paper-with-me

홈 › Papers

Improving Robustness of Convolutional Neural Networks Using Element-Wise Activation Scaling

2022-02-24 · Zhi-Yuan Zhang, Di Liu

Recent works reveal that re-calibrating the intermediate activation of adversarial examples can improve the adversarial robustness of a CNN model. The state of the arts [Baiet al., 2021] and [Yanet al., 2021] explores this feature at the channel level, i.e. the activation of a channel is uniformly scaled by a factor. In this paper, we investigate the intermediate activation manipulation at a more fine-grained level. Instead of uniformly scaling the activation, we individually adjust each element within an activation and thus propose Element-Wise Activation Scaling, dubbed EWAS, to improve CNNs' adversarial robustness. Experimental results on ResNet-18 and WideResNet with CIFAR10 and SVHN show that EWAS significantly improves the robustness accuracy. Especially for ResNet18 on CIFAR10, EWAS increases the adversarial accuracy by 37.65% to 82.35% against C&W attack. EWAS is simple yet very effective in terms of improving robustness. The codes are anonymously available at https://anonymous.4open.science/r/EWAS-DD64.

📄 PDF Abstract BibTeX arXiv:2202.11898

Code (1)

ieslab-ynu/EWAS 공식 구현 pytorch

Tasks

Adversarial Robustness

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Average Pooling 설명 없음
Residual Connection 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Kaiming Initialization 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Batch Normalization 설명 없음

Similar Papers 제목 키워드 기반

Revisiting Residual Networks for Adversarial Robustness: An Architectural Perspective

2022-12-21 · Shihua Huang, Zhichao Lu, Kalyanmoy Deb, Vishnu Naresh Boddeti

Efforts to improve the adversarial robustness of convolutional neural networks have primarily focused on developing more effective adversarial training methods. In contrast, little attention was devoted to analyzing the …

Adversarial Robustness

Network Quantization with Element-wise Gradient Scaling

2021-04-02 · CVPR 2021 1 · Junghyup Lee, Dohyung Kim, Bumsub Ham

Network quantization aims at reducing bit-widths of weights and/or activations, particularly important for implementing deep neural networks with limited hardware resources. Most methods use the straight-through estimato…

image-classificationImage ClassificationQuantization

GETAM: Gradient-weighted Element-wise Transformer Attention Map for Weakly-supervised Semantic segmentation

2021-12-06 · Weixuan Sun, Jing Zhang, Zheyuan Liu, Yiran Zhong 외

Weakly Supervised Semantic Segmentation (WSSS) is challenging, particularly when image-level labels are used to supervise pixel level prediction. To bridge their gap, a Class Activation Map (CAM) is usually generated to …

Semantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation

AReLU: Attention-based Rectified Linear Unit

2020-06-24 · Dengsheng Chen, Jun Li, Kai Xu

Element-wise activation functions play a critical role in deep neural networks via affecting the expressivity power and the learning dynamics. Learning-based activation functions have recently gained increasing attention…

Meta-LearningTransfer Learning

PikeLPN: Mitigating Overlooked Inefficiencies of Low-Precision Neural Networks

2024-01-01 · CVPR 2024 1 · Marina Neseem, Conor McCullough, Randy Hsin, Chas Leichner 외

Low-precision quantization is recognized for its efficacy in neural network optimization. Our analysis reveals that non-quantized elementwise operations which are prevalent in layers such as parameterized activation …

Quantization