paper-with-me

Papers Self-Knowledge Distillation

“Self-Knowledge Distillation” 태그가 달린 논문 68편 · 필터 해제

Tackling Data Heterogeneity in Federated Learning through Knowledge Distillation with Inequitable Aggregation

2025-06-25 · Xing Ma

Federated learning aims to train a global model in a distributed environment that is close to the performance of centralized training. However, issues such as client label skew, data quantity skew, and other heterogeneit…

Federated LearningKnowledge DistillationSelf-Knowledge Distillation

MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation

2025-03-26 · Rongyu Zhang, Menghang Dong, Yuan Zhang, Liang Heng 외

Multimodal Large Language Models (MLLMs) excel in understanding complex language and visual data, enabling generalist robotic systems to interpret instructions and perform embodied tasks. Nevertheless, their real-world d…

Knowledge DistillationMixture-of-ExpertsRobot ManipulationSelf-Knowledge Distillation+1

xVLM2Vec: Adapting LVLM-based embedding models to multilinguality using Self-Knowledge Distillation

2025-03-12 · Elio Musacchio, Lucia Siciliani, Pierpaolo Basile, Giovanni Semeraro

In the current literature, most embedding models are based on the encoder-only transformer architecture to extract a dense and meaningful representation of the given input, which can be a text, an image, and more. With t…

Knowledge DistillationLanguage ModelingLanguage ModellingSelf-Knowledge Distillation

Investigating and Enhancing Vision-Audio Capability in Omnimodal Large Language Models

2025-02-27 · Rui Hu, Delai Qiu, Shuyu Wei, Jiaming Zhang 외

Omnimodal Large Language Models (OLLMs) have shown significant progress in integrating vision and text, but still struggle with integrating vision and audio, often exhibiting suboptimal performance when processing audio …

Knowledge DistillationSelf-Knowledge Distillation

Efficient Lung Ultrasound Severity Scoring Using Dedicated Feature Extractor

2025-01-21 · Jiaqi Guo, Yunan Wu, Evangelos Kaimakamis, Georgios Petmezas 외

With the advent of the COVID-19 pandemic, ultrasound imaging has emerged as a promising technique for COVID-19 detection, due to its non-invasive nature, affordability, and portability. In response, researchers have focu…

DiagnosticKnowledge DistillationSelf-Knowledge DistillationVideo Classification

Generative Dataset Distillation Based on Self-knowledge Distillation

2025-01-08 · Longzhen Li, Guang Li, Ren Togo, Keisuke Maeda 외

Dataset distillation is an effective technique for reducing the cost and complexity of model training while maintaining performance by compressing large datasets into smaller, more efficient versions. In this paper, we p…

Dataset DistillationKnowledge DistillationSelf-Knowledge Distillation

Towards Satellite Non-IID Imagery: A Spectral Clustering-Assisted Federated Learning Approach

2024-10-17 · Luyao Zou, Yu Min Park, Chu Myaet Thwal, Yan Kyaw Tun 외

Low Earth orbit (LEO) satellites are capable of gathering abundant Earth observation data (EOD) to enable different Internet of Things (IoT) applications. However, to accomplish an effective EOD processing mechanism, it …

Earth ObservationFederated LearningKnowledge DistillationSelf-Knowledge Distillation

Frequency-Guided Masking for Enhanced Vision Self-Supervised Learning

2024-09-16 · Amin Karimi Monsefi, Mengxi Zhou, Nastaran Karimi Monsefi, Ser-Nam Lim 외

We present a novel frequency-based Self-Supervised Learning (SSL) approach that significantly enhances its efficacy for pre-training. Prior work in this direction masks out pre-defined frequencies in the input image and …

Few-Shot Learningimage-classificationImage ClassificationImage Compression+4

SalNAS: Efficient Saliency-prediction Neural Architecture Search with self-knowledge distillation

2024-07-29 · Chakkrit Termritthikun, Ayaz Umer, Suwichaya Suwanwimolkul, Feng Xia 외

Recent advancements in deep convolutional neural networks have significantly improved the performance of saliency prediction. However, the manual configuration of the neural network architectures requires domain knowledg…

DecoderKnowledge DistillationNeural Architecture SearchPrediction+2

Towards A Generalizable Pathology Foundation Model via Unified Knowledge Distillation

2024-07-26 · Jiabo Ma, Zhengrui Guo, Fengtao Zhou, Yihui Wang 외

Foundation models pretrained on large-scale datasets are revolutionizing the field of computational pathology (CPath). The generalization ability of foundation models is crucial for the success in various downstream clin…

Knowledge DistillationQuestion AnsweringRepresentation LearningSelf-Knowledge Distillation+3

Three-Stream Temporal-Shift Attention Network Based on Self-Knowledge Distillation for Micro-Expression Recognition

2024-06-25 · Guanghao Zhu, Lin Liu, Yuhao Hu, Haixin Sun 외

Micro-expressions are subtle facial movements that occur spontaneously when people try to conceal real emotions. Micro-expression recognition is crucial in many fields, including criminal analysis and psychotherapy. Howe…

Knowledge DistillationMicro Expression RecognitionMicro-Expression RecognitionMotion Magnification+1

SeCoKD: Aligning Large Language Models for In-Context Learning with Fewer Shots

2024-06-20 · Weixing Wang, Haojin Yang, Christoph Meinel

Previous studies have shown that demonstrations can significantly help Large Language Models (LLMs ) perform better on the given tasks. However, this so-called In-Context Learning ( ICL ) ability is very sensitive to the…

In-Context LearningKnowledge DistillationSelf-Knowledge Distillation

Self-Knowledge Distillation for Learning Ambiguity

2024-06-14 · Hancheol Park, Soyeong Jeong, Sukmin Cho, Jong C. Park

Recent language models have shown remarkable performance on natural language understanding (NLU) tasks. However, they are often sub-optimal when faced with ambiguous samples that can be interpreted in multiple ways, over…

Knowledge DistillationNatural Language UnderstandingSelf-Knowledge Distillation

Guiding Frame-Level CTC Alignments Using Self-knowledge Distillation

2024-06-12 · Eungbeom Kim, Hantae Kim, Kyogu Lee

Transformer encoder with connectionist temporal classification (CTC) framework is widely used for automatic speech recognition (ASR). However, knowledge distillation (KD) for ASR displays a problem of disagreement betwee…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Knowledge DistillationSelf-Knowledge Distillation+2

Vision-Language Meets the Skeleton: Progressively Distillation with Cross-Modal Knowledge for 3D Action Representation Learning

2024-05-31 · Yang Chen, Tian He, Junfeng Fu, Ling Wang 외

Skeleton-based action representation learning aims to interpret and understand human behaviors by encoding the skeleton sequences, which can be categorized into two primary training paradigms: supervised learning and sel…

Action RecognitionContrastive LearningKnowledge DistillationRepresentation Learning+4

CrossMatch: Enhance Semi-Supervised Medical Image Segmentation with Perturbation Strategies and Knowledge Distillation

2024-05-01 · Bin Zhao, Chunshi Wang, Shuxue Ding

Semi-supervised learning for medical image segmentation presents a unique challenge of efficiently using limited labeled data while leveraging abundant unlabeled data. Despite advancements, existing methods often do not …

Image SegmentationKnowledge DistillationMedical Image SegmentationSelf-Knowledge Distillation+2

Weakly Supervised Monocular 3D Detection with a Single-View Image

2024-02-29 · CVPR 2024 1 · Xueying Jiang, Sheng Jin, Lewei Lu, Xiaoqin Zhang 외

Monocular 3D detection (M3D) aims for precise 3D object localization from a single-view image which usually involves labor-intensive annotation of 3D detection boxes. Weakly supervised M3D has recently been studied to ob…

Knowledge DistillationObject LocalizationSelf-Knowledge DistillationTransfer Learning

Distilled Gradual Pruning with Pruned Fine-tuning

2024-02-15 · IEEE Transactions on Artificial Intelligence 2024 2 · Federico Fontana, Romeo Lanzino, Marco Raoul Marini, Danilo Avola 외

Neural Networks (NNs) have been driving machine learning progress in recent years, but their larger models present challenges in resource-limited environments. Weight pruning reduces the computational demand, often with …

Image ClassificationKnowledge DistillationSelf-Knowledge Distillation

BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation

2024-02-05 · Jianlv Chen, Shitao Xiao, Peitian Zhang, Kun Luo 외

In this paper, we present a new embedding model, called M3-Embedding, which is distinguished for its versatility in Multi-Linguality, Multi-Functionality, and Multi-Granularity. It can support more than 100 working langu…

Knowledge DistillationRetrievalSelf-Knowledge Distillation

Deep Clustering with Diffused Sampling and Hardness-aware Self-distillation

2024-01-25 · Hai-Xin Zhang, Dong Huang

Deep clustering has gained significant attention due to its capability in learning clustering-friendly representations without labeled data. However, previous deep clustering methods tend to treat all samples equally, wh…

ClusteringContrastive LearningDeep ClusteringKnowledge Distillation+2
1–20 / 68 다음 →