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

2020-08-13 · Md Amirul Islam, Matthew Kowal, Konstantinos G. Derpanis, Neil D. B. Bruce

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.

📄 PDF Abstract BibTeX arXiv:2008.05667

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Robustness Denoising Semantic Segmentation

FedSM: Robust Semantics-Guided Feature Mixup for Bias Reduction in Federated Learning with Long-Tail Data

2025-10-31 · Jingrui Zhang, Yimeng Xu, Shujie Li, Feng Liang 외 arxiv

Federated Learning (FL) enables collaborative model training across decentralized clients without sharing private data. However, FL suffers from biased global models due to non-IID and long-tail data distributions. We pr…

Computational Efficiency Federated Learning

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

2021-08-23 · Md Amirul Islam, Matthew Kowal, Konstantinos G. Derpanis, Neil D. B. Bruce

Adversarial Robustness Denoising Semantic Segmentation

Mixup Regularized Adversarial Networks for Multi-Domain Text Classification

2021-01-31 · Yuan Wu, Diana Inkpen, Ahmed El-Roby

Using the shared-private paradigm and adversarial training has significantly improved the performances of multi-domain text classification (MDTC) models. However, there are two issues for the existing methods. First, ins…

Classification General Classification text-classification Text Classification

Dual Mixup Regularized Learning for Adversarial Domain Adaptation

2020-07-07 · ECCV 2020 8 · Yuan Wu, Diana Inkpen, Ahmed El-Roby

Recent advances on unsupervised domain adaptation (UDA) rely on adversarial learning to disentangle the explanatory and transferable features for domain adaptation. However, there are two issues with the existing methods…

Domain Adaptation Unsupervised Domain Adaptation

Recurrent Feature Mining and Keypoint Mixup Padding for Category-Agnostic Pose Estimation

2025-03-27 · CVPR 2025 1 · Junjie Chen, Weilong Chen, Yifan Zuo, Yuming Fang

Category-agnostic pose estimation aims to locate keypoints on query images according to a few annotated support images for arbitrary novel classes. Existing methods generally extract support features via heatmap pooling,…

Category-Agnostic Pose Estimation Pose Estimation