Visual Domain Adaptation in the Deep Learning Era
暫譯: 深度學習時代的視覺領域適應

Csurka, Gabriela, Hospedales, Timothy M., Salzmann, Mathieu

  • 出版商: Springer
  • 出版日期: 2022-04-05
  • 售價: $2,660
  • 貴賓價: 9.5$2,527
  • 語言: 英文
  • 頁數: 192
  • 裝訂: Quality Paper - also called trade paper
  • ISBN: 3031791703
  • ISBN-13: 9783031791703
  • 相關分類: DeepLearning
  • 海外代購書籍(需單獨結帳)

商品描述

Solving problems with deep neural networks typically relies on massive amounts of labeled training data to achieve high performance/b>. While in many situations huge volumes of unlabeled data can be and often are generated and available, the cost of acquiring data labels remains high. Transfer learning (TL), and in particular domain adaptation (DA), has emerged as an effective solution to overcome the burden of annotation, exploiting the unlabeled data available from the target domain together with labeled data or pre-trained models from similar, yet different source domains. The aim of this book is to provide an overview of such DA/TL methods applied to computer vision, a field whose popularity has increased significantly in the last few years.

We set the stage by revisiting the theoretical background and some of the historical shallow methods before discussing and comparing different domain adaptation strategies that exploit deep architectures for visual recognition. We introduce the space of self-training-based methods that draw inspiration from the related fields of deep semi-supervised and self-supervised learning in solving the deep domain adaptation. Going beyond the classic domain adaptation problem, we then explore the rich space of problem settings that arise when applying domain adaptation in practice such as partial or open-set DA, where source and target data categories do not fully overlap, continuous DA where the target data comes as a stream, and so on. We next consider the least restrictive setting of domain generalization (DG), as an extreme case where neither labeled nor unlabeled target data are available during training. Finally, we close by considering the emerging area of learning-to-learn and how it can be applied to further improve existing approaches to cross domain learning problems such as DA and DG.

商品描述(中文翻譯)

解決深度神經網絡的問題通常依賴於大量標記的訓練數據以達到高性能。雖然在許多情況下,會生成並且通常可用大量未標記的數據,但獲取數據標籤的成本仍然很高。遷移學習(Transfer Learning, TL),特別是領域適應(Domain Adaptation, DA),已成為克服標註負擔的有效解決方案,利用來自目標領域的未標記數據以及來自相似但不同源領域的標記數據或預訓練模型。本書的目的是提供一個關於應用於計算機視覺的DA/TL方法的概述,這是一個在過去幾年中顯著增長的領域。

我們首先回顧理論背景和一些歷史上的淺層方法,然後討論和比較利用深度架構進行視覺識別的不同領域適應策略。我們介紹基於自我訓練的方法空間,這些方法受到深度半監督學習和自監督學習相關領域的啟發,以解決深度領域適應問題。超越經典的領域適應問題,我們接著探索在實踐中應用領域適應時出現的豐富問題設置,例如部分或開放集DA,其中源數據和目標數據類別並不完全重疊,連續DA,其中目標數據以流的形式出現,等等。接下來,我們考慮領域泛化(Domain Generalization, DG)的最不限制設置,這是一種極端情況,在訓練期間既沒有標記的也沒有未標記的目標數據可用。最後,我們考慮新興的學習如何學習(learning-to-learn)領域,以及它如何應用於進一步改善現有的跨領域學習問題的方法,例如DA和DG。