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

arXiv: https://arxiv.org/abs/2008.05667 · HTML: https://mlsanity.com/paper/2008.05667/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Aug 2020.

## Built on by (most cited first, 6 of 6)

- [Position, Padding and Predictions: A Deeper Look at Position Information in CNNs](https://mlsanity.com/paper/2101.12322/) (2021)
- [GAMA: Generative Adversarial Multi-Object Scene Attacks](https://mlsanity.com/paper/2209.09502/) (2022)
- [SegMix: Co-occurrence Driven Mixup for Semantic Segmentation and Adversarial Robustness](https://mlsanity.com/paper/2108.09929/) (2021)
- [Simpler Does It: Generating Semantic Labels with Objectness Guidance](https://mlsanity.com/paper/2110.10335/) (2021)
- [Visual Transformers with Primal Object Queries for Multi-Label Image Classification](https://mlsanity.com/paper/2112.05485/) (2021)
- [Multi-View Correlation Consistency for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2208.08437/) (2022)

## Abstract (arXiv)

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.