Zero-data Learning of New Tasks

By Hugo Larochelle, Dumitru Erhan, Yoshua Bengio. 2008

617 citations recorded by the source corpus.

Subfields: 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 Representation & Self-Supervised Learning

Citations in the corpus

Learning Transferable Visual Models From Natural Language Supervision (2021, methodology): “We motivate this as a proxy for performing unseen tasks, as aspired to in the zero-data learning paper of Larochelle et al. (2008).”
RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning (2016, background): “In the broader context of machine learning, there has been a lot of interest in one-shot learning for object classiﬁcation (Vilalta & Drissi, 2002; Fei-Fei et al., 2006; Larochelle et al., 2008; Lake et al., 2011; Koch, 2015).”
Predicting Deep Zero-Shot Convolutional Neural Networks Using Textual Descriptions (2015, background): “The concept of “Zero-Shot Learning” has been introduced in the literature [7, 8, 16, 21, 5, 17] with the aim to improve the scalability of traditional object recognition systems.”
Zero-Shot Learning Through Cross-Modal Transfer (2013, background): “veral zero-shot classes. However, the do not classify new test instances into both seen and unseen classes. We extend their approach to allow for this setup using outlier detection. Larochelle et al. [21] describe the unseen zero-shot classes by a “canonical” example or use ground truth human labeli”
LiT: Zero-Shot Transfer with Locked-image text Tuning (2021, background): “Early works demonstrated how to train zero-shot classifiers based on attributes [35] or numerical descriptors [36].”
Zero-shot Knowledge Transfer via Adversarial Belief Matching (2019, methodology): “In zero-shot learning (Larochelle et al., 2008; Socher et al., 2013), we are typically given training images with labels and some additional intermediate semantic representation T , such as textual descriptions.”
Learning Rapid-Temporal Adaptations (2017, background): “In the scenario where labels are missing for some input examples and yet additional side information is provided as the partial description, it closely resembles zero-shot learning [19].”
Subspace Regularizers for Few-Shot Class Incremental Learning (2021, background): “…et al., 2021; Reed et al., 2016; Yan et al., 2021)—particularly in the zero-shot learning and generalized zero-shot learning where side information is the only source of information about the novel class (Chang et al., 2008; Larochelle et al., 2008; Akata et al., 2013; Pourpanah et al., 2020).”
Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the Ugly (2017, background): “Zero-shot learning aims to recognize objects whose instances may not have been seen during training [1], [2], [3], [4], [5], [6].”
Zero-Shot Learning by Convex Combination of Semantic Embeddings (2013, background): “Recently, zero-shot learning [10, 14] has received a growing amount of attention [16, 11, 6, 18].”
Zero-Shot Learning — The Good, the Bad and the Ugly (2017, background): “Zero-shot learning aims to recognize objects whose instances may not have been seen during training [17, 22, 23, 30, 40].”
Meta-Learning in Neural Networks: A Survey (2020, neutral): “[54].”
Latent Embeddings for Zero-Shot Classification (2016, background): “We are interested in the problem of zero-shot learning where the test classes are disjoint from the training classes [14, 20, 21, 30, 41].”
Label-Embedding for Image Classification (2015, neutral): “Consequently, the main applications have been multiclass classiﬁcation with many classes[3], [66], [67], [4] and zero-shot learning [31], [43].”
Learning to Learn: Meta-Critic Networks for Sample Efficient Learning (2017, background): “Other parameterisations such as word vectors used in zero-shot learning are also possible [21, 12].”
Feature Generating Networks for Zero-Shot Learning (2017, background): “In the zero-shot learning setting, the set of classes seen during training and evaluated during test are disjoint [22, 24, 25, 39, 47].”
Language models enable zero-shot prediction of the effects of mutations on protein function (2021, background): “[18], this perspective on transfer has been at the center of recent work understanding the generalization capabilities of large language models [9–11, 19].”
Label Embedding for Zero-shot Fine-grained Named Entity Typing (2016, background): “…to label itself, prior works have also tried to learn label embeddings from side information such as attributes (Akata et al., 2013), manually-written descriptions (Larochelle et al., 2008), taxonomy of types (Weinberger and Chapelle, 2009; Akata et al., 2013; Akata et al., 2015), and so on.”
A Review of Generalized Zero-Shot Learning Methods (2020, background): “Zero-shot learning (ZSL) [12], [13] techniques offer a good solution to address such challenge.”