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

by   Colton R. Crum, et al.

Machine learning models have shown increased accuracy in classification tasks when the training process incorporates human perceptual information. However, a challenge in training human-guided models is the cost associated with collecting image annotations for human salience. Collecting annotation data for all images in a large training set can be prohibitively expensive. In this work, we utilize ”teacher” models (trained on a small amount of human-annotated data) to annotate additional data by means of teacher models' saliency maps. Then, ”student” models are trained using the larger amount of annotated training data. This approach makes it possible to supplement a limited number of human-supplied annotations with an arbitrarily large number of model-generated image annotations. We compare the accuracy achieved by our teacher-student training paradigm with (1) training using all available human salience annotations, and (2) using all available training data without human salience annotations. We use synthetic face detection and fake iris detection as example challenging problems, and report results across four model architectures (DenseNet, ResNet, Xception, and Inception), and two saliency estimation methods (CAM and RISE). Results show that our teacher-student training paradigm results in models that significantly exceed the performance of both baselines, demonstrating that our approach can usefully leverage a small amount of human annotations to generate salience maps for an arbitrary amount of additional training data.


page 2

page 10

page 11

page 12


Teacher-Student Architecture for Mixed Supervised Lung Tumor Segmentation

Purpose: Automating tasks such as lung tumor localization and segmentati...

Self-training of Machine Learning Models for Liver Histopathology: Generalization under Clinical Shifts

Histopathology images are gigapixel-sized and include features and infor...

Human-Aided Saliency Maps Improve Generalization of Deep Learning

Deep learning has driven remarkable accuracy increases in many computer ...

CYBORG: Blending Human Saliency Into the Loss Improves Deep Learning

Can deep learning models achieve greater generalization if their trainin...

Learning from a tiny dataset of manual annotations: a teacher/student approach for surgical phase recognition

Vision algorithms capable of interpreting scenes from a real-time video ...

A New Learning Paradigm for Stochastic Configuration Network: SCN+

Learning using privileged information (LUPI) paradigm, which pioneered t...

Benchmarking Automatic Detection of Psycholinguistic Characteristics for Better Human-Computer Interaction

When two people pay attention to each other and are interested in what t...

Please sign up or login with your details

Forgot password? Click here to reset