Structure-Guided Masked Autoencoders for Ultra-High Resolution Scientific Image Understanding

arXiv:2609.30682 · cs.CV · Submitted 2026-09-25 · Read on arXiv

cs.CV

Submitted: 2026-09-25

Updated: 2026-09-25

Terminology

• Transformer — 57× in this paper · explained in 2 episodes
• Fine-Tuning — 16× in this paper · explained in 5 episodes
• Accuracy — 15× in this paper · explained in 1 episode
• Tokenization — 12× in this paper · explained in 2 episodes
• Ablation — 8× in this paper · explained in 1 episode
• Structure-Guided Feature Tokenizer — 7× in this paper
• Ultra-High Resolution — 7× in this paper
• Attention Mechanism — 5× in this paper · explained in 3 episodes
• Damped Accumulation — 5× in this paper
• Benchmark — 4× in this paper · explained in 2 episodes
• Core — 4× in this paper · explained in 2 episodes
• Downstream Tasks — 4× in this paper · explained in 2 episodes
• International Conference on Learning Representations — 3× in this paper
• Self-Supervised Learning — 3× in this paper · explained in 8 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Conference on Computer Vision and Pattern Recognition — 2× in this paper
• Contrastive Learning — 2× in this paper · explained in 5 episodes
• Masked Autoencoder (MAE) — 2× in this paper · explained in 5 episodes
• Objective Function — 2× in this paper · explained in 2 episodes
• Sparse Attention — 2× in this paper · explained in 5 episodes
• Sparsity — 2× in this paper · explained in 4 episodes
• Transformer Models — 2× in this paper · explained in 2 episodes
• X-ray Computed Tomography — 2× in this paper
• Adaptivity — 1× in this paper · explained in 1 episode
• Additivity — 1× in this paper · explained in 1 episode
• Fidelity — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Segmentation Masks — 1× in this paper · explained in 2 episodes
• Transformer Architecture — 1× in this paper · explained in 2 episodes
• Vision Transformer (ViT) — 1× in this paper · explained in 2 episodes

Sources

• ETC: Encoding Long and Structured Inputs in Transformers
• Longformer: The Long-Document Transformer
• TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
• Generating Long Sequences with Sparse Transformers
• Rethinking Attention with Performers
• FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
• Reformer: The Efficient Transformer
• U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation
• SPFormer: Enhancing Vision Transformer with Superpixel Representation
• SAM 2: Segment Anything in Images and Videos
• Three-level Hierarchical Transformer Networks for Long-sequence and Multiple Clinical Documents Classification
• QuadTree Attention for Vision Transformers
• Ultra-Long Sequence Distributed Transformer
• ORBIT-2: Scaling Exascale Vision Foundation Models for Weather and Climate Downscaling
• DeepSeek-OCR: Contexts Optical Compression
• Topology-Preserving Segmentation Network: A Deep Learning Segmentation Framework for Connected Component

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models