Canonical Saliency Maps: Decoding Deep Face Models

by   Thrupthi Ann John, et al.

As Deep Neural Network models for face processing tasks approach human-like performance, their deployment in critical applications such as law enforcement and access control has seen an upswing, where any failure may have far-reaching consequences. We need methods to build trust in deployed systems by making their working as transparent as possible. Existing visualization algorithms are designed for object recognition and do not give insightful results when applied to the face domain. In this work, we present 'Canonical Saliency Maps', a new method that highlights relevant facial areas by projecting saliency maps onto a canonical face model. We present two kinds of Canonical Saliency Maps: image-level maps and model-level maps. Image-level maps highlight facial features responsible for the decision made by a deep face model on a given image, thus helping to understand how a DNN made a prediction on the image. Model-level maps provide an understanding of what the entire DNN model focuses on in each task and thus can be used to detect biases in the model. Our qualitative and quantitative results show the usefulness of the proposed canonical saliency maps, which can be used on any deep face model regardless of the architecture.


page 2

page 3

page 4

page 6

page 8

page 10

page 11

page 12


Visual Saliency Maps Can Apply to Facial Expression Recognition

Human eyes concentrate different facial regions during distinct cognitiv...

Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNet

Recent results suggest that state-of-the-art saliency models perform far...

Concept Saliency Maps to Visualize Relevant Features in Deep Generative Models

Evaluating, explaining, and visualizing high-level concepts in generativ...

Explanation of Face Recognition via Saliency Maps

Despite the significant progress in face recognition in the past years, ...

Discriminative Deep Feature Visualization for Explainable Face Recognition

Despite the huge success of deep convolutional neural networks in face r...

Clustered Saliency Prediction

We present a new method for image salience prediction, Clustered Salienc...

Focused LRP: Explainable AI for Face Morphing Attack Detection

The task of detecting morphed face images has become highly relevant in ...

Please sign up or login with your details

Forgot password? Click here to reset