Rethinking Natural Adversarial Examples for Classification Models
Recently, it was found that many real-world examples without intentional modifications can fool machine learning models, and such examples are called "natural adversarial examples". ImageNet-A is a famous dataset of natural adversarial examples. By analyzing this dataset, we hypothesized that large, cluttered and/or unusual background is an important reason why the images in this dataset are difficult to be classified. We validated the hypothesis by reducing the background influence in ImageNet-A examples with object detection techniques. Experiments showed that the object detection models with various classification models as backbones obtained much higher accuracy than their corresponding classification models. A detection model based on the classification model EfficientNet-B7 achieved a top-1 accuracy of 53.95%, surpassing previous state-of-the-art classification models trained on ImageNet, suggesting that accurate localization information can significantly boost the performance of classification models on ImageNet-A. We then manually cropped the objects in images from ImageNet-A and created a new dataset, named ImageNet-A-Plus. A human test on the new dataset showed that the deep learning-based classifiers still performed quite poorly compared with humans. Therefore, the new dataset can be used to study the robustness of classification models to the internal variance of objects without considering the background disturbance.
Code (1)
Tasks
ClassificationGeneral Classificationobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
Rethinking Machine Learning Robustness via its Link with the Out-of-Distribution Problem
Despite multiple efforts made towards robust machine learning (ML) models, their vulnerability to adversarial examples remains a challenging problem that calls for rethinking the defense strategy. In this paper, we take …
BIG-bench Machine LearningImage-to-Image TranslationTranslationRethinking Textual Adversarial Defense for Pre-trained Language Models
Although pre-trained language models (PrLMs) have achieved significant success, recent studies demonstrate that PrLMs are vulnerable to adversarial attacks. By generating adversarial examples with slight perturbations on…
Adversarial AttackAdversarial DefenseSentenceRethinking Cost-sensitive Classification in Deep Learning via Adversarial Data Augmentation
Cost-sensitive classification is critical in applications where misclassification errors widely vary in cost. However, over-parameterization poses fundamental challenges to the cost-sensitive modeling of deep neural netw…
Data AugmentationRethinking Feature Distribution for Loss Functions in Image Classification
We propose a large-margin Gaussian Mixture (L-GM) loss for deep neural networks in classification tasks. Different from the softmax cross-entropy loss, our proposal is established on the assumption that the deep features…
ClassificationGeneral Classificationimage-classificationImage ClassificationRethinking Gradient-based Adversarial Attacks on Point Cloud Classification
Gradient-based adversarial attacks have become a dominant approach for evaluating the robustness of point cloud classification models. However, existing methods often rely on uniform update rules that fail to consider th…
3D Point Cloud ClassificationPoint Cloud Classification