Deep CNNs have been pushing the frontier of visual recognition over past years. Besides recognition accuracy, strong demands in understanding deep CNNs in the research community motivate developments of tools to dissect pre-trained models to visualize how they make predictions. Recent works further push the interpretability in the network learning stage to learn more meaningful representations. In this work, focusing on a specific area of visual recognition, we report our efforts towards interpretable face recognition. We propose a spatial activation diversity loss to learn more structured face representations. By leveraging the structure, we further design a feature activation diversity loss to push the interpretable representations to be discriminative and robust to occlusions. We demonstrate on three face recognition benchmarks that our proposed method is able to achieve the state-of-art face recognition accuracy with easily interpretable face representations.
Visualization of filter response "heat maps" of 10 different filters on faces from different subjects (Top 4 rows) and the same subject (Bottom 4 rows). The positive and negative responses are shown as two colors within each image. Note the high consistency of response locations across subjects and across poses.
The average locations of positive (Left 3 faces) and negative (Right 3 faces) peak responses of 320 filters for three models: (a) base CNN model (d=6.9), (b) our (SAD only, d=17.1), and (c) our model (d=18.7), where d quantifies the average locations spreadness. The color on each location denotes the standard deviation of peak locations. The face size is 96 * 96.