Copertina

$Δ$-AttnMask: Attention-Guided Masked Hidden States for Efficient Data Selection and Augmentation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hu, Jucheng, Yang, Suorong, Zhou, Dongzhan
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

When Dynamic Data Selection Meets Data Augmentation
di: Yang, Suorong, et al.
Pubblicazione: (2025)

MaskCD: Mitigating LVLM Hallucinations by Image Head Masked Contrastive Decoding
di: Deng, Jingyuan, et al.
Pubblicazione: (2025)

AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers
di: Achtibat, Reduan, et al.
Pubblicazione: (2024)

Towards Efficient Diffusion-Based Image Editing with Instant Attention Masks
di: Zou, Siyu, et al.
Pubblicazione: (2024)

LOCR: Location-Guided Transformer for Optical Character Recognition
di: Sun, Yu, et al.
Pubblicazione: (2024)

Out-of-Distribution Detection with Attention Head Masking for Multimodal Document Classification
di: Constantinou, Christos, et al.
Pubblicazione: (2024)

Rectified SpaAttn: Revisiting Attention Sparsity for Efficient Video Generation
di: Liu, Xuewen, et al.
Pubblicazione: (2025)

Efficient Masked Attention Transformer for Few-Shot Classification and Segmentation
di: Carrión-Ojeda, Dustin, et al.
Pubblicazione: (2025)

SyncMask: Synchronized Attentional Masking for Fashion-centric Vision-Language Pretraining
di: Song, Chull Hwan, et al.
Pubblicazione: (2024)

Motion Guided Token Compression for Efficient Masked Video Modeling
di: Feng, Yukun, et al.
Pubblicazione: (2024)

Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation
di: Yu, Seonghoon, et al.
Pubblicazione: (2026)

AttnMod: Attention-Based New Art Styles
di: Su, Shih-Chieh
Pubblicazione: (2024)

A CLIP-Powered Framework for Robust and Generalizable Data Selection
di: Yang, Suorong, et al.
Pubblicazione: (2024)

MaskAnyNet: Rethinking Masked Image Regions as Valuable Information in Supervised Learning
di: Hong, Jingshan, et al.
Pubblicazione: (2025)

MAST: Mask-Guided Attention Mass Allocation for Training-Free Multi-Style Transfer
di: Kang, Dongkyung, et al.
Pubblicazione: (2026)

Mask-aware Text-to-Image Retrieval: Referring Expression Segmentation Meets Cross-modal Retrieval
di: Shen, Li-Cheng, et al.
Pubblicazione: (2025)

Comp-Attn: Present-and-Align Attention for Compositional Video Generation
di: Zhang, Hongyu, et al.
Pubblicazione: (2025)

ASPIRE: Language-Guided Data Augmentation for Improving Robustness Against Spurious Correlations
di: Ghosh, Sreyan, et al.
Pubblicazione: (2023)

Attention-Guided Integration of CLIP and SAM for Precise Object Masking in Robotic Manipulation
di: Muttaqien, Muhammad A., et al.
Pubblicazione: (2025)

Rethinking Causal Mask Attention for Vision-Language Inference
di: Pei, Xiaohuan, et al.
Pubblicazione: (2025)

RIV: Recursive Introspection Mask Diffusion Vision Language Model
di: Li, YuQian, et al.
Pubblicazione: (2025)

Domain-Guided Masked Autoencoders for Unique Player Identification
di: Balaji, Bavesh, et al.
Pubblicazione: (2024)

Masked Generative Story Transformer with Character Guidance and Caption Augmentation
di: Papadimitriou, Christos, et al.
Pubblicazione: (2024)

UrFound: Towards Universal Retinal Foundation Models via Knowledge-Guided Masked Modeling
di: Yu, Kai, et al.
Pubblicazione: (2024)

Gradient-Guided Parameter Mask for Multi-Scenario Image Restoration Under Adverse Weather
di: Guo, Jilong, et al.
Pubblicazione: (2024)

MaGGIe: Masked Guided Gradual Human Instance Matting
di: Huynh, Chuong, et al.
Pubblicazione: (2024)

Salient Mask-Guided Vision Transformer for Fine-Grained Classification
di: Demidov, Dmitry, et al.
Pubblicazione: (2023)

When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMs
di: Zhao, Beidi, et al.
Pubblicazione: (2026)

Mask & Match: Learning to Recognize Handwritten Math with Self-Supervised Attention
di: Mitra, Shree, et al.
Pubblicazione: (2025)

Mamba-3D as Masked Autoencoders for Accurate and Data-Efficient Analysis of Medical Ultrasound Videos
di: Zhou, Jiaheng, et al.
Pubblicazione: (2025)

Resource-Efficient Motion Control for Video Generation via Dynamic Mask Guidance
di: Feng, Sicong, et al.
Pubblicazione: (2025)

Pan-FM: A Pan-Organ Foundation Model with Saliency-Guided Masking for Missing Robustness
di: Wu, Qiangqiang, et al.
Pubblicazione: (2026)

MaS-VQA: A Mask-and-Select Framework for Knowledge-Based Visual Question Answering
di: Mao, Xianwei, et al.
Pubblicazione: (2026)

DiffAttn: Diffusion-Based Drivers' Visual Attention Prediction with LLM-Enhanced Semantic Reasoning
di: Liu, Weimin, et al.
Pubblicazione: (2026)

MedSegFactory: Text-Guided Generation of Medical Image-Mask Pairs
di: Mao, Jiawei, et al.
Pubblicazione: (2025)

Gaussian Masked Autoencoders
di: Rajasegaran, Jathushan, et al.
Pubblicazione: (2025)

Triple Point Masking
di: Liu, Jiaming, et al.
Pubblicazione: (2024)

Data Metabolism: An Efficient Data Design Schema For Vision Language Model
di: Zhang, Jingyuan, et al.
Pubblicazione: (2025)

Masked Latent Transformer with the Random Masking Ratio to Advance the Diagnosis of Dental Fluorosis
di: Wu, Yun, et al.
Pubblicazione: (2024)

HU-based Foreground Masking for 3D Medical Masked Image Modeling
di: Lee, Jin, et al.
Pubblicazione: (2025)