Image de couverture de livre

Object-level Self-Distillation for Vision Pretraining

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Hızlı, Çağlar, Yıldız, Çağatay, Marttinen, Pekka
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Identifying latent state transition in non-linear dynamical systems
par: Hızlı, Çağlar, et autres
Publié: (2024)

Improving Medical Multi-modal Contrastive Learning with Expert Annotations
par: Kumar, Yogesh, et autres
Publié: (2024)

A Reproduction Study: The Kernel PCA Interpretation of Self-Attention Fails Under Scrutiny
par: Sarıtaş, Karahan, et autres
Publié: (2025)

Rethinking Temporal Consistency in Video Object-Centric Learning: From Prediction to Correspondence
par: Li, Zhiyuan, et autres
Publié: (2026)

Strategies for Robust Deep Learning Based Deformable Registration
par: Honkamaa, Joel, et autres
Publié: (2025)

New multimodal similarity measure for image registration via modeling local functional dependence with linear combination of learned basis functions
par: Honkamaa, Joel, et autres
Publié: (2025)

SITReg: Multi-resolution architecture for symmetric, inverse consistent, and topology preserving image registration
par: Honkamaa, Joel, et autres
Publié: (2023)

A Study on Self-Supervised Pretraining for Vision Problems in Gastrointestinal Endoscopy
par: Sanderson, Edward, et autres
Publié: (2024)

ReMem: Mutual Information-Aware Fine-tuning of Pretrained Vision Transformers for Effective Knowledge Distillation
par: Dong, Chengyu, et autres
Publié: (2025)

Infinite dSprites for Disentangled Continual Learning: Separating Memory Edits from Generalization
par: Dziadzio, Sebastian, et autres
Publié: (2023)

DINORANKCLIP: DINOv3 Distillation and Injection for Vision-Language Pretraining with High-Order Ranking Consistency
par: Jiang, Shuyang, et autres
Publié: (2026)

Self-Supervised Pretraining for Aerial Road Extraction
par: Polley, Rupert, et autres
Publié: (2025)

CLIP with Quality Captions: A Strong Pretraining for Vision Tasks
par: Vasu, Pavan Kumar Anasosalu, et autres
Publié: (2024)

Negative Label Guided OOD Detection with Pretrained Vision-Language Models
par: Jiang, Xue, et autres
Publié: (2024)

TESPEC: Temporally-Enhanced Self-Supervised Pretraining for Event Cameras
par: Mohammadi, Mohammad, et autres
Publié: (2025)

Self-supervised Pretraining for Cardiovascular Magnetic Resonance Cine Segmentation
par: de Mooij, Rob A. J., et autres
Publié: (2024)

Dataset Distillation for Pre-Trained Self-Supervised Vision Models
par: Cazenavette, George, et autres
Publié: (2025)

Self-Distillation of Hidden Layers for Self-Supervised Representation Learning
par: Lowe, Scott C., et autres
Publié: (2026)

MAM-CLIP: Vision-Language Pretraining on Mammography Atlases for BI-RADS Classification
par: Gulluk, Halil Ibrahim, et autres
Publié: (2026)

MASSV: Multimodal Adaptation and Self-Data Distillation for Speculative Decoding of Vision-Language Models
par: Ganesan, Mugilan, et autres
Publié: (2025)

Improving Generative Adversarial Networks with Self-Distillation
par: Nowinowski, Antoni, et autres
Publié: (2026)

Debiasify: Self-Distillation for Unsupervised Bias Mitigation
par: Bayasi, Nourhan, et autres
Publié: (2024)

Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation
par: Zhou, Mingyuan, et autres
Publié: (2024)

Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers?
par: Li, Yihao, et autres
Publié: (2025)

Video-Language Critic: Transferable Reward Functions for Language-Conditioned Robotics
par: Alakuijala, Minttu, et autres
Publié: (2024)

SatDINO: A Deep Dive into Self-Supervised Pretraining for Remote Sensing
par: Straka, Jakub, et autres
Publié: (2025)

TeD-Loc: Text Distillation for Weakly Supervised Object Localization
par: Murtaza, Shakeeb, et autres
Publié: (2025)

Optimizing YOLOv5s Object Detection through Knowledge Distillation algorithm
par: Huang, Guanming, et autres
Publié: (2024)

Universal Pose Pretraining for Generalizable Vision-Language-Action Policies
par: Lin, Haitao, et autres
Publié: (2026)

The Role of Masking for Efficient Supervised Knowledge Distillation of Vision Transformers
par: Son, Seungwoo, et autres
Publié: (2023)

Federated EndoViT: Pretraining Vision Transformers via Federated Learning on Endoscopic Image Collections
par: Kirchner, Max, et autres
Publié: (2025)

LLM-Guided Diagnostic Evidence Alignment for Medical Vision-Language Pretraining under Limited Pairing
par: Yan, Huimin, et autres
Publié: (2026)

OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks
par: Sirko-Galouchenko, Sophia, et autres
Publié: (2024)

Image Clustering Algorithm Based on Self-Supervised Pretrained Models and Latent Feature Distribution Optimization
par: Zhu, Qiuyu, et autres
Publié: (2024)

Mitigating Instance-Dependent Label Noise: Integrating Self-Supervised Pretraining with Pseudo-Label Refinement
par: Bala, Gouranga, et autres
Publié: (2024)

Self-Supervised Pretraining on Satellite Imagery: a Case Study on Label-Efficient Vehicle Detection
par: BOURCIER, Jules, et autres
Publié: (2022)

UniTable: Towards a Unified Framework for Table Recognition via Self-Supervised Pretraining
par: Peng, ShengYun, et autres
Publié: (2024)

OccamVTS: Distilling Vision Models to 1% Parameters for Time Series Forecasting
par: Lyu, Sisuo, et autres
Publié: (2025)

PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization
par: Chen, Zining, et autres
Publié: (2024)

LIB-KD: Teaching Inductive Bias for Efficient Vision Transformer Distillation and Compression
par: Habib, Gousia, et autres
Publié: (2023)