Research Outputs
Permanent URI for this communityhttps://hdl.handle.net/20.500.14288/2
Browse
14 results
Search Results
Publication Restricted Domain adaptation for speech-driven affective facial features synthesis(Koç University, 2020) Sadıq, Rızwan; Erzin, Engin; 0000-0002-2715-2368; Koç University Graduate School of Sciences and Engineering; Electrical and Electronics Engineering; 34503Publication Restricted Efficient machine learning models for cancer biology(Koç University, 2022) Bektaş, Ayyüce Begüm; Gönen, Mehmet; 0000-0002-2483-075X; Koç University Graduate School of Sciences and Engineering; Industrial Engineering and Operations Management; 237468
Publication Metadata only Flexible luma-chroma bit allocation in learned image compression for high-fidelity sharper images(IEEE, 2022) N/A; Department of Electrical and Electronics Engineering; Ulaş, Ökkeş Uğur; Tekalp, Ahmet Murat; Master student; Faculty Member; Department of Electrical and Electronics Engineering; Graduate School of Sciences and Engineering; College of Engineering; N/A; 26207High-fidelity learned image/video compression solutions are typically optimized with respect to l1 or l2 loss in RGB 444 format and evaluated by RGB PSNR. It is well-known that optimization of a fidelity criterion results in blurry images, which is typically alleviated by adding a content-based and/or adversarial loss terms. However, such conditional generative models result in loss of fidelity. In this paper, we propose a simple solution to obtain sharper images without losing fidelity based on learned flexible-rate coding using gained variational auto-encoder (gained-VAE) in the luma-chroma (YCrCb 444) domain. This allows us to implement image-adaptive luma-chroma bit allocation during inference, i.e., to increase Y PSNR at the expense of slightly lower chroma PSNR to obtain sharper images without introducing color artifacts based on the observation that Y PSNR correlates with image sharpness better than RGB PSNR. We note that the proposed inference-time image-adaptive luma-chroma bit allocation strategy can be incorporated into any VAE-based image compression model. Experimental results show that sharper images with better VMAF and Y PSNR can be obtained by optimizing models for YCrCb MSE with the proposed image-adaptive luma-chroma bit/quality allocation compared to stateof-the-art models optimizing RGB MSE at the same bpp.Publication Restricted ICT-based understanding of spinal cord networks with applications to spinal cord injuries(Koç University, 2018) Civaş, Meltem; Akan, Özgür Barış; 0000-0003-2523-3858; Koç University Graduate School of Sciences and Engineering; Electrical and Electronics Engineering; 6647Publication Restricted Intent prediction in pHRI: subtask recognition with deep learning(Koç University, 2020) Erdem, Utku; Akgün, Barış; 0000-0002-4079-6889; Koç University Graduate School of Sciences and Engineering; Computer Science and Engineering; 258784Publication Restricted Kernel and launch time optimizations for deep learning frameworks(Koç University, 2019) Dikbayır, Doğa; Erten, Didem Unat; 0000-0002-2351-0770; Koç University Graduate School of Sciences and Engineering; Computer Science and Engineering; 219274Publication Restricted MILP based hyper-box enclosure approach to multi-class data classification(Koç University, 2009) Yüksektepe, Fadime Üney; Türkay, Metin; 0000-0003-4769-6714; Koç University Graduate School of Sciences and Engineering; Industrial Engineering and Operations Management; 24956Publication Restricted Morphological tagging and lemmatization with neural components(Koç University, 2018) Dayanık, Erenay; Yüret, Deniz; 0000-0002-7039-0046; Koç University Graduate School of Sciences and Engineering; Computer Science and Engineering; 179996Publication Restricted Optimizing multiple object tracking with graph neural networks on a graphcore IPU(Koç University, 2024) Acar, Mustafa Orkun; Erten, Didem Unat; 0000-0002-2351-0770; Koç University Graduate School of Sciences and Engineering; Computer Science and Engineering; 219274Publication Restricted RGB-D Object recognition using deep convolutional neural networks(Koç University, 2016) Zia, Saman; Yemez, Yücel; 0000-0002-7515-3138; Koç University Graduate School of Sciences and Engineering; Computer Science and Engineering; 107907