SegMix: Co-occurrence Driven Mixup for Semantic Segmentation and Adversarial Robustness

In this paper, we present a strategy for training convolutional neural networks to effectively resolve interference arising from competing hypotheses relating to inter-categorical information throughout the network. In this work, this is accomplished for the task of dense image labelling by blending images based on (i) categorical clustering or (ii) the co-occurrence likelihood of categories. We then train a source separation network which simultaneously segments and separates the blended images. Subsequent feature denoising to suppress noisy activations reveals additional desirable properties and high degrees of successful predictions. Through this process, we reveal a general mechanism, distinct from any prior methods, for boosting the performance of the base segmentation and salient object detection network while simultaneously increasing robustness to adversarial attacks.