no code implementations • 8 Jun 2023 • M. Esat Kalfaoglu, Halil Ibrahim Ozturk, Ozsel Kilinc, Alptekin Temizel
In this study, we have introduced a new approach called TopoMask for predicting centerlines in road topology.
Ranked #1 on 3D Lane Detection on OpenLane-V2 test
no code implementations • 5 Aug 2020 • Ozsel Kilinc, Giovanni Montana
Learning robot manipulation through deep reinforcement learning in environments with sparse rewards is a challenging task.
2 code implementations • 16 Oct 2019 • Ozsel Kilinc, Giovanni Montana
In order to exploit this idea, we introduce a framework whereby an object locomotion policy is initially obtained using a realistic physics simulator.
no code implementations • 3 Dec 2018 • Ozsel Kilinc, Giovanni Montana
An agent's policy depends on its own private observations as well as those explicitly shared by others through a communication medium.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • ICLR 2018 • Ozsel Kilinc, Ismail Uysal
In this paper, we propose a novel unsupervised clustering approach exploiting the hidden information that is indirectly introduced through a pseudo classification objective.
Ranked #1 on Unsupervised Image Classification on SVHN (using extra training data)
no code implementations • 19 May 2017 • Ozsel Kilinc, Ismail Uysal
Adjacency of the examples is inferred using the predictions of a neural network model which is first initialized by a supervised pretraining.
no code implementations • 1 Apr 2017 • Ozsel Kilinc, Ismail Uysal
We introduce a novel validation framework to measure the true robustness of learning models for real-world applications by creating source-inclusive and source-exclusive partitions in a dataset via clustering.
no code implementations • 28 Feb 2017 • Ozsel Kilinc, Ismail Uysal
As the proposed output layer modification duplicates the softmax nodes at the output layer for each class, GAR allows for competitive learning between these duplicates on a traditional error-correction learning framework to ultimately enable a neural network to learn the latent annotations in this partially supervised setup.