paper-with-me

홈 › Papers

Rethinking Natural Adversarial Examples for Classification Models

2021-02-23 · Xiao Li, Jianmin Li, Ting Dai, Jie Shi, Jun Zhu, Xiaolin Hu

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.

📄 PDF Abstract BibTeX arXiv:2102.11731

Code (1)

thu-ml/imagenet-a-plus 공식 구현 pytorch

Tasks

ClassificationGeneral Classificationobject-detectionObject Detection

Similar Papers 제목 키워드 기반

Rethinking Machine Learning Robustness via its Link with the Out-of-Distribution Problem

2022-02-18 · Abderrahmen Amich, Birhanu Eshete

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 TranslationTranslation

Rethinking Textual Adversarial Defense for Pre-trained Language Models

2022-07-21 · Jiayi Wang, Rongzhou Bao, Zhuosheng Zhang, Hai Zhao

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 DefenseSentence

Rethinking Cost-sensitive Classification in Deep Learning via Adversarial Data Augmentation

2022-08-24 · Qiyuan Chen, Raed Al Kontar, Maher Nouiehed, Jessie Yang 외

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 Augmentation

Rethinking Feature Distribution for Loss Functions in Image Classification

2018-03-08 · CVPR 2018 6 · Weitao Wan, Yuanyi Zhong, Tianpeng Li, Jiansheng Chen

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 Classification

Rethinking Gradient-based Adversarial Attacks on Point Cloud Classification

2025-05-28 · Jun Chen, Xinke Li, Mingyue Xu, Tianrui Li 외

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