Samet Hicsonmez
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Samet Hicsonmez has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Emre Akbas
Middle East Technical University (METU)
7 shared publications - Nermin Samet
Valeo.ai
5 shared publications - Pinar Duygulu
Hacettepe University Ankara Turkey
5 shared publications Fidan Samet
1 shared publication- Nermin Samet
Ecole des Ponts Univ Gustave Eiffel CNRS Marne-la-Vallée France
1 shared publication - Nermin Samet
Middle East Technical University Ankara Turkey
1 shared publication
Latest Publications
- Open Access
- 20 October 2026
- Published by Elsevier in SSRN Electronic Journal
NSYNC: Negative Synthetic Image Generation for Contrastive Training to Improve Stylized Text-To-Image Translation
Text-conditioned image generation models can synthesize highly realistic images, but they fail to capture specific styles. Fine-tuning on style-specific datasets alone is not always sufficient to capture the defining characteristics of a target style. In this work, we introduce NSYNC, a contrastive training framework for improving the stylization capability of large text-to-image diffusion models through synthetic negative samples.Unlike conventional synthetic data generation, which typically augments real datasets with additional positive examples, NSYNC constructs synthetic negative sets and trains them jointly with real positive images in a novel contrastive training scheme. Specifically, we compute gradients from positive and negative samples and refine the positive gradient by removing its projection onto the negative gradient. The resulting orthogonal update suppresses attributes shared by both sets and emphasizes features that are more distinctive of the target style.Extensive experiments across multiple painter and illustrator styles demonstrate that NSYNC consistently improves over baseline methods in both quantitative metrics and qualitative evaluations. Our code is available at \url{https://github.com/giddyyupp/NSYNC}.
- 20 October 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessNSYNC: Negative Synthetic Image Generation for Contrastive Training to Improve Stylized Text-To-Image Translation
Text-conditioned image generation models can synthesize highly realistic images, but they fail to capture specific styles. Fine-tuning on style-specific datasets alone is not always sufficient to capture the defining characteristics of a target style. In this work, we introduce NSYNC, a contrastive training framework for improving the stylization capability of large text-to-image diffusion models through synthetic negative samples.Unlike conventional synthetic data generation, which typically augments real datasets with additional positive examples, NSYNC constructs synthetic negative sets and trains them jointly with real positive images in a novel contrastive training scheme. Specifically, we compute gradients from positive and negative samples and refine the positive gradient by removing its projection onto the negative gradient. The resulting orthogonal update suppresses attributes shared by both sets and emphasizes features that are more distinctive of the target style.Extensive experiments across multiple painter and illustrator styles demonstrate that NSYNC consistently improves over baseline methods in both quantitative metrics and qualitative evaluations. Our code is available at \url{https://github.com/giddyyupp/NSYNC}.
- 1 April 2025
- Published by Elsevier in Neurocomputing
- Vol. 637
WAIT: Feature warping for animation to illustration video translation using GANs
- 1 April 2025
- Published by Elsevier in Neurocomputing
- Vol. 637
WAIT: Feature warping for animation to illustration video translation using GANs
- Open Access
Improving Sketch Colorization using Adversarial Segmentation Consistency
We propose a new method for producing color images from sketches. Current solutions in sketch colorization either necessitate additional user instruction or are restricted to the "paired" translation strategy. We leverage semantic image segmentation from a general-purpose panoptic segmentation network to generate an additional adversarial loss function. The proposed loss function is compatible with any GAN model. Our method is not restricted to datasets with segmentation labels and can be applied to unpaired translation tasks as well. Using qualitative, and quantitative analysis, and based on a user study, we demonstrate the efficacy of our method on four distinct image datasets. On the FID metric, our model improves the baseline by up to 35 points. Our code, pretrained models, scripts to produce newly introduced datasets and corresponding sketch images are available at https://github.com/giddyyupp/AdvSegLoss.
Open AccessImproving Sketch Colorization using Adversarial Segmentation Consistency
We propose a new method for producing color images from sketches. Current solutions in sketch colorization either necessitate additional user instruction or are restricted to the "paired" translation strategy. We leverage semantic image segmentation from a general-purpose panoptic segmentation network to generate an additional adversarial loss function. The proposed loss function is compatible with any GAN model. Our method is not restricted to datasets with segmentation labels and can be applied to unpaired translation tasks as well. Using qualitative, and quantitative analysis, and based on a user study, we demonstrate the efficacy of our method on four distinct image datasets. On the FID metric, our model improves the baseline by up to 35 points. Our code, pretrained models, scripts to produce newly introduced datasets and corresponding sketch images are available at https://github.com/giddyyupp/AdvSegLoss.
- 22 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-15
HoughNet: Integrating Near and Long-Range Evidence for Visual Detection
This paper presents HoughNet, a one-stage, anchor-free, voting-based, bottom-up object detection method. Inspired by the Generalized Hough Transform, HoughNet determines the presence of an object at a certain location by the sum of the votes cast on that location. Votes are collected from both near and long-distance locations based on a log-polar vote field. Thanks to this voting mechanism, HoughNet is able to integrate both near and long-range, class-conditional evidence for visual recognition, thereby generalizing and enhancing current object detection methodology, which typically relies on only local evidence. On the COCO dataset, HoughNet's best model achieves 46.4$AP$ (and 65.1$AP_{50}$ ), performing on par with the state-of-the-art in bottom-up object detection and outperforming most major one-stage and two-stage methods. We further validate the effectiveness of our proposal in other visual detection tasks, namely, video object detection, instance segmentation, 3D object detection and keypoint detection for human pose estimation, and an additional “labels to photo” image generation task, where the integration of our voting module consistently improves performance in all cases. Code is available at https://github.com/nerminsamet/houghnet.- 22 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-15
HoughNet: Integrating Near and Long-Range Evidence for Visual Detection
This paper presents HoughNet, a one-stage, anchor-free, voting-based, bottom-up object detection method. Inspired by the Generalized Hough Transform, HoughNet determines the presence of an object at a certain location by the sum of the votes cast on that location. Votes are collected from both near and long-distance locations based on a log-polar vote field. Thanks to this voting mechanism, HoughNet is able to integrate both near and long-range, class-conditional evidence for visual recognition, thereby generalizing and enhancing current object detection methodology, which typically relies on only local evidence. On the COCO dataset, HoughNet's best model achieves 46.4$AP$ (and 65.1$AP_{50}$ ), performing on par with the state-of-the-art in bottom-up object detection and outperforming most major one-stage and two-stage methods. We further validate the effectiveness of our proposal in other visual detection tasks, namely, video object detection, instance segmentation, 3D object detection and keypoint detection for human pose estimation, and an additional “labels to photo” image generation task, where the integration of our voting module consistently improves performance in all cases. Code is available at https://github.com/nerminsamet/houghnet.- Open Access
HoughNet: Integrating near and long-range evidence for visual detection
This paper presents HoughNet, a one-stage, anchor-free, voting-based, bottom-up object detection method. Inspired by the Generalized Hough Transform, HoughNet determines the presence of an object at a certain location by the sum of the votes cast on that location. Votes are collected from both near and long-distance locations based on a log-polar vote field. Thanks to this voting mechanism, HoughNet is able to integrate both near and long-range, class-conditional evidence for visual recognition, thereby generalizing and enhancing current object detection methodology, which typically relies on only local evidence. On the COCO dataset, HoughNet's best model achieves $46.4$ $AP$ (and $65.1$ $AP_{50}$), performing on par with the state-of-the-art in bottom-up object detection and outperforming most major one-stage and two-stage methods. We further validate the effectiveness of our proposal in other visual detection tasks, namely, video object detection, instance segmentation, 3D object detection and keypoint detection for human pose estimation, and an additional "labels to photo" image generation task, where the integration of our voting module consistently improves performance in all cases. Code is available at https://github.com/nerminsamet/houghnet.Open AccessHoughNet: Integrating near and long-range evidence for visual detection
This paper presents HoughNet, a one-stage, anchor-free, voting-based, bottom-up object detection method. Inspired by the Generalized Hough Transform, HoughNet determines the presence of an object at a certain location by the sum of the votes cast on that location. Votes are collected from both near and long-distance locations based on a log-polar vote field. Thanks to this voting mechanism, HoughNet is able to integrate both near and long-range, class-conditional evidence for visual recognition, thereby generalizing and enhancing current object detection methodology, which typically relies on only local evidence. On the COCO dataset, HoughNet's best model achieves $46.4$ $AP$ (and $65.1$ $AP_{50}$), performing on par with the state-of-the-art in bottom-up object detection and outperforming most major one-stage and two-stage methods. We further validate the effectiveness of our proposal in other visual detection tasks, namely, video object detection, instance segmentation, 3D object detection and keypoint detection for human pose estimation, and an additional "labels to photo" image generation task, where the integration of our voting module consistently improves performance in all cases. Code is available at https://github.com/nerminsamet/houghnet. - Open Access
Reducing Label Noise in Anchor-Free Object Detection
Current anchor-free object detectors label all the features that spatially fall inside a predefined central region of a ground-truth box as positive. This approach causes label noise during training, since some of these positively labeled features may be on the background or an occluder object, or they are simply not discriminative features. In this paper, we propose a new labeling strategy aimed to reduce the label noise in anchor-free detectors. We sum-pool predictions stemming from individual features into a single prediction. This allows the model to reduce the contributions of non-discriminatory features during training. We develop a new one-stage, anchor-free object detector, PPDet, to employ this labeling strategy during training and a similar prediction pooling method during inference. On the COCO dataset, PPDet achieves the best performance among anchor-free top-down detectors and performs on-par with the other state-of-the-art methods. It also outperforms all major one-stage and two-stage methods in small object detection (${AP}_{S}$ $31.4$). Code is available at https://github.com/nerminsamet/ppdet
Open AccessReducing Label Noise in Anchor-Free Object Detection
Current anchor-free object detectors label all the features that spatially fall inside a predefined central region of a ground-truth box as positive. This approach causes label noise during training, since some of these positively labeled features may be on the background or an occluder object, or they are simply not discriminative features. In this paper, we propose a new labeling strategy aimed to reduce the label noise in anchor-free detectors. We sum-pool predictions stemming from individual features into a single prediction. This allows the model to reduce the contributions of non-discriminatory features during training. We develop a new one-stage, anchor-free object detector, PPDet, to employ this labeling strategy during training and a similar prediction pooling method during inference. On the COCO dataset, PPDet achieves the best performance among anchor-free top-down detectors and performs on-par with the other state-of-the-art methods. It also outperforms all major one-stage and two-stage methods in small object detection (${AP}_{S}$ $31.4$). Code is available at https://github.com/nerminsamet/ppdet
- Open Access
GANILLA: Generative Adversarial Networks for Image to Illustration Translation
In this paper, we explore illustrations in children's books as a new domain in unpaired image-to-image translation. We show that although the current state-of-the-art image-to-image translation models successfully transfer either the style or the content, they fail to transfer both at the same time. We propose a new generator network to address this issue and show that the resulting network strikes a better balance between style and content. There are no well-defined or agreed-upon evaluation metrics for unpaired image-to-image translation. So far, the success of image translation models has been based on subjective, qualitative visual comparison on a limited number of images. To address this problem, we propose a new framework for the quantitative evaluation of image-to-illustration models, where both content and style are taken into account using separate classifiers. In this new evaluation framework, our proposed model performs better than the current state-of-the-art models on the illustrations dataset. Our code and pretrained models can be found at https://github.com/giddyyupp/ganilla.
Open AccessGANILLA: Generative Adversarial Networks for Image to Illustration Translation
In this paper, we explore illustrations in children's books as a new domain in unpaired image-to-image translation. We show that although the current state-of-the-art image-to-image translation models successfully transfer either the style or the content, they fail to transfer both at the same time. We propose a new generator network to address this issue and show that the resulting network strikes a better balance between style and content. There are no well-defined or agreed-upon evaluation metrics for unpaired image-to-image translation. So far, the success of image translation models has been based on subjective, qualitative visual comparison on a limited number of images. To address this problem, we propose a new framework for the quantitative evaluation of image-to-illustration models, where both content and style are taken into account using separate classifiers. In this new evaluation framework, our proposed model performs better than the current state-of-the-art models on the illustrations dataset. Our code and pretrained models can be found at https://github.com/giddyyupp/ganilla.
- 1 May 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 1-4
Could we create a training set for image captioning using automatic translation?
Automatic image captioning has received increasing attention in recent years. Although there are many English datasets developed for this problem, there is only one Turkish dataset and it is very small compared to its English counterparts. Creating a new dataset for image captioning is a very costly and time consuming task. This work is a first step towards transferring the available, large English datasets into Turkish. We translated English captioning datasets into Turkish by using an automated translation tool and we trained an image captioning model on the automatically obtained Turkish captions. Our experiments show that this model yields the best performance so far on Turkish captioning.
- 1 May 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 1-4
Could we create a training set for image captioning using automatic translation?
Automatic image captioning has received increasing attention in recent years. Although there are many English datasets developed for this problem, there is only one Turkish dataset and it is very small compared to its English counterparts. Creating a new dataset for image captioning is a very costly and time consuming task. This work is a first step towards transferring the available, large English datasets into Turkish. We translated English captioning datasets into Turkish by using an automated translation tool and we trained an image captioning model on the automatically obtained Turkish captions. Our experiments show that this model yields the best performance so far on Turkish captioning.