paper-with-me

Papers

Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding

2021-05-26 · Zizhao Zhang, Han Zhang, Long Zhao, Ting Chen, Sercan O. Arik, Tomas Pfister

Hierarchical structures are popular in recent vision transformers, however, they require sophisticated designs and massive datasets to work well. In this paper, we explore the idea of nesting basic local transformers on non-overlapping image blocks and aggregating them in a hierarchical way. We find that the block aggregation function plays a critical role in enabling cross-block non-local information communication. This observation leads us to design a simplified architecture that requires minor code changes upon the original vision transformer. The benefits of the proposed judiciously-selected design are threefold: (1) NesT converges faster and requires much less training data to achieve good generalization on both ImageNet and small datasets like CIFAR; (2) when extending our key ideas to image generation, NesT leads to a strong decoder that is 8$\times$ faster than previous transformer-based generators; and (3) we show that decoupling the feature learning and abstraction processes via this nested hierarchy in our design enables constructing a novel method (named GradCAT) for visually interpreting the learned model. Source code is available https://github.com/google-research/nested-transformer.

📄 PDF Abstract BibTeX arXiv:2105.12723

Code (6)

google-research/nested-transformer 공식 구현 jax
ahmedelmahy/myownvit pytorch
conceptofmind/NesT-flax jax
freder-chen/vitp pytorch
rwightman/pytorch-image-models pytorch
ttt496/vit-pytorch pytorch

Tasks

DecoderImage ClassificationImage Generation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
NesT NesT stacks canonical transformer layers to conduct local self-attention on every image block independently, and then "nests" them hierarchically. Coupling of processed…
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
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…
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 $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

HiTRANS: A Hierarchical Transformer Network for Nested Named Entity Recognition

2021-11-01 · Findings (EMNLP) 2021 11 · Zhiwei Yang, Jing Ma, Hechang Chen, Yunke Zhang 외

Nested Named Entity Recognition (NNER) has been extensively studied, aiming to identify all nested entities from potential spans (i.e., one or more continuous tokens). However, recent studies for NNER either focus on ted…

named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)Nested Named Entity Recognition+2

Nested-TNT: Hierarchical Vision Transformers with Multi-Scale Feature Processing

2024-04-20 · Yuang Liu, Zhiheng Qiu, Xiaokai Qin

Transformer has been applied in the field of computer vision due to its excellent performance in natural language processing, surpassing traditional convolutional neural networks and achieving new state-of-the-art. ViT d…

image-classificationImage ClassificationSentence

Hierarchical Reinforcement Learning with Deep Nested Agents

2018-05-18 · Marc Brittain, Peng Wei

Deep hierarchical reinforcement learning has gained a lot of attention in recent years due to its ability to produce state-of-the-art results in challenging environments where non-hierarchical frameworks fail to learn us…

Hierarchical Reinforcement LearningMinecraftreinforcement-learningReinforcement Learning+1

Sparse Hierarchical Tucker Factorization and its Application to Healthcare

2016-10-25 · Ioakeim Perros, Robert Chen, Richard Vuduc, Jimeng Sun

We propose a new tensor factorization method, called the Sparse Hierarchical-Tucker (Sparse H-Tucker), for sparse and high-order data tensors. Sparse H-Tucker is inspired by its namesake, the classical Hierarchical Tucke…

Forming Trees with Treeformers

2022-07-14 · Nilay Patel, Jeffrey Flanigan

Human language is known to exhibit a nested, hierarchical structure, allowing us to form complex sentences out of smaller pieces. However, many state-of-the-art neural networks models such as Transformers have no explici…

Abstractive Text SummarizationInductive BiasMachine TranslationNatural Language Understanding+1