Log In Sign Up

Feature Binding with Category-Dependant 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 activation's 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 their class labels, and then training 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 network while simultaneously increasing robustness to adversarial attacks.


page 1

page 4

page 6

page 8

page 9


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

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

Single-Step Adversarial Training for Semantic Segmentation

Even though deep neural networks succeed on many different tasks includi...

Defending From Physically-Realizable Adversarial Attacks Through Internal Over-Activation Analysis

This work presents Z-Mask, a robust and effective strategy to improve th...

On the Robustness of Semantic Segmentation Models to Adversarial Attacks

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

Clustering Effect of (Linearized) Adversarial Robust Models

Adversarial robustness has received increasing attention along with the ...

Robust Prototypical Few-Shot Organ Segmentation with Regularized Neural-ODEs

Despite the tremendous progress made by deep learning models in image se...