CYBORG: Blending Human Saliency Into the Loss Improves Deep Learning

12/01/2021
by   Aidan Boyd, et al.
8

Can deep learning models achieve greater generalization if their training is guided by reference to human perceptual abilities? And how can we implement this in a practical manner? This paper proposes a first-ever training strategy to ConveY Brain Oversight to Raise Generalization (CYBORG). This new training approach incorporates human-annotated saliency maps into a CYBORG loss function that guides the model towards learning features from image regions that humans find salient when solving a given visual task. The Class Activation Mapping (CAM) mechanism is used to probe the model's current saliency in each training batch, juxtapose model saliency with human saliency, and penalize the model for large differences. Results on the task of synthetic face detection show that the CYBORG loss leads to significant improvement in performance on unseen samples consisting of face images generated from six Generative Adversarial Networks (GANs) across multiple classification network architectures. We also show that scaling to even seven times as much training data with standard loss cannot beat the accuracy of CYBORG loss. As a side effect, we observed that the addition of explicit region annotation to the task of synthetic face detection increased human classification performance. This work opens a new area of research on how to incorporate human visual saliency into loss functions. All data, code and pre-trained models used in this work are offered with this paper.

READ FULL TEXT

page 1

page 3

page 5

page 12

research
08/22/2022

The Value of AI Guidance in Human Examination of Synthetically-Generated Faces

Face image synthesis has progressed beyond the point at which humans can...
research
03/01/2023

Improving Model's Focus Improves Performance of Deep Learning-Based Synthetic Face Detectors

Deep learning-based models generalize better to unknown data samples aft...
research
05/07/2021

Human-Aided Saliency Maps Improve Generalization of Deep Learning

Deep learning has driven remarkable accuracy increases in many computer ...
research
06/08/2023

Teaching AI to Teach: Leveraging Limited Human Salience Data Into Unlimited Saliency-Based Training

Machine learning models have shown increased accuracy in classification ...
research
04/05/2018

End-to-End Saliency Mapping via Probability Distribution Prediction

Most saliency estimation methods aim to explicitly model low-level consp...
research
03/21/2023

Explain To Me: Salience-Based Explainability for Synthetic Face Detection Models

The performance of convolutional neural networks has continued to improv...
research
07/22/2013

Is Bottom-Up Attention Useful for Scene Recognition?

The human visual system employs a selective attention mechanism to under...

Please sign up or login with your details

Forgot password? Click here to reset