paper-with-me

홈 › Papers

Memory transformers for full context and high-resolution 3D Medical Segmentation

2022-10-11 · Loic Themyr, Clément Rambour, Nicolas Thome, Toby Collins, Alexandre Hostettler

Transformer models achieve state-of-the-art results for image segmentation. However, achieving long-range attention, necessary to capture global context, with high-resolution 3D images is a fundamental challenge. This paper introduces the Full resolutIoN mEmory (FINE) transformer to overcome this issue. The core idea behind FINE is to learn memory tokens to indirectly model full range interactions while scaling well in both memory and computational costs. FINE introduces memory tokens at two levels: the first one allows full interaction between voxels within local image regions (patches), the second one allows full interactions between all regions of the 3D volume. Combined, they allow full attention over high resolution images, e.g. 512 x 512 x 256 voxels and above. Experiments on the BCV image segmentation dataset shows better performances than state-of-the-art CNN and transformer baselines, highlighting the superiority of our full attention mechanism compared to recent transformer baselines, e.g. CoTr, and nnFormer.

📄 PDF Abstract BibTeX arXiv:2210.05313

Code (0)

등록된 구현이 없습니다.

Tasks

Image SegmentationSegmentationSemantic SegmentationVocal Bursts Intensity Prediction

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
Multi-Head Attention 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

MCUFormer: Deploying Vision Transformers on Microcontrollers with Limited Memory

2023-10-25 · NeurIPS 2023 11 · Yinan Liang, Ziwei Wang, Xiuwei Xu, Yansong Tang 외

Due to the high price and heavy energy consumption of GPUs, deploying deep models on IoT devices such as microcontrollers makes significant contributions for ecological AI. Conventional methods successfully enable convol…

image-classificationImage Classification

HiResNets: Native Full-HD Video Recognition with Foveal Residual Streams

2026-08-03 · Shivani Mall, Swarnim Jain, Joao F. Henriques arxiv

Much of the recent progress in image and video recognition has come at the cost of memory: larger models, increased resolution, and longer temporal contexts. An inevitable component is the quadratic (or larger) growth of…

Full-resolution MLPs Empower Medical Dense Prediction

2023-11-28 · Mingyuan Meng, Yuxin Xue, Dagan Feng, Lei Bi 외

Dense prediction is a fundamental requirement for many medical vision tasks such as medical image restoration, registration, and segmentation. The most popular vision model, Convolutional Neural Networks (CNNs), has reac…

AnatomyImage RestorationPrediction

Correlation-aware Coarse-to-fine MLPs for Deformable Medical Image Registration

2024-05-31 · CVPR 2024 1 · Mingyuan Meng, Dagan Feng, Lei Bi, Jinman Kim

Deformable image registration is a fundamental step for medical image analysis. Recently, transformers have been used for registration and outperformed Convolutional Neural Networks (CNNs). Transformers can capture long-…

Deformable Medical Image RegistrationImage RegistrationInductive BiasMedical Image Analysis+1

Full Contextual Attention for Multi-resolution Transformers in Semantic Segmentation

2022-12-15 · Loic Themyr, Clement Rambour, Nicolas Thome, Toby Collins 외

Transformers have proved to be very effective for visual recognition tasks. In particular, vision transformers construct compressed global representations through self-attention and learnable class tokens. Multi-resoluti…

Semantic Segmentation