paper-with-me

홈 › Papers

Retina Vision Transformer (RetinaViT): Introducing Scaled Patches into Vision Transformers

2024-03-20 · Yuyang Shu, Michael E. Bain

Humans see low and high spatial frequency components at the same time, and combine the information from both to form a visual scene. Drawing on this neuroscientific inspiration, we propose an altered Vision Transformer architecture where patches from scaled down versions of the input image are added to the input of the first Transformer Encoder layer. We name this model Retina Vision Transformer (RetinaViT) due to its inspiration from the human visual system. Our experiments show that when trained on the ImageNet-1K dataset with a moderate configuration, RetinaViT achieves a 3.3% performance improvement over the original ViT. We hypothesize that this improvement can be attributed to the inclusion of low spatial frequency components in the input, which improves the ability to capture structural features, and to select and forward important features to deeper layers. RetinaViT thereby opens doors to further investigations into vertical pathways and attention patterns.

📄 PDF Abstract BibTeX arXiv:2403.13677

Code (1)

yuyangshu/retinavit 공식 구현 jax

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Position-Wise Feed-Forward Layer 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Pyramid U-Net for Retinal Vessel Segmentation

2021-04-06 · Jiawei Zhang, Yanchun Zhang, Xiaowei Xu

Retinal blood vessel can assist doctors in diagnosis of eye-related diseases such as diabetes and hypertension, and its segmentation is particularly important for automatic retinal image analysis. However, it is challeng…

DecoderRetinal Vessel SegmentationSegmentation

MoCoViT: Mobile Convolutional Vision Transformer

2022-05-25 · Hailong Ma, Xin Xia, Xing Wang, Xuefeng Xiao 외

Recently, Transformer networks have achieved impressive results on a variety of vision tasks. However, most of them are computationally expensive and not suitable for real-world mobile applications. In this work, we pres…

object-detectionObject Detection

Benchmarking Convolutional, Transformer, Hybrid, and Vision Language Models for Multi Disease Retinal Screening

2026-05-25 · Durjoy Dey, Aymane Ajbar, Yuhong Yan arxiv

Modern deep learning offers powerful tools for automated retinal screening, but it remains unclear how different visual model families compare in realistic multi-disease settings and under domain shift. In this work, we …

Multi-Label Classification

VTGAN: Semi-supervised Retinal Image Synthesis and Disease Prediction using Vision Transformers

2021-04-14 · Sharif Amit Kamran, Khondker Fariha Hossain, Alireza Tavakkoli, Stewart Lee Zuckerbrod 외

In Fluorescein Angiography (FA), an exogenous dye is injected in the bloodstream to image the vascular structure of the retina. The injected dye can cause adverse reactions such as nausea, vomiting, anaphylactic shock, a…

Disease PredictionFundus to Angiography GenerationGenerative Adversarial NetworkImage Generation

TSPTQ-ViT: Two-scaled post-training quantization for vision transformer

2023-05-22 · Yu-Shan Tai, Ming-Guang Lin, An-Yeu, Wu

Vision transformers (ViTs) have achieved remarkable performance in various computer vision tasks. However, intensive memory and computation requirements impede ViTs from running on resource-constrained edge devices. Due …

Quantization