-
Ghent University
- Incheon, South Korea
- utkuozbulak.github.io
- https://orcid.org/0000-0003-3084-6034
- in/utkuozbulak
Stars
GDMaim is a GDScript obfuscation plugin for the Godot Engine.
A large library of free and open-source shaders for the Godot game engine. Here, you'll get 2D and 3D shaders with playable demos.
Materials for the paper (Bioinformatics) "Mutate and Observe: Utilizing Deep Neural Networks to Investigate the Impact of Mutations on Translation Initiation"
(ICLR 2022 Spotlight) Official PyTorch implementation of "How Do Vision Transformers Work?"
Probing the representations of Vision Transformers.
(ICLR 2023) Official PyTorch implementation of "What Do Self-Supervised Vision Transformers Learn?"
Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"
A small library for automatical adjustment of text position in matplotlib plots to minimize overlaps.
solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning
Code and some materials from the papers "Selection of Source Images Heavily Influences the Effectiveness of Adversarial Attacks" (BMVC 2021) and "Evaluating Adversarial Attacks on ImageNet:A Realit…
Large yet imperceptible adversarial perturbations with perceptual color distance (CVPR 2020)
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
Matlab implementation of automated model reduction of biochemical reaction networks
Code and materials for the paper "Regional Image Perturbation Reduces Lp Norms of Adversarial Examples While Maintaining Model-to-model Transferability" (ICML 2020, UDL).
Robustness vs Accuracy Survey on ImageNet
Novel Coronavirus (COVID-19) Cases, provided by JHU CSSE
Latex code for making neural networks diagrams
Proper implementation of ResNet-s for CIFAR10/100 in pytorch that matches description of the original paper.
official implementation of "Visualization of Convolutional Neural Networks for Monocular Depth Estimation"
Pre-trained model, code, and materials from the paper "Impact of Adversarial Examples on Deep Learning Models for Biomedical Image Segmentation" (MICCAI 2019).
Code for ICML 2019 paper "Simple Black-box Adversarial Attacks"
A Pytorch implement of 《Deeper Depth Prediction with Fully Convolutional Residual Networks》
Pytorch Implementation of Deeper Depth Prediction with Fully Convolutional Residual Networks
Pre-trained models, data, code & materials from the paper "ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness" (ICLR 2019 Oral)
Code to create Stylized-ImageNet, a stylized version of standard ImageNet (ICLR 2019 Oral)
Visualisation tool for CNNs in pytorch
Collection of scripts and tweaks to adapt Ubuntu running smooth on Dell XPS 15 9570.