: A Heterogeneity-Aware Language-Aligned IMU Foundation Model for Open-Set Human Activity Recognition

2026-08-27 · Zihan Ding, Liyu Zhang, Xiaomin Ouyang arxiv

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 Learning

Graph-Based Pseudo-multimodal Contrastive Learning for 12-Lead ECG Representations

2026-08-27 · Mengyu Wang, Kozo Okada, Takafumi Goto, Natsuko Jinba 외 arxiv

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

Embedding NDRE Trajectories into Contrastive Learning for Label-Free, Physiology-Aware Crop-Stress Staging and DSS Outputs

2026-08-26 · Shafqaat Ahmad arxiv

Timely detection of crop stress is critical for sustaining yields under increasing drought frequency, yet conventional vegetation index thresholds or image-based clustering often fail to capture stress progression, limit…

Contrastive Learning

Skeleton-based Zero-Shot Spatio-Temporal Action Localization via Weakly-Supervised Pretraining

2026-08-26 · Koshiro Nagano, Fumiaki Sato, Ryo Hachiuma, Kazuki Tsutsukawa 외 arxiv

We propose a novel pretraining strategy for skeleton-based zero-shot spatio-temporal action localization to estimate unseen actions for person instances while overcoming high annotation costs for training via new target …

Spatio-Temporal Action LocalizationContrastive Learning

AdaptiveEmbed: Sample-Adaptive Multi-Vector Representation for Multimodal Retrieval

2026-08-26 · Xinze Liu, Lei Yang, Dayan Wu, Hengjie Zhu 외 arxiv

Multi-vector representations have emerged as an effective paradigm for multimodal retrieval, representing each sample with multiple complementary embeddings to capture fine-grained cross-modal information. However, exist…

Contrastive Learning
1–20 / 8,164 다음 →