Mete Ozay

Mete Ozay


Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 October 2017 in Brain Imaging and Behavior
Verified
Journal Article
Closed access
PDF file
IEItir Onal Ertugrul
Itir Onal Ertugrul
MOMete Ozay
Mete Ozay
FVFatos T. Yarman Vural
Fatos T. Yarman Vural

15 June 2018 in Brain Imaging and Behavior
Verified
Journal Article
Closed access
PDF file
IEItir Onal Ertugrul
Itir Onal Ertugrul
MOMete Ozay
Mete Ozay
FVFatos T Yarman Vural
Fatos T Yarman Vural

22 September 2018 in arXiv
Verified
Preprint
Open access
PDF file
JHJunjie Hu
Junjie Hu
MOMete Ozay
Mete Ozay
YZYan Zhang
Yan Zhang
TOTakayuki Okatani
Takayuki Okatani
This paper considers the problem of single image depth estimation. The employment of convolutional neural networks (CNNs) has recently brought about significant advancements in the research of this problem. However, most existing methods suffer from loss of spatial resolution in the estimated depth maps; a typical symptom is distorted and blurry reconstruction of object boundaries. In this paper, toward more accurate estimation with a focus on depth maps with higher spatial resolution, we propose two improvements to existing approaches. One is about the strategy of fusing features extracted at different scales, for which we propose an improved network architecture consisting of four modules: an encoder, decoder, multi-scale feature fusion module, and refinement module. The other is about loss functions for measuring inference errors used in training. We show that three loss terms, which measure errors in depth, gradients and surface normals, respectively, contribute to improvement of accuracy in an complementary fashion. Experimental results show that these two improvements enable to attain higher accuracy than the current state-of-the-arts, which is given by finer resolution reconstruction, for example, with small objects and object boundaries.

1 March 2018 in arXiv
Verified
Preprint
Open access
PDF file
MSMasanori Suganuma
Masanori Suganuma
MOMete Ozay
Mete Ozay
TOTakayuki Okatani
Takayuki Okatani
Researchers have applied deep neural networks to image restoration tasks, in which they proposed various network architectures, loss functions, and training methods. In particular, adversarial training, which is employed in recent studies, seems to be a key ingredient to success. In this paper, we show that simple convolutional autoencoders (CAEs) built upon only standard network components, i.e., convolutional layers and skip connections, can outperform the state-of-the-art methods which employ adversarial training and sophisticated loss functions. The secret is to employ an evolutionary algorithm to automatically search for good architectures. Training optimized CAEs by minimizing the $\ell_2$ loss between reconstructed images and their ground truths using the ADAM optimizer is all we need. Our experimental results show that this approach achieves 27.8 dB peak signal to noise ratio (PSNR) on the CelebA dataset and 40.4 dB on the SVHN dataset, compared to 22.8 dB and 33.0 dB provided by the former state-of-the-art methods, respectively.

22 January 2019 in Brain Imaging and Behavior
Verified
Journal Article
Closed access
PDF file
IEItir Onal Ertugrul
Itir Onal Ertugrul
MOMete Ozay
Mete Ozay
FVFatos T. Yarman Vural
Fatos T. Yarman Vural

29 November 2016 in arXiv
Verified
Preprint
Open access
PDF file
ZSZhun Sun
Zhun Sun
MOMete Ozay
Mete Ozay
TOTakayuki Okatani
Takayuki Okatani
Despite the effectiveness of Convolutional Neural Networks (CNNs) for image classification, our understanding of the relationship between shape of convolution kernels and learned representations is limited. In this work, we explore and employ the relationship between shape of kernels which define Receptive Fields (RFs) in CNNs for learning of feature representations and image classification. For this purpose, we first propose a feature visualization method for visualization of pixel-wise classification score maps of learned features. Motivated by our experimental results, and observations reported in the literature for modeling of visual systems, we propose a novel design of shape of kernels for learning of representations in CNNs. In the experimental results, we achieved a state-of-the-art classification performance compared to a base CNN model [28] by reducing the number of parameters and computational time of the model using the ILSVRC-2012 dataset [24]. The proposed models also outperform the state-of-the-art models employed on the CIFAR-10/100 datasets [12] for image classification. Additionally, we analyzed the robustness of the proposed method to occlusion for classification of partially occluded images compared with the state-of-the-art methods. Our results indicate the effectiveness of the proposed approach. The code is available in github.com/minogame/caffe-qhconv.