Can Shape Structure Features Improve Model Robustness Under Diverse Adversarial Settings?
Recent studies show that convolutional neural networks (CNNs) are vulnerable under various settings, including adversarial attacks, common corruptions, and backdoor attacks. Motivated by the findings that human visual system pays more attention to global structure (e.g., shapes) for recognition while CNNs are biased towards local texture features in images, in this work we aim to analyze whether "edge features" could improve the recognition robustness in these scenarios, and if so, to what extent? To answer these questions and systematically evaluate the global structure features, we focus on shape features and pro-pose two edge-enabled pipelines EdgeNetRob and Edge-GANRob, forcing the CNNs to rely more on edge features. Specifically, EdgeNetRob and EdgeGANRob first explicitly extract shape structure features from a given image via an edge detection algorithm. Then EdgeNetRob trains down-stream learning tasks directly on the extracted edge features, while EdgeGANRob reconstructs a new image by re-filling the texture information with a trained generative adversarial network (GANs). To reduce the sensitivity of edge detection algorithms to perturbations, we additionally propose a robust edge detection approach Robust Canny based on vanilla Canny. Based on our evaluation, we find that EdgeNetRob can help boost model robustness under differ-ent attack scenarios at the cost of the clean model accuracy. EdgeGANRob, on the other hand, is able to improve the clean model accuracy compared to EdgeNetRob while preserving robustness. This shows that given such edge features, how to leverage them matters for robustness, and it also depends on data properties. Our systematic studies on edge structure features under different settings will shed light on future robust feature exploration and optimization.
Code (0)
등록된 구현이 없습니다.
Tasks
Edge DetectionGenerative Adversarial NetworkSimilar Papers 제목 키워드 기반
DinoComplete: 3D Shape Completion with Distilled Semantic Priors and State Space Models
3D shape completion from partial scans remains challenging for unseen categories and noisy real-world observations, where geometry alone is often insufficient for inferring missing structure. We present DinoComplete, a d…
Does enhanced shape bias improve neural network robustness to common corruptions?
Convolutional neural networks (CNNs) learn to extract representations of complex features, such as object shapes and textures to solve image recognition tasks. Recent work indicates that CNNs trained on ImageNet are bias…
Data AugmentationImproving the robustness of ImageNet classifiers using elements of human visual cognition
We investigate the robustness properties of image recognition models equipped with two features inspired by human vision, an explicit episodic memory and a shape bias, at the ImageNet scale. As reported in previous work,…
ClusteringRetrievalClarifying Myths About the Relationship Between Shape Bias, Accuracy, and Robustness
Deep learning models can perform well when evaluated on images from the same distribution as the training set. However, applying small perturbations in the forms of noise, artifacts, occlusions, blurring, etc. to a model…
Data AugmentationA Novel Shape-Aware Topological Representation for GPR Data with DNN Integration
Ground Penetrating Radar (GPR) is a widely used Non-Destructive Testing (NDT) technique for subsurface exploration, particularly in infrastructure inspection and maintenance. However, conventional interpretation methods …
GPRobject-detectionObject DetectionTopological Data Analysis