Unsupervised Domain Adaptation for Zero-Shot Learning

By Elyor Kodirov, Tao A. Xiang, Zhenyong Fu, Shaogang Gong. 2015

400 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the Ugly (2017, background): “Apart from the inductive zero-shot learning set-up where the model has no access to neither visual nor side-information of unseen classes, transductive zero-shot learning approaches [28], [44], [45], [46], [47], [48], [49] use visual or semantic information of both seen and unseen classes without ha”
Zero-Shot Learning — The Good, the Bad and the Ugly (2017, neutral): “compatibility learning frameworks [3, 4, 11, 15, 27, 32, 34, 39, 32, 12, 29, 1, 6, 24, 13, 21].”
An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild (2016, methodology): “Existing research on ZSL has been almost entirely focusing on this setting [4,10,11,12,13,14,15,8,16,17,18,19,20,21,22,23,24,25,26,27,28].”
Feature Generating Networks for Zero-Shot Learning (2017, background): “[50, 31, 8] learn unseen classes as a mixture of seen class proportions, and [2, 3, 14, 42, 45, 40, 16, 33, 1, 6, 17, 23] learn a compatibility between images and classes.”
Unsupervised Multi-Target Domain Adaptation: An Information Theoretic Approach (2018, background): “Domain Adaptation ( DA ) approaches (e.g., [ 16 , 19 , 23 , 44 ]) aim to tackle this by transferring knowledge from a source domain (training data) to an unlabeled target domain (test data) to reduce the discrepancy between the source and target data distributions, typically by exploring…”
Guiding Exploratory Behaviors for Multi-Modal Grounding of Linguistic Descriptions (2018, background): “The problem we address bears some similarities to the zero-shot learning problem (Xian, Schiele, and Akata 2017; Fu et al. 2015; Kodirov et al. 2015).”
Fine-Grained Recognition in the Wild: A Multi-task Domain Adaptation Approach (2017, background): “Kodirov et al. [31] uses sparse coding and subspace alignment techniques to perform zero shot learning when images are sourced from multiple domains.”
Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts (2018, background): “This assumption is consistent with recent efforts in the literature which consider class semantics to solve the domain shift problem in ZSL [7,12] and does not a constitute transductive setting [8,11,18].”
F-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning (2019, neutral): “[26, 16] exploit semantic manifold learning.”
DLOW: Domain Flow for Adaptation and Generalization (2018, background): “A group of recent works aim to reduce the distribution difference on the feature level by learning domain-invariant features [13, 18, 31, 16], while others work on the image level to transfer source images to mimic the target domain style [64, 38, 65, 27, 1, 8].”
Joint Dictionaries for Zero-Shot Learning (2017, methodology): “Our JD-ZSL build on similar ideas as in (Isele, Rostami, and Eaton 2016; Kodirov et al. 2015) and introduce a novel ZSL method based on learning joint sparse dictionaries for the image features and the semantic attributes.”
Semantic Projection Network for Zero- and Few-Label Semantic Segmentation (2019, background): “As complementary tasks [24, 40] focuses on assigning multiple previously unseen labels to a single image, [22, 52, 53] on predicting novel actions in a video, and recently, [4] on unseen object detection.”
A Generative Model for Zero Shot Learning Using Conditional Variational Autoencoders (2017, methodology): “[20] present a sparse coding framework based on an unsupervised domain adaptation for ZSL.”
Zero-Shot Learning with Generative Latent Prototype Model (2017, neutral): “They are SJE [31], HAP [38], ZSLwUA [39], PST [13], TMV [21], AMP [26], UDA [40] and UDICA [16].”
Zero-Shot Object Detection: Joint Recognition and Localization of Novel Concepts (2020, methodology): “To minimize the diﬃculty level of the ZSL problem, researchers have investigated transductive setting [62, 61,27], domain adaptation [11,20] and class-attribute association [4,9] techniques.”
Small Sample Learning in Big Data Era (2018, methodology): “For example, Kodirov et al. (2015) cast the mapping function learning problem as a sparse coding problem, joint learning seen and unseen semantic embedding.”
Deep Transfer Learning for Few-Shot SAR Image Classification (2019, methodology): “We use the few accessible labeled data points in the SAR domain to align both distribution’s class-conditionally to tackle the class matching challenge [21].”