Cross-generalization: learning novel classes from a single example by feature replacement

By Evgeniy Bart, Shimon Ullman. 2005

220 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Media Technology, 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 Media Technology

In Representation & Self-Supervised Learning

Citations in the corpus

Zero-Shot Learning Through Cross-Modal Transfer (2013, background): “This is usually achieved by either sharing of feature representations [2], model parameters [12] or via similar context [14].”
CrossTransformers: spatially-aware few-shot transfer (2020, background): “Discriminative parts [5, 10, 22, 34, 42, 83] and visual words [74, 100] have a rich history, and have found applications in deformable-parts models [26], and classification [70, 100].”
Low-Shot Learning from Imaginary Data (2018, background): “Some work tries to share features between seen and novel classes [1, 36] or incrementally learn them as new classes are encountered [21].”
Learning to Reconstruct Shapes from Unseen Classes (2018, background): “A number of earlier papers have explored sharing features across categories to recognize new objects from a few examples [Bart and Ullman, 2005, Farhadi et al., 2009, Lampert et al., 2009, Torralba et al., 2007].”
Meta-Learning: A Survey (2018, neutral): “ameters, so that l new can be trained much faster than otherwise possible. Earlier workonone-shot learning islargely based on hand-engineered features(Fei-Fei et al., 2006; Fei-Fei, 2006; Fink, 2005; Bart and Ullman, 2005). With meta-learning, however, we hope to learn a common feature representatio”
Zero-Shot Learning by Convex Combination of Semantic Embeddings (2013, background): “Zero-shot learning is closely related to one-shot learning [13, 5, 1, 8], where the goal is to learn object classiﬁers based on a few labeled training exemplars.”
Learning with Hierarchical-Deep Models (2013, background): “Bart and Ullman [3] further proposed a cross-generalization framework for learning with few examples.”
Sharing Visual Features for Multiclass and Multiview Object Detection (2007, background): “Transferring knowledge between objects to improve generalization has also been studied in several recent papers [4], [17], [34].”
Computational Baby Learning (2014, background): “partially similar to the one-shot learning [10] which learns visual object classiﬁers by using very few samples. Most of the one-shot learning methods are based on the feature representation transfer [2], similar geometric context [15] or cross-modal knowledge transfer [26]. However, their performan”
Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, background): “In general, it is solved by knowledge transfer through the reuse of model parameters [85], by sharing parts or features [12], or by contextual information [152].”
Generalizing from a Few Examples (2019, methodology): “In [10], few-shot object classification is performed by leveraging samples and classifiers from similar classes.”
An Ensemble of Epoch-Wise Empirical Bayes for Few-Shot Learning (2019, background): “Research literature on few-shot learning paradigms exhibits a high diversity from using data augmentation techniques [9, 75,77] over sharing feature representation [2,76] to meta-learning [18,72].”
Knowledge Distillation from Few Samples (2018, methodology): “This cognition phenomenon has motivated the development of the few-shot learning (Fei-Fei et al., 2006; Bart & Ullman, 2005), which aims to learn information about object categories from a few training samples, and focuses more on image classification task.”
Learning to share visual appearance for multiclass object detection (2011, unknown): “, parts) across different classes [15, 30, 2, 21, 17].”
What helps where – and why? Semantic relatedness for knowledge transfer (2010, background): “Similar in spirit, several works transfer knowledge in the form of learned distance metrics [3, 14, 28] or object class priors [11, 27].”
Sharing features between objects and their attributes (2011, background): “The focus has been on inter-class transfer between objects [10, 5, 22, 20] , and jointly training detectors so that features are shared across objects [23, 3, 29], which lends to better efficiency during detection.”
Relational Generalized Few-Shot Learning (2019, background): “Few-shot learning (FSL) [1, 2, 3, 4] is inspired by the human ability to learn new concepts from very few or even only one example.”
Discriminative Transfer Learning with Tree-based Priors (2013, methodology): “In essence, our model learns low-level features, high-level features, as well as a hierarchy over classes in an end-to-end way.”