Learning Embedding Adaptation for Few-Shot Learning

最新推荐文章于 2024-09-26 07:11:45 发布

wuxtwu

最新推荐文章于 2024-09-26 07:11:45 发布

阅读量693

点赞数

CC 4.0 BY-SA版权

分类专栏： AI

本文链接：https://blog.youkuaiyun.com/xnmc2014/article/details/87730024

AI 专栏收录该内容

32 篇文章

订阅专栏

本文介绍了一种利用Transformer架构实现的自适应策略，该策略通过学习一个实例嵌入函数来处理少样本学习任务。这种方法从已知类别中学习判别性的实例嵌入模型，并将其应用于未知类别的实例，尤其是在有限的标签情况下。通过自我注意力机制，每个实例的嵌入可以考虑其上下文信息，从而改善嵌入质量。实验表明，使用排列不变的集函数代替序列模型可以提高模型的效果。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Abstract

by learning an instance embedding function from seen classes, and apply the function to instances from unseen classes with limited labels.
usually learn a discriminative instance embedding model from the SEEN categories, and apply the embedding model to visual data in UNSEEN categories
no-parametric classifiers to avoid learning complicated recognition models from a small number of examples.
The most useful features for discerning “cat” versus “tiger” could be irrelevant and noise to the task of discerning “cat” versus “dog”

Introduce

What is lacking in the current approaches for few-shot learning is an adaptation strategy that tailors the visual knowledge extracted from the SEEN classes to the UNSEEN ones in a target task. In other words, we desire separate embedding spaces where each one of them is customized such that the visual features are most discriminative for a given task
The key assumption is that the embeddings capture all necessarily discriminative representations of data such that simple classifiers are sufficed。
We use the Transformer architecture to implement T. In particular, we employes self-attention mechanism to improve each instance embedding with consideration to its contextual embedding

实验

use pre-train??

to demonstrate the effectiveness of using a permutation-invariant set function instead of a sequence model. Please see supplementary for details.
Transformer is set-to-set transformation
customizes a task-specific embedding spaces via a self-attention architecture