深度学习小样本学习：注意力驱动的Stanet在AAAI19中的应用

需积分: 34 193 浏览量更新于2024-09-04 1 收藏 1.26MB PDF 举报

深度学习小样本学习是当前研究领域的热点问题，特别是在处理有限标注数据时，如何提高模型的泛化能力和适应性。这篇名为"ADualAttentionNetworkwithSemanticEmbeddingforFew-shotLearning"的论文（stanet_aaai19.pdf）由Shipeng Yan、Songyang Zhang和Xuming He在2019年AAAI会议上提出，针对这一挑战提出了新颖的解决方案。论文的核心内容关注于构建一个高效的小样本学习框架，即元学习方法。传统的元学习策略依赖于全局图像表示和复杂的模型结构，这可能导致对背景噪音敏感且难以解释。作者意识到这些问题，他们提出了一种基于双重视角注意力机制的网络模型。首先，他们引入了空间注意力机制，旨在通过定位图像中的关键区域来增强模型对目标对象的识别能力。这种局部聚焦有助于减少无关背景对学习的影响，提高模型的针对性。其次，他们采用了任务注意力机制，目的是在小样本学习环境中，通过选择相似的训练数据进行预测，从而增强模型的迁移学习能力。论文的核心创新在于设计了一个双注意力网络（Dual-Attention Network），该网络结合了这两种注意力机制，使得模型能够智能地提取特征并选择有用的信息。此外，他们还设计了一种语义感知的元学习损失函数，用于训练这个元学习网络。这种损失函数不仅考虑了数据的视觉特征，还纳入了语义信息，进一步提高了模型对新概念的泛化性能。这篇论文提供了一个有效的深度学习小样本学习框架，通过简单的注意力机制和巧妙的网络设计，解决了小样本情况下模型泛化和理解的问题，对于那些关注小样本学习和深度学习方向的研究人员来说，具有很高的参考价值。通过学习和应用这些方法，研究人员可以更好地应对现实世界中数据稀缺但需求快速学习新概念的挑战。

A Dual Attention Network with Semantic Embedding for Few-shot Learning

Shipeng Yan

∗

, Songyang Zhang

∗

, Xuming He

†

School of Information Science and Technology, ShanghaiTech University

{yanshp, zhangsy1, hexm}@shanghaitech.edu.cn

Abstract

Despite recent success of deep neural networks, it remains

challenging to efﬁciently learn new visual concepts from lim-

ited training data. To address this problem, a prevailing strat-

egy is to build a meta-learner that learns prior knowledge

on learning from a small set of annotated data. However,

most of existing meta-learning approaches rely on a global

representation of images and a meta-learner with complex

model structures, which are sensitive to background clutter

and difﬁcult to interpret. We propose a novel meta-learning

method for few-shot classiﬁcation based on two simple at-

tention mechanisms: one is a spatial attention to localize

relevant object regions and the other is a task attention to

select similar training data for label prediction. We imple-

ment our method via a dual-attention network and design a

semantic-aware meta-learning loss to train the meta-learner

network in an end-to-end manner. We validate our model on

three few-shot image classiﬁcation datasets with extensive

ablative study, and our approach shows competitive perfor-

mances over these datasets with fewer parameters. For facil-

itating the future research, code and data split are available:

https://github.com/tonysy/STANet-PyTorch

1 Introduction

A particular intriguing property of human cognition is be-

ing able to learn a new concept from only a few exam-

ples, which, despite recent success of deep learning, remains

a challenging task for machine learning systems (Lake et

al. 2017). Such a few-shot learning problem setting has at-

tracted much attention recently, and in particular, for the

task of classiﬁcation (Lake, Salakhutdinov, and Tenenbaum

2015; Vinyals et al. 2016; Triantaﬁllou, Zemel, and Urta-

sun 2017). To tackle the issue of data deﬁciency, a pre-

vailing strategy of few-shot classiﬁcation is to formulate

it as a meta-learning problem, aiming to learn a prior on

the few-shot classiﬁers from a set of similar classiﬁcation

tasks (Vinyals et al. 2016; Mishra et al. 2018). Typically, a

meta-learner learns an embedding that maps the input into

a feature space and a predictor that transfers the label infor-

mation from the training set of each task to its test instance.

∗

Authors contributed equally and are listed in alphabetical order

†

In part supported by the NSFC Grant No. 61703195.

 2019, Association for the Advancement of Artiﬁcial

While this learning framework is capable of extracting ef-

fective meta-level prediction strategy, it suffers several lim-

itations in the task of image classiﬁcation. First, the i.i.d as-

sumption on tasks tends to ignore the semantic relations be-

tween image classes that reﬂects the intrinsic similarity be-

tween individual tasks. This can lead to inefﬁcient embed-

ding feature learning. Second, most of existing work rely on

an off-the-shelf deep network to compute a holistic feature

of each input image, which is sensitive to nuisance varia-

tions, e.g, background clutter. This makes it challenging to

learn an effective meta-learner, particularly for the methods

based on feature similarity. Moreover, recent attempts typi-

cally resort to learning complex prediction strategies to in-

corporate the context of training set in each task (Santoro et

al. 2016; Mishra et al. 2018), which are difﬁcult to interpret

in terms of the prior knowledge that has been learned.

In this work, we aim to address the aforementioned weak-

nesses by a semantic-aware meta-learning framework, in

which we explicitly incorporates class sharing across tasks

and focuses on only semantically informative parts of input

images in each task. To this end, we make use of attention

mechanisms (Vaswani et al. 2017) to develop a novel mod-

ularized deep network for the problem of few-shot classi-

ﬁcation. Our deep network consists of two main modules:

an embedding network that computes a semantic-aware fea-

ture map for each image, and an meta-learning network that

learns a similarity-based classiﬁcation strategy to transfer

the training label cues to a test example.

Speciﬁcally, given a few-shot classiﬁcation task, our em-

bedding network ﬁrst generates a convolutional feature map

for each image. Taking as input all these feature maps, the

meta-learning network then extracts a task-speciﬁc repre-

sentation of input data with a dual-attention mechanism,

which is used for few-shot class prediction. To achieve this,

the meta-learning network ﬁrst infers a spatial attention map

for each image to capture relevant regions on the feature

maps and produces a selectively pooled feature vector for

every image (Xu et al. 2015). Given these image features,

the network employs a second attention module, referred as

task attention, to compute an attention map over the train-

ing set of the task. This attention encodes the relevance of

each training example to the test image class in the task

and is used to calculate a context-aware representation of

the test instance (Vinyals et al. 2016) for its class prediction.

下载后可阅读完整内容，剩余7页未读，立即下载

miracleo_

粉丝: 1w+
资源: 52

深度学习小样本学习：注意力驱动的Stanet在AAAI19中的应用

小样本下的卫星图像典型目标识别_测试集

深度学习车辆识别训练统一尺寸负样本1500个

深度学习 小样本学习-何旭明.pptx

aaai_2020_xai_tutorial_Explainable AI.pdf

ACT_AAAI20:AAAI 2020论文“ ACT”的代码

全网收集人工智能学术会议AAAI论文，最全_Awesome-AAAI.zip

Deep learning of Representions_AAAI_Yoshua-超清文字版本

matlab精度检验代码-lstm_speaker_naming_aaai16:演示多峰LSTM的代码

PMGI_AAAI2020:重新思考图像融合的纸张代码

17篇必看[知识图谱Knowledge Graphs] 论文@AAAI2020.zip

最新资源

深度学习小样本学习-何旭明.pptx