PushPull-Net：由抑制机制驱动的对图像损坏具有鲁棒性的ResNet
PushPull-Net: Inhibition-driven ResNet robust to image corruptions
AI总结：
受初级视觉皮层反相抑制启发，提出PushPull-Conv计算单元，通过互补的push和pull核增强刺激选择性，将其加入ResNet可显著提升图像损坏鲁棒性，结合PRIME增强在ImageNet-C上ResNet50的mCE达49.95%。
摘要：
受初级视觉皮层中观察到的反相抑制现象启发，我们在ResNet架构的第一层引入了一种名为PushPull-Conv的新型计算单元。该单元通过实现一对互补滤波器——可训练的push核及其对应的pull核——重新定义了传统卷积层。push核（类似于传统卷积）学习对特定刺激做出响应，而pull核对相同但对比度相反的刺激做出反应。这种配置增强了刺激选择性，并有效抑制了缺乏偏好刺激区域的响应。这种效应归因于push和pull核，它们在这类区域产生幅度相当的响应，从而相互抵消。将PushPull-Conv整合到ResNet中可显著提升其对图像损坏的鲁棒性。我们在基准损坏数据集上的实验表明，PushPull-Conv可与其他数据增强技术结合以进一步提升模型鲁棒性。当将PRIME增强与PushPull抑制相结合时，我们在ResNet50上创下了新的鲁棒性基准，在ImageNet-C上达到49.95%的mCE。
英文摘要：
We introduce a novel computational unit, termed PushPull-Conv, in the first layer of a ResNet architecture, inspired by the anti-phase inhibition phenomenon observed in the primary visual cortex. This unit redefines the traditional convolutional layer by implementing a pair of complementary filters: a trainable push kernel and its counterpart, the pull kernel. The push kernel (analogous to traditional convolution) learns to respond to specific stimuli, while the pull kernel reacts to the same stimuli but of opposite contrast. This configuration enhances stimulus selectivity and effectively inhibits response in regions lacking preferred stimuli. This effect is attributed to the push and pull kernels, which produce responses of comparable magnitude in such regions, thereby neutralizing each other. The incorporation of the PushPull-Conv into ResNets significantly increases their robustness to image corruption. Our experiments with benchmark corruption datasets show that the PushPull-Conv can be combined with other data augmentation techniques to further improve model robustness. We set a new robustness benchmark on ResNet50 achieving an $mCE$ of 49.95$\%$ on ImageNet-C when combining PRIME augmentation with PushPull inhibition.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
