THIN: THrowable Information Networks and Application for Facial Expression Recognition In The Wild
share
For a number of tasks solved using deep learning techniques, an exogenous variable can be identified such that (a) it heavily influences the appearance of the different classes, and (b) an ideal classifier should be invariant to this variable. An example of such exogenous variable is identity if facial expression recognition (FER) is considered. In this paper, we propose a dual exogenous/endogenous representation. The former captures the exogenous variable whereas the second one models the task at hand (e.g. facial expression). We design a prediction layer that uses a deep ensemble conditioned by the exogenous representation. It employs a differential tree gate that learns an adaptive weak predictor weighting, therefore modeling a partition of the exogenous representation space, upon which the weak predictors specialize. This layer explicitly models the dependency between the exogenous variable and the predicted task (a). We also propose an exogenous dispelling loss to remove the exogenous information from the endogenous representation, enforcing (b). Thus, the exogenous information is used two times in a throwable fashion, first as a conditioning variable for the target task, and second to create invariance within the endogenous representation. We call this method THIN, standing for THrowable Information Networks. We experimentally validate THIN in several contexts where an exogenous information can be identified, such as digit recognition under large rotations and shape recognition at multiple scales. We also apply it to FER with identity as the exogenous variable. In particular, we demonstrate that THIN significantly outperforms state-of-the-art approaches on several challenging datasets.
READ FULL TEXT