Anomalous behaviour in loss-gradient based interpretability methods

07/15/2022
by   Vinod Subramanian, et al.
0

Loss-gradients are used to interpret the decision making process of deep learning models. In this work, we evaluate loss-gradient based attribution methods by occluding parts of the input and comparing the performance of the occluded input to the original input. We observe that the occluded input has better performance than the original across the test dataset under certain conditions. Similar behaviour is observed in sound and image recognition tasks. We explore different loss-gradient attribution methods, occlusion levels and replacement values to explain the phenomenon of performance improvement under occlusion.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset