Copertina

Salience-Based Adaptive Masking: Revisiting Token Dynamics for Enhanced Pre-training

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Choi, Hyesong, Park, Hyejin, Yi, Kwang Moo, Cha, Sungmin, Min, Dongbo
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

Emerging Property of Masked Token for Effective Pre-training
di: Choi, Hyesong, et al.
Pubblicazione: (2024)

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

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

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

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

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

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

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

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

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

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

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

Hyperparameters in Continual Learning: A Reality Check
di: Cha, Sungmin, et al.
Pubblicazione: (2024)

Revisiting Deep Ensemble Uncertainty for Enhanced Medical Anomaly Detection
di: Gu, Yi, et al.
Pubblicazione: (2024)

Can Natural Image Autoencoders Compactly Tokenize fMRI Volumes for Long-Range Dynamics Modeling?
di: Kim, Peter Yongho, et al.
Pubblicazione: (2026)

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

Follow the Saliency: Supervised Saliency for Retrieval-augmented Dense Video Captioning
di: Choi, Seung hee, et al.
Pubblicazione: (2026)

DTFSal: Audio-Visual Dynamic Token Fusion for Video Saliency Prediction
di: Hooshanfar, Kiana, et al.
Pubblicazione: (2025)

Making Video Models Adhere to User Intent with Minor Adjustments
di: Ajisafe, Daniel, et al.
Pubblicazione: (2026)

Radiant Foam: Real-Time Differentiable Ray Tracing
di: Govindarajan, Shrisudhan, et al.
Pubblicazione: (2025)

Evaluating Alternatives to SFM Point Cloud Initialization for Gaussian Splatting
di: Foroutan, Yalda, et al.
Pubblicazione: (2024)

Enhancing SAR Object Detection with Self-Supervised Pre-training on Masked Auto-Encoders
di: Pu, Xinyang, et al.
Pubblicazione: (2025)

SMCL: Saliency Masked Contrastive Learning for Long-tailed Recognition
di: Park, Sanglee, et al.
Pubblicazione: (2024)

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

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

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

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

ALTo: Adaptive-Length Tokenizer for Autoregressive Mask Generation
di: Wang, Lingfeng, et al.
Pubblicazione: (2025)

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

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

Volumetric Rendering with Baked Quadrature Fields
di: Sharma, Gopal, et al.
Pubblicazione: (2023)

Reinforcement Learning meets Masked Video Modeling : Trajectory-Guided Adaptive Token Selection
di: Rai, Ayush K., et al.
Pubblicazione: (2025)

Are We Truly Forgetting? A Critical Re-examination of Machine Unlearning Evaluation Protocols
di: Kim, Yongwoo, et al.
Pubblicazione: (2025)

Towards Realistic Incremental Scenario in Class Incremental Semantic Segmentation
di: Kwak, Jihwan, et al.
Pubblicazione: (2024)

MaskAdapt: Learning Flexible Motion Adaptation via Mask-Invariant Prior for Physics-Based Characters
di: Park, Soomin, et al.
Pubblicazione: (2026)

Revisiting Continual Semantic Segmentation with Pre-trained Vision Models
di: Zhang, Duzhen, et al.
Pubblicazione: (2025)

MMCOMPOSITION: Revisiting the Compositionality of Pre-trained Vision-Language Models
di: Hua, Hang, et al.
Pubblicazione: (2024)

ROODI: Reconstructing Occluded Objects with Denoising Inpainters
di: Chang, Yeonjin, et al.
Pubblicazione: (2025)

LSE-NeRF: Learning Sensor Modeling Errors for Deblured Neural Radiance Fields with RGB-Event Stereo
di: Tang, Wei Zhi, et al.
Pubblicazione: (2024)