paper-with-me

Papers

HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning

2022-01-11 · Andrey Zhmoginov, Mark Sandler, Max Vladymyrov

In this work we propose a HyperTransformer, a Transformer-based model for supervised and semi-supervised few-shot learning that generates weights of a convolutional neural network (CNN) directly from support samples. Since the dependence of a small generated CNN model on a specific task is encoded by a high-capacity Transformer model, we effectively decouple the complexity of the large task space from the complexity of individual tasks. Our method is particularly effective for small target CNN architectures where learning a fixed universal task-independent embedding is not optimal and better performance is attained when the information about the task can modulate all model parameters. For larger models we discover that generating the last layer alone allows us to produce competitive or better results than those obtained with state-of-the-art methods while being end-to-end differentiable.

📄 PDF Abstract BibTeX arXiv:2201.04182

Code (2)

google-research/google-research/tree/master/hypertransformer 공식 구현 jax
shyamsn97/hyper-nn jax

Tasks

Few-Shot Image ClassificationFew-Shot Learning

Methods 이 논문이 사용한 방법론

Multi-Head 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 $x$…
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…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
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…
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

HyperTransformer: Attention-Based CNN Model Generation from Few Samples

2021-09-29 · Andrey Zhmoginov, Max Vladymyrov, Mark Sandler

In this work we propose a HyperTransformer, a transformer based model that generates all weights of a CNN model directly from the support samples. This approach allows to use a high-capacity model for encoding task-depen…

Few-Shot Learning

Continual HyperTransformer: A Meta-Learner for Continual Few-Shot Learning

2023-01-11 · Max Vladymyrov, Andrey Zhmoginov, Mark Sandler

We focus on the problem of learning without forgetting from multiple tasks arriving sequentially, where each task is defined using a few-shot episode of novel or already seen classes. We approach this problem using the r…

class-incremental learningClass Incremental Learningcontinual few-shot learningContinual Learning+2

StrokeGAN+: Few-Shot Semi-Supervised Chinese Font Generation with Stroke Encoding

2022-11-11 · Jinshan Zeng, Yefei Wang, Qi Chen, Yunxin Liu 외

The generation of Chinese fonts has a wide range of applications. The currently predominated methods are mainly based on deep generative models, especially the generative adversarial networks (GANs). However, existing GA…

Font Generation

HyperTransformer: A Textural and Spectral Feature Fusion Transformer for Pansharpening

2022-03-04 · CVPR 2022 1 · Wele Gedara Chaminda Bandara, Vishal M. Patel

Pansharpening aims to fuse a registered high-resolution panchromatic image (PAN) with a low-resolution hyperspectral image (LR-HSI) to generate an enhanced HSI with high spectral and spatial resolution. Existing pansharp…

PansharpeningSuper-Resolution

Empirical Perspectives on One-Shot Semi-supervised Learning

2020-04-08 · Leslie N. Smith, Adam Conovaloff

One of the greatest obstacles in the adoption of deep neural networks for new applications is that training the network typically requires a large number of manually labeled training samples. We empirically investigate t…

image-classificationImage Classification