Use of superordinate labels yields more robust and human-like visual representations in convolutional neural networks
Open Access
- 1 December 2021
- journal article
- research article
- Published by Association for Research in Vision and Ophthalmology (ARVO) in Journal of Vision
- Vol. 21 (13) , 13
Abstract
Human visual recognition is outstandingly robust. People can recognize thousands of object classes in the blink of an eye (50–200 ms) even when the objects vary in position, scale, viewpoint, and illumination. What aspects of human category learning facilitate the extraction of invariant visual features for object recognition? Here, we explore the possibility that a contributing factor to learning such robust visual representations may be a taxonomic hierarchy communicated in part by common labels to which people are exposed as part of natural language. We did this by manipulating the taxonomic level of labels (e.g., superordinate-level [mammal, fruit, vehicle] and basic-level [dog, banana, van]), and the order in which these training labels were used during learning by a Convolutional Neural Network. We found that training the model with hierarchical labels yields visual representations that are more robust to image transformations (e.g., position/scale, illumination, noise, and blur), especially when images were first trained with superordinate labels and then fine-tuned with basic labels. We also found that Superordinate-label followed by Basic-label training best predicts functional magnetic resonance imaging responses in visual cortex and behavioral similarity judgments recorded while viewing naturalistic images. The benefits of training with superordinate labels in the earlier stages of category learning is discussed in the context of representational efficiency and generalization.Keywords
This publication has 55 references indexed in Scilit:
- Random effects structure for testing interactions in linear mixed-effects modelsFrontiers in Psychology, 2013
- How Does the Brain Solve Visual Object Recognition?Neuron, 2012
- Selectivity and Tolerance (“Invariance”) Both Increase as Visual Information Propagates from Cortical Area V4 to ITThe Journal of Neuroscience, 2010
- Categorical perceptionWIREs Cognitive Science, 2009
- Unconscious effects of language-specific terminology on preattentive color perceptionProceedings of the National Academy of Sciences, 2009
- Representational similarity analysis – connecting the branches of systems neuroscienceFrontiers in Systems Neuroscience, 2008
- Laterality effects in the recognition of depth-rotated novel objectsCognitive, Affective, & Behavioral Neuroscience, 2004
- Brain mechanisms for invariant visual recognition and learningBehavioural Processes, 1994
- Visual Object Representation: Interpreting Neurophysiological Data within a Computational FrameworkJournal of Cognitive Neuroscience, 1990
- When does Human Object Recognition use a Viewer-Centered Reference Frame?Psychological Science, 1990