Cover Image

Emerging Property of Masked Token for Effective Pre-training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Choi, Hyesong, Lee, Hunsang, Joung, Seyoung, Park, Hyejin, Kim, Jiyeong, Min, Dongbo
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Salience-Based Adaptive Masking: Revisiting Token Dynamics for Enhanced Pre-training
by: Choi, Hyesong, et al.
Published: (2024)

SG-MIM: Structured Knowledge Guided Efficient Pre-training for Dense Prediction
by: Son, Sumin, et al.
Published: (2024)

Enhancing Alignment for Unified Multimodal Models via Semantically-Grounded Supervision
by: Kim, Jiyeong, et al.
Published: (2026)

MaDis-Stereo: Enhanced Stereo Matching via Distilled Masked Image Modeling
by: Ahn, Jihye, et al.
Published: (2024)

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models
by: Choi, Hyesong, et al.
Published: (2024)

RobIA: Robust Instance-aware Continual Test-time Adaptation for Deep Stereo
by: Ko, Jueun, et al.
Published: (2025)

UniTT-Stereo: Unified Training of Transformer for Enhanced Stereo Matching
by: Kim, Soomin, et al.
Published: (2024)

Dynamic Guidance Adversarial Distillation with Enhanced Teacher Knowledge
by: Park, Hyejin, et al.
Published: (2024)

iConFormer: Dynamic Parameter-Efficient Tuning with Input-Conditioned Adaptation
by: Jo, Hayeon, et al.
Published: (2024)

Collaborative Learning for Enhanced Unsupervised Domain Adaptation
by: Cho, Minhee, et al.
Published: (2024)

TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning
by: Baek, Seungmin, et al.
Published: (2025)

Spatio-Temporal Similarity Volume Aggregation for Open-Vocabulary Action Recognition
by: So, Yerim, et al.
Published: (2026)

Hybrid-TTA: Continual Test-time Adaptation via Dynamic Domain Shift Detection
by: Park, Hyewon, et al.
Published: (2024)

InstantFamily: Masked Attention for Zero-shot Multi-ID Image Generation
by: Kim, Chanran, et al.
Published: (2024)

The Rescue Effect: Spatio-Semantic Early Exit Bypasses Quantization Collapse in CLIP
by: Nam, Kahyeon, et al.
Published: (2026)

FluoCLIP: Stain-Aware Focus Quality Assessment in Fluorescence Microscopy
by: Park, Hyejin, et al.
Published: (2026)

Let Triggers Control: Frequency-Aware Dropout for Effective Token Control
by: Koh, Junyoung, et al.
Published: (2026)

How Effective is Pre-training of Large Masked Autoencoders for Downstream Earth Observation Tasks?
by: Sosa, Jose, et al.
Published: (2024)

Difficulty-Aware Label-Guided Denoising for Monocular 3D Object Detection
by: Lee, Soyul, et al.
Published: (2025)

Efficient Vision-Language Pre-training by Cluster Masking
by: Wei, Zihao, et al.
Published: (2024)

Dataset Ownership Verification for Pre-trained Masked Models
by: Xie, Yuechen, et al.
Published: (2025)

SeiT++: Masked Token Modeling Improves Storage-efficient Training
by: Lee, Minhyun, et al.
Published: (2023)

PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation
by: Kim, Kwonyoung, et al.
Published: (2022)

Masks and Manuscripts: Advancing Medical Pre-training with End-to-End Masking and Narrative Structuring
by: Gowda, Shreyank N, et al.
Published: (2024)

When Eyes Betray AI: Social Gaze Consistency as a Semantic Cue for AI-Generated Image Detection
by: Kim, Jihyeon, et al.
Published: (2026)

Towards Scalable Pre-training of Visual Tokenizers for Generation
by: Yao, Jingfeng, et al.
Published: (2025)

Masked Pre-training Enables Universal Zero-shot Denoiser
by: Ma, Xiaoxiao, et al.
Published: (2024)

Masked Clustering Prediction for Unsupervised Point Cloud Pre-training
by: Ren, Bin, et al.
Published: (2025)

Veta-GS: View-dependent deformable 3D Gaussian Splatting for thermal infrared Novel-view Synthesis
by: Nam, Myeongseok, et al.
Published: (2025)

MaskDiffusion: Exploiting Pre-trained Diffusion Models for Semantic Segmentation
by: Kawano, Yasufumi, et al.
Published: (2024)

Universal Image Restoration Pre-training via Masked Degradation Classification
by: Hu, JiaKui, et al.
Published: (2025)

MaskedCLIP: Bridging the Masked and CLIP Space for Semi-Supervised Medical Vision-Language Pre-training
by: Zhu, Lei, et al.
Published: (2025)

MaskHOI: Robust 3D Hand-Object Interaction Estimation via Masked Pre-training
by: Xie, Yuechen, et al.
Published: (2025)

APPLE: Attribute-Preserving Pseudo-Labeling for Diffusion-Based Face Swapping
by: Kang, Jiwon, et al.
Published: (2026)

SceneNAT: Masked Generative Modeling for Language-Guided Indoor Scene Synthesis
by: Choi, Jeongjun, et al.
Published: (2026)

ERASE: Eliminating Redundant Visual Tokens via Adaptive Two-Stage Token Pruning
by: Lee, Yuna, et al.
Published: (2026)

Hybrid 3D-4D Gaussian Splatting for Fast Dynamic Scene Representation
by: Oh, Seungjun, et al.
Published: (2025)

Long-term Pre-training for Temporal Action Detection with Transformers
by: Kim, Jihwan, et al.
Published: (2024)

MLIP: Medical Language-Image Pre-training with Masked Local Representation Learning
by: Liu, Jiarun, et al.
Published: (2024)

Data-efficient Event Camera Pre-training via Disentangled Masked Modeling
by: Huang, Zhenpeng, et al.
Published: (2024)