Papers › PushPull-Net: Inhibition-driven ResNet robust to image corruptions

PushPull-Net: Inhibition-driven ResNet robust to image corruptions

7 Aug 2024arXiv:2408.04077archive 2025-07-28

Guru Swaroop Bennabhaktula, Enrique Alegre, Nicola Strisciuglio, George Azzopardi

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.

PaperPDFCode

Code

bgswaroop/pushpull-conv officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Data AugmentationDomain Generalization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Generalization ImageNet-C ResNet-50 (PushPull-Conv) + PRIME Number of params 25.6 #27 of 47 Archive leaderboard report
Domain Generalization ImageNet-C ResNet-50 (PushPull-Conv) + PRIME Top 1 Accuracy 69.4 #27 of 47 Archive leaderboard report
Domain Generalization ImageNet-C ResNet-50 (PushPull-Conv) + PRIME mean Corruption Error (mCE) 49.95 #27 of 47 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: PushPull-Conv

Average PoolingConvolutionGlobal Average PoolingKaiming InitializationMax PoolingPushPull-ConvSET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections