Article

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

2020-02-19

Abstract excerpt

Humans quickly learn new visual concepts from sparse data, sometimes just a single example. Decades of prior work have established the hierarchical organization of the ventral visual stream as key to this ability. Computational work has shown that networks which hierarchically pool afferents across scales and positions can achieve human-like object recognition performance and predict human neural activity. Prior c...

Topics

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

Identifiers and source

Literature Corpus work: 93ceb310-8f1e-5c76-8c0b-8b3ec956543e
DOI: 10.1101/2020.02.18.944702

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Leveraging prior concept learning improves ability to generalize from few examples in computational models of human object recognitionDOI 10.1101/2020.02.18.944702Read

The representational hierarchy in human and artificial visual systems in the presence of object-scene regularitiesSemantic proximity Read

Using Compositionality to Learn Many Categories from Few ExamplesSemantic proximity Read

Abstract representations emerge naturally in neural networks trained to perform multiple tasksSemantic proximity Read

Neural and Computational Mechanisms Underlying One-shot Perceptual Learning in HumansSemantic proximity Read

Recent advances in understanding object recognition in the human brain: deep neural networks, temporal dynamics, and contextSemantic proximity Read

A self-supervised domain-general learning framework for human ventral stream representationSemantic proximity Read

A neuronal code for object representation and memory in the human amygdala and hippocampusSemantic proximity Read

Excess Capacity LearningSemantic proximity Read

The attentive reconstruction of objects facilitates robust object recognitionSemantic proximity Read

Feature blindness: a challenge for understanding and modelling visual object recognitionSemantic proximity Read

Activated Neuron Group Based Extract-Remember Model for Humanlike Object RecognitionSemantic proximity Read

Teaching deep networks to see shape: Lessons from a simplified visual worldSemantic proximity Read