Berker Demirel

I am a PhD candidate at IST Austria. My research interests lie in the domains of domain generalization and out-of-distribution generalization, where statistical and information-theoretical interpretations of the models are emphasized.

Prior to beginning my PhD, I earned a master's degree from Sabanci University. During this time, I was a member of the VPA Lab and was under the supervision of Asst. Prof. Huseyin Ozkan and Asst. Prof. Erchan Aptoula. The primary focus of my master's studies was on group activity recognition and domain generalization.

In the summer of 2019, I completed a summer internship at Erasmus University Rotterdam.

Email  /  CV  /  GitHub  /  Google Scholar  /  Twitter

profile photo
Publications and Projects
ADRMX: Additive Disentanglement of Domain Features with Remix Loss
Berker Demirel, Erchan Aptoula, Huseyin Ozkan
arXiv:2308.06624, 2023
pdf / code / bib

We propose an additive disentanglement of domain specific and domain invariant features for the domain generalization problem. Unlike prior work, we demonstrate the potential benefits of utilizing domain specific features along with domain invariant ones. Moreover, we introduce a new data augmentation technique to enhance the generalization capacity of the architecture, where samples from different domains are mixed within the latent space.

DECOMPL: Decompositional Learning with Attention Pooling for Group Activity Recognition from a Single Volleyball Image
Berker Demirel, Huseyin Ozkan,
arXiv:2303.06439, 2023
pdf / code / bib

We show that Group Activity Recognition Problem can be formulated using Attention Pooling mechanism and can perform on par with the other state-of-the-art methods even with a single RGB frame. Moreover, we manually reannotated the flawed instances in the Volleyball Dataset, which is one of the widely used datasets in Group Activity Recognition.

Vertex Ordering Algorithms for Graph Coloring Problem
Berker Demirel, Arda Asik, Bugra Demir, Kamer Kaya, Baris Batuhan Topal
IEEE Signal Processing and Communications Applications (SIU), 2020
pdf / code / bib

We developed a ranking algorithm that uses metrics of degree 1/2/3, closeness centrality, clustering coefficient, and page rank to rank the nodes in a graph. Then, we applied greedy coloring to the graph using the ranking as a guide, which resulted in significantly better colorings. Furthermore, we tried to extend this idea using a model-free policy based reinforcement learning algorithm while parallelizing C++ backend using OpenMP.

Implementation of a small GPT from scratch
Berker Demirel
pdf / code

I re-implemented Andrej Karpathy's nanoGPT. It is designed to be simpler and easier to update. Performance evaluation is performed on Tiny Shakespeare Dataset and results can be found in the repository.

Implementation of UMAP in Python (Course Project)
Berker Demirel
pdf / code

I implemented Uniform Manifold Approximation and Projection (UMAP) algorithm in Python from scratch and performed experiments on MNIST and Load Digits datasets.

Implementation of DCGAN using PyTorch (Course Project)
Berker Demirel
pdf / code

I implemented convolutional Generator-Discriminator based GAN using PyTorch, and performed experiments on MNIST, CIFAR-10 and Celeb-A datasets.

Implementation of Expectation-Maximization Algorithm using Matlab (Course Project)
Berker Demirel
pdf / code

I implemented Expectation-Maximization algorithm for Gaussian Mixture Model using Matlab.

Implementation of Direction-Optimized Breadth First Search using OpenMP and CUDA (Course Project)
Berker Demirel, Naci Ege Sarac
pdf / code

We implemented Direction-Optimized BFS using OpenMP and CUDA.


Website template credits to Jon Barron.