Paul Gavrikov's repositories
visualkeras
Visualkeras is a Python package to help visualize Keras (either standalone or included in TensorFlow) neural network architectures. It allows easy styling to fit most needs. This module supports layered style architecture generation which is great for CNNs (Convolutional Neural Networks), and a graph style architecture, which works great for most models including plain feed-forward networks.
CNN-Filter-DB
A database of over 1.4 billion 3x3 convolution filters extracted from hundreds of diverse CNN models with relevant meta information (CVPR 2022 ORAL)
vlm_shapebias
Official code for "Can We Talk Models Into Seeing the World Differently?" (ICLR 2025).
parallel-matplotlib-grid
This Python 3 module helps you speedup generation of subplots in pseudo-parallel mode using matplotlib and multiprocessing. This can be useful if you are dealing with expensive preprocessing or plotting tasks such as violin plots per subplot.
biases_vs_generalization
Official code for the CVPR 2024 Paper "Can Biases in ImageNet Models Explain Generalization?".
arxiv-deep-research
A LLM based research assistant that generates a report based on papers from arxiv.org
torchconvquality
A library for PyTorch model convolution quality analysis.
diffusion-noise-cls-pytorch
This is an unofficial implementation of the diffusion-style noise frontend in "Intriguing properties of generative classifiers" by Priyank Jaini, Kevin Clark, Robert Geirhos to improve the shape-bias of vision models.
tinytorchtrainer
A small framework to train image classifiers in PyTorch
adversarial_solarization
Official implementation of Don't Look into the Sun: Adversarial Solarization Attacks on Image Classifiers
layer_criticality
Code for the paper "How Do Training Methods Influence the Utilization of Vision Models?"
adversarial_training_vs_humans
Official repository for the CVPRW2023 paper "An Extended Study of Human-like Behavior under Adversarial Training".
padding_robustness
Official repository for the ICCVW2023 paper "On the Interplay of Convolutional Padding and Adversarial Robustness".
torchconvview
A library for PyTorch convolution layer visualizations.
visualtorch
VisualTorch aims to help visualize Torch-based neural network architectures.
ImageBind
ImageBind One Embedding Space to Bind Them All
InternImage
[CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
keuper-labs
Keuper Labs website
kornia
Computer Vision and Robotics Library for AI
model-vs-human
Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)
Papers-of-Robust-ML
Related papers for robust machine learning
pytorch-image-models
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
pytorch_lenet5
A clean implementation of LeNet-5 for MNIST in PyTorch without any tweaks.
vonenet
Repository for VOneNet models