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

by   Md Amirul Islam, et al.

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. The premise is based on the notion of feature binding, which is defined as the process by which activations spread across space and layers in the network are successfully integrated to arrive at a correct inference decision. In our 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 feature binding 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 saliency network while simultaneously increasing robustness to adversarial attacks.



There are no comments yet.


page 2

page 9

page 11

page 13

page 15


Feature Binding with Category-Dependant MixUp for Semantic Segmentation and Adversarial Robustness

In this paper, we present a strategy for training convolutional neural n...

Improved Noise and Attack Robustness for Semantic Segmentation by Using Multi-Task Training with Self-Supervised Depth Estimation

While current approaches for neural network training often aim at improv...

Stochastic Local Winner-Takes-All Networks Enable Profound Adversarial Robustness

This work explores the potency of stochastic competition-based activatio...

On the Robustness of Semantic Segmentation Models to Adversarial Attacks

Deep Neural Networks (DNNs) have been demonstrated to perform exceptiona...

Gradient-based adversarial attacks on categorical sequence models via traversing an embedded world

An adversarial attack paradigm explores various scenarios for vulnerabil...

Calibrated Adversarial Refinement for Multimodal Semantic Segmentation

Ambiguities in images or unsystematic annotation can lead to multiple va...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.