Title Information
Title
ClickMe: Large-Scale Human-in-the-Loop Feature Importance Mapping to Train Brain-Aligned Deep Neural Networks
Abstract
Discrepancies between human and deep neural network (DNN) strategies for object recognition pose critical challenges in domains demanding interpretable and trustworthy models. To address this gap, we introduce ClickMe v2, a large-scale human-in-the-loop data collection paradigm that captures category-diagnostic visual features through a gamified interface. In contrast to the original ClickMe, our new pipeline scales to the full ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2012 dataset, aggregates feature importance maps from an additional order of magnitude of global participants, and enforces rigorous data quality controls via catch trials and automated bot detection. This expansion enables a comprehensive examination of how humans prioritize visual information across diverse object categories. By making these large-scale human-derived saliency maps publicly available, ClickMe v2 provides a foundation for benchmarking model interpretability and guiding the development of biologically inspired vision systems.
Name: Personal
Name Part
Gopal, Jay
Role
Role Term (marcrelator) (authorityURI="http://id.loc.gov/vocabulary/relators", valueURI="http://id.loc.gov/vocabulary/relators/cre")
creator
Name: Personal
Name Part
Serre, Thomas
Role
Role Term (marcrelator) (authorityURI="http://id.loc.gov/vocabulary/relators", valueURI="http://id.loc.gov/vocabulary/relators/ths")
thesis advisor
Name: Personal
Name Part
Linsley, Drew
Role
Role Term
reader
Name: Personal
Name Part
Sridhar, Srinath
Role
Role Term
reader
Name: Corporate
Name Part
Brown University. Cognitive and Psychological Sciences
Role
Role Term: Text
sponsor
Origin Information
Copyright Date
2025
Type of Resource (primo)
text_resources
Physical Description
digitalOrigin
born digital
Language
Language Term: Text (ISO639-2B) (authorityURI="http://id.loc.gov/vocabulary/iso639-2.html", valueURI="http://id.loc.gov/vocabulary/iso639-2/eng")
English
Note: thesis
Senior thesis (ScB)--Brown University, 2025
Note (displayLabel="Concentration")
Computational Neuroscience
Genre (aat)
theses
Subject (fast) (authorityURI="http://id.worldcat.org/fast", valueURI="http://id.worldcat.org/fast/00872004")
Topic
computational neuroscience
Subject (Local)
Topic
deep neural networks
Subject (Local)
Topic
artificial intelligence
Subject (Local)
Topic
computer vision
Subject (Local)
Topic
psychophysics
Subject (Local)
Topic
explainability
Subject (Local)
Topic
machine learning
Subject (Local)
Topic
deep learning
Subject (Local)
Topic
neuroscience
Access Condition: use and reproduction
All rights reserved
Access Condition: rights statement (href="http://rightsstatements.org/vocab/InC/1.0/")
In Copyright
Access Condition: restriction on access
All Rights Reserved
Identifier: DOI
10.26300/6a0j-ay62