adobe/antialiased-cnns

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

1683 stars · 202 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A PyTorch library providing antialiased CNN models and a BlurPool layer from the ICML 2019 paper 'Making Convolutional Networks Shift-Invariant Again'. It replaces standard downsampling operations (max-pooling, strided convolution) with low-pass filtered versions to improve shift-invariance, consistency, and accuracy.

Use cases

• make my CNN robust to small image shifts
• improve classification consistency on ImageNet
• load a pretrained antialiased ResNet as a backbone
• replace max-pooling with a blur pool layer in my architecture
• finetune an existing model with antialiasing
• reduce sensitivity of my vision model to input corruptions

When to choose

• you need a PyTorch vision backbone with better shift-invariance and robustness
• you want to drop-in replace pooling layers with BlurPool in an existing CNN
• you want pretrained antialiased variants of ResNet, DenseNet, VGG, or similar architectures

When to avoid

• you are not using PyTorch
• you need transformer-based vision models rather than CNNs
• you need actively developed features or frequent updates

Facets

library · maturity maintenance

machine-learning image-processing computer-vision deep-learning computer-vision machine-learning python cnn antialiasing blurpool shift-invariance pytorch pretrained-models icml-2019

Member repositories

For agents

markdown · JSON · MCP: product_card(name="adobe/antialiased-cnns")