Write a Classifier: Zero-Shot Learning Using Purely Textual Descriptions

By Mohamed Elhoseiny, Babak Saleh, Ahmed M. Elgammal. 2013

323 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, 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 Natural Language Processing

In Representation & Self-Supervised Learning

Citations in the corpus

Learning Transferable Visual Models From Natural Language Supervision (2021, background): “Lei Ba et al. (2015) first introduced a zero-shot image classifier of this form while the idea of generating a classifier from natural language dates back to at least Elhoseiny et al. (2013).”
Shaping Visual Representations with Language for Few-Shot Classification (2019, methodology): “Language has been shown to assist visual classification in various settings, including traditional visual classification with no transfer [16] and with language available at test time in the form of class labels or descriptions for zero- [10, 11, 27] or few-shot [24, 33] learning.”
Predicting Deep Zero-Shot Convolutional Neural Networks Using Textual Descriptions (2015, methodology): “In this work, we build on the ideas of [5] and introduce a novel Zero-Shot Learning model that predicts visual classes using a text corpus, in particular, the encyclopedia corpus.”
Learning to Prompt for Vision-Language Models (2021, methodology): “For text features extraction, early work has mainly utilized pre-trained word vectors (Socher et al., 2013; Frome et al., 2013) or the hand-crafted TF-IDF features (Elhoseiny et al., 2013; Lei Ba et al., 2015).”
Prototypical Networks for Few-shot Learning (2017, neutral): “In addition, our approach naturally generalizes to other distance functions, particularly Bregman divergences.”
Learning Deep Representations of Fine-Grained Visual Descriptions (2016, background): “Previously-reported zero-shot results on the Flowers dataset [11, 3] do not report multi-class classification (instead reporting binary one-vs-rest detection of unseen categories) or do not currently have published splits.”
Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the Ugly (2017, background): “[31], [34], [50], [51], [52], [53], [54] which exploit other auxiliary information that reduces this annotation effort.”
Learning Like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images (2015, background): “Zero-shot and one-shot learning For zero-shot learning, the task is to associate dense word vectors or attributes with image features [49, 17, 12, 2, 31].”
Conditional Prompt Learning for Vision-Language Models (2022, methodology): “Images are often encoded using hand-crafted descriptors [10, 45] or neural networks [12, 29], while texts are encoded using, for instance, pre-trained word vectors [12, 45] or the frequency-based TF-IDF features [10, 29].”
An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild (2016, methodology): “[33] and [34] focus on training a zero-shot binary classifier for each unseen class (against seen ones) — it is not clear how to distinguish multiple unseen classes from the seen ones.”
A Survey of Zero-Shot Learning (2019, methodology): “Suppose we want to recognize flowers of different breeds [8, 31].”
Leveraging Visual Question Answering for Image-Caption Ranking (2016, background): “More recent works also explore using word embed-dings [28] and free-form text [29] as representations that allow zero-shot learning of new object categories.”
K-LITE: Learning Transferable Visual Models with External Knowledge (2022, background): “35], text [18, 19, 72, 70], knowledge graphs [91, 74], or rules and ontologies [23].”
Learning to Segment Every Thing (2017, background): “In [8], image classifiers are predicted from the natural language description of a zero-shot category.”
Audio Visual Attribute Discovery for Fine-Grained Object Recognition (2018, background): “Belhumeur 2013; Elhoseiny, Saleh, and Elgammal 2013; Reed et al. 2016; Vedaldi et al. 2014; Zhang et al. 2013; He and Peng 2017).”
MetaAnchor: Learning to Detect Objects with Customized Anchors (2018, background): “Weight prediction means a mechanism in neural networks where weights are predicted by another structure rather than directly learned, which is mainly used in the fields of learning to learn [9, 1, 41], few/zero-shot learning [4, 41] and transfer learning [26].”
Unsupervised Domain Adaptation for Zero-Shot Learning (2015, background): “The text corpus is so big that any class label or textual description of the class [5] can be embedded in this space, effectively mitigating the scalability issue.”
Large-Scale Object Classification Using Label Relation Graphs (2014, methodology): “Finally, by modeling the label relations and ensuring consistency between visual predictions and semantic relations, our approach relates to work in transfer learning [31,30], zero-shot learning [28,12,25], and attribute-based recognition [1,36,33,14], especially those that use semantic knowledge to”