paper-with-me

홈 › Papers

Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles

2023-06-01 · Chaitanya Ryali, Yuan-Ting Hu, Daniel Bolya, Chen Wei, Haoqi Fan, Po-Yao Huang, Vaibhav Aggarwal, Arkabandhu Chowdhury, Omid Poursaeed, Judy Hoffman, Jitendra Malik, Yanghao Li, Christoph Feichtenhofer

Modern hierarchical vision transformers have added several vision-specific components in the pursuit of supervised classification performance. While these components lead to effective accuracies and attractive FLOP counts, the added complexity actually makes these transformers slower than their vanilla ViT counterparts. In this paper, we argue that this additional bulk is unnecessary. By pretraining with a strong visual pretext task (MAE), we can strip out all the bells-and-whistles from a state-of-the-art multi-stage vision transformer without losing accuracy. In the process, we create Hiera, an extremely simple hierarchical vision transformer that is more accurate than previous models while being significantly faster both at inference and during training. We evaluate Hiera on a variety of tasks for image and video recognition. Our code and models are available at https://github.com/facebookresearch/hiera.

📄 PDF Abstract BibTeX arXiv:2306.00989

Code (4)

facebookresearch/hiera 공식 구현 pytorch
huggingface/pytorch-image-models pytorch
leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/hiera tf
https://gitlab.com/birder/birder pytorch

Tasks

Action ClassificationAction RecognitionAction Recognition In VideosImage ClassificationInstance SegmentationObject DetectionVideo Recognition

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 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…
Residual Connection 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
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 $x$…
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…

Similar Papers 제목 키워드 기반

Cutting the Skip: Training Residual-Free Transformers

2025-09-30 · Yiping Ji, James Martens, Jianqiao Zheng, Ziqin Zhou 외 arxiv

Transformers have achieved remarkable success across a wide range of applications, a feat often attributed to their scalability. Yet training them without skip (residual) connections remains notoriously difficult. While …

Representation Learning

Stochastic Layer-Wise Shuffle: A Good Practice to Improve Vision Mamba Training

2024-08-30 · Zizheng Huang, Haoxing Chen, Jiaqi Li, Jun Lan 외

Recent Vision Mamba models not only have much lower complexity for processing higher resolution images and longer videos but also the competitive performance with Vision Transformers (ViTs). However, they are stuck into …

Image ClassificationMambaObject DetectionSemantic Segmentation

Exploring Plain Vision Transformer Backbones for Object Detection

2022-03-30 · Yanghao Li, Hanzi Mao, Ross Girshick, Kaiming He

We explore the plain, non-hierarchical Vision Transformer (ViT) as a backbone network for object detection. This design enables the original ViT architecture to be fine-tuned for object detection without needing to redes…

Cross-Domain Few-Shot Object DetectionInstance SegmentationObjectobject-detection+1

HiViT: Hierarchical Vision Transformer Meets Masked Image Modeling

2022-05-30 · Xiaosong Zhang, Yunjie Tian, Wei Huang, Qixiang Ye 외

Recently, masked image modeling (MIM) has offered a new methodology of self-supervised pre-training of vision transformers. A key idea of efficient implementation is to discard the masked image patches (or tokens) throug…

Transfer Learning

Hierarchical Vision Transformers for Context-Aware Prostate Cancer Grading in Whole Slide Images

2023-12-19 · Clément Grisi, Geert Litjens, Jeroen van der Laak

Vision Transformers (ViTs) have ushered in a new era in computer vision, showcasing unparalleled performance in many challenging tasks. However, their practical deployment in computational pathology has largely been cons…

whole slide images