Article

Abstracted Gaussian Prototypes for One-Shot Concept Learning

2024-09-11

Abstract excerpt

<title>Abstract</title> <p>We introduce a cluster-based generative image segmentation framework to encode higher-level representations of visual concepts based on one-shot learning inspired by the Omniglot Challenge. The inferred parameters of each component of a Gaussian Mixture Model (GMM) represent a distinct topological subpart of a visual concept. Sampling new data from these parameters generates augmented s...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 46785f21-03c4-5592-b94e-5c7b3bd17f27
DOI: 10.21203/rs.3.rs-4908926/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Abstracted Gaussian Prototypes for One-Shot Concept LearningDOI 10.21203/rs.3.rs-4908926/v1Read

Contextual Feature Expansion with Superordinate Concept for Compositional Zero-Shot LearningSemantic proximity Read

DiscoverNet: Unsupervised Video Object Discovery through Discrete Visual Tokenization and Language Model-Inspired ReconstructionSemantic proximity Read

Leveraging prior concept learning improves ability to generalize from few examples in computational models of human object recognitionSemantic proximity Read

Unsupervised Few-shot Object Recognition by Self-Supervised TrainingSemantic proximity Read

Unified Generative Vision-Language UnderstandingSemantic proximity Read

The Oomplet Dataset Toolkit: A flexible and extensible system for large-scale, multi-category image generationSemantic proximity Read

Probing Human Categorization of Naturalistic Images by Combining Deep Neural Networks with Cognitive ModelsSemantic proximity Read

HEADHUNTER: Training-Free Annotated Dataset Synthesis via Self-Guided Diffusion Transformer Attention Head SelectionSemantic proximity Read

Guiding attention during search using generative target template matchingSemantic proximity Read

Making a scene – using GAN generated scenes to test the role of real-world co-occurence statistics and hierarchical feature spaces in scene understanding.Semantic proximity Read

Towards Cognition-Aligned Visual Language Models via Zero-Shot Instance RetrievalSemantic proximity Read

Generative Similarity, Generalization, and AbstractionSemantic proximity Read