Search Results for author: Brett D. Roads

Found 7 papers, 3 papers with code

A Too-Good-to-be-True Prior to Reduce Shortcut Reliance

no code implementations12 Feb 2021 Nikolay Dagaev, Brett D. Roads, Xiaoliang Luo, Daniel N. Barry, Kaustubh R. Patil, Bradley C. Love

Furthermore, an LCN's predictions can be used in a two-stage approach to encourage a high-capacity network (HCN) to rely on deeper invariant features that should generalize broadly.

Object Recognition

Enriching ImageNet with Human Similarity Judgments and Psychological Embeddings

1 code implementation CVPR 2021 Brett D. Roads, Bradley C. Love

The Human Similarity Judgments extension to ImageNet (ImageNet-HSJ) is composed of human similarity judgments that supplement the ILSVRC validation set.

Bayesian Inference Object Recognition

Transforming Neural Network Visual Representations to Predict Human Judgments of Similarity

no code implementations13 Oct 2020 Maria Attarian, Brett D. Roads, Michael C. Mozer

Deep-learning vision models have shown intriguing similarities and differences with respect to human vision.

The Costs and Benefits of Goal-Directed Attention in Deep Convolutional Neural Networks

no code implementations6 Feb 2020 Xiaoliang Luo, Brett D. Roads, Bradley C. Love

Motivated by selective attention in categorisation models, we developed a goal-directed attention mechanism that can process naturalistic (photographic) stimuli.

Object Recognition Transfer Learning

Learning as the Unsupervised Alignment of Conceptual Systems

no code implementations21 Jun 2019 Brett D. Roads, Bradley C. Love

Concept induction requires the extraction and naming of concepts from noisy perceptual experience.

Learning to Generate Images with Perceptual Similarity Metrics

1 code implementation19 Nov 2015 Jake Snell, Karl Ridgeway, Renjie Liao, Brett D. Roads, Michael C. Mozer, Richard S. Zemel

We propose instead to use a loss function that is better calibrated to human perceptual judgments of image quality: the multiscale structural-similarity score (MS-SSIM).

Image Classification Image Generation +3

Cannot find the paper you are looking for? You can Submit a new open access paper.