Behçet Uğur Töreyın

Onur Can Koyun, Reyhan Kevser Keser, İbrahim Batuhan Akkaya et al.

Despite recent advances, object detection in aerial images is still a challenging task. Specific problems in aerial images makes the detection problem harder, such as small objects, densely packed objects, objects in different sizes and with different orientations. To address small object detection problem, we propose a two-stage object detection framework called "Focus-and-Detect". The first stage which consists of an object detector network supervised by a Gaussian Mixture Model, generates clusters of objects constituting the focused regions. The second stage, which is also an object detector network, predicts objects within the focal regions. Incomplete Box Suppression (IBS) method is also proposed to overcome the truncation effect of region search approach. Results indicate that the proposed two-stage framework achieves an AP score of 42.06 on VisDrone validation dataset, surpassing all other state-of-the-art small object detection methods reported in the literature, to the best of authors' knowledge.

Yunus Sevim, Behçet Uğur Töreyin

Infrared small target detection remains challenging due to severe background clutter, low contrast, and weak spatial responses where geometric overlap alone is insufficient to characterize detection quality. In this work, we propose REEM (Reweighted Explicit-visibility Enhanced Modulation), a lightweight SCR-guided difficulty-aware optimization framework that incorporates Signal-to-Clutter Ratio (SCR) as a physically meaningful visibility prior during training. Instead of modifying the network architecture or directly optimizing SCR, REEM computes a ground-truth local SCR from the input image and applies a differentiable modulation to the soft-IoU learning signal, emphasizing low-visibility targets while preserving stable optimization and identical inference behavior. REEM is integrated into a U-Net-based MSHNet without introducing additional parameters, architectural modifications, or inference-time overhead. Extensive experiments demonstrate consistent improvements over the baseline, achieving higher IoU and detection probability (Pd) together with substantially reduced false alarms (FA), particularly under challenging low-visibility conditions. These results suggest that SCR-guided difficulty-aware optimization provides an effective and physically grounded complement to conventional overlap-based objectives for infrared small target detection. The code is available at https://github. com/yall-in-one/Reemm.

Onur Can Koyun, Behçet Uğur Töreyin

Deep learning models like Transformers and Convolutional Neural Networks (CNNs) have revolutionized various domains, but their parameter-intensive nature hampers deployment in resource-constrained settings. In this paper, we introduce a novel concept utilizes column space and row space of weight matrices, which allows for a substantial reduction in model parameters without compromising performance. Leveraging this paradigm, we achieve parameter-efficient deep learning models.. Our approach applies to both Bottleneck and Attention layers, effectively halving the parameters while incurring only minor performance degradation. Extensive experiments conducted on the ImageNet dataset with ViT and ResNet50 demonstrate the effectiveness of our method, showcasing competitive performance when compared to traditional models. This approach not only addresses the pressing demand for parameter efficient deep learning solutions but also holds great promise for practical deployment in real-world scenarios.

Muhammet Sebul Beratoğlu, Behçet Uğur Töreyin

In the field of video analytics, particularly traffic surveillance, there is a growing need for efficient and effective methods for processing and understanding video data. Traditional full video decoding techniques can be computationally intensive and time-consuming, leading researchers to explore alternative approaches in the compressed domain. This study introduces a novel random perturbation-based compressed domain method for reconstructing images from High Efficiency Video Coding (HEVC) bitstreams, specifically designed for traffic surveillance applications. To the best of our knowledge, our method is the first to propose substituting random perturbations for residual values, creating a condensed representation of the original image while retaining information relevant to video understanding tasks, particularly focusing on vehicle detection and classification as key use cases. By not using residual data, our proposed method significantly reduces the data needed in the image reconstruction process, allowing for more efficient storage and transmission of information. This is particularly important when considering the vast amount of video data involved in surveillance applications. Applied to the public BIT-Vehicle dataset, we demonstrate a significant increase in the reconstruction speed compared to the traditional full decoding approach, with our proposed method being approximately 56% faster than the pixel domain method. Additionally, we achieve a detection accuracy of 99.9%, on par with the pixel domain method, and a classification accuracy of 96.84%, only 0.98% lower than the pixel domain method. Furthermore, we showcase the significant reduction in data size, leading to more efficient storage and transmission. Our research establishes the potential of compressed domain methods in traffic surveillance applications, where speed and data size are critical factors.

Didem Makaroglu, Altan Cakir, Behcet Ugur Toreyin

Clickstream data, which come with a massive volume generated by human activities on websites, have become a prominent feature for identifying readers' characteristics by newsrooms after the digitization of news outlets. Although the nature of clickstream data has a similar logic within websites, it has inherent limitations in recognizing human behaviours when looking from a broad perspective, which brings the need to limit the problem in niche areas. This study investigates the anonymized readers' click activities on the organizations' websites to identify news consumption patterns following referrals from Twitter,who incidentally reach but propensity is mainly routed news content. Methodologies for ensemble cluster analysis with mixed-type embedding strategies are applied and compared to find similar reader groups and interests independent of time. Various internal validation perspectives are used to determine the optimality of the quality of clusters, where the Calinski Harabasz Index (CHI) is found to give a generalizable result. Our findings demonstrate that clustering a mixed-type dataset approaches the optimal internal validation scores, which we define to discriminate the clusters and algorithms considering applied strategies when embedded by Uniform Manifold Approximation and Projection (UMAP) and using a consensus function as a key to access the most applicable hyperparameter configurations in the given ensemble rather than using consensus function results directly. Evaluation of the resulting clusters highlights specific clusters repeatedly present in the separated monthly samples by Adjusted Mutual Information scores greater than 0.5, which provide insights to the news organizations and overcome the degradation of the modeling behaviours due to the change in the interest over time.

Indrit Nallbani, Reyhan Kevser Keser, Aydin Ayanzadeh et al.

Graph autoencoders are efficient at embedding graph-based data sets. Most graph autoencoder architectures have shallow depths which limits their ability to capture meaningful relations between nodes separated by multi-hops. In this paper, we propose Residual Variational Graph Autoencoder, ResVGAE, a deep variational graph autoencoder model with multiple residual modules. We show that our multiple residual modules, a convolutional layer with residual connection, improve the average precision of the graph autoencoders. Experimental results suggest that our proposed model with residual modules outperforms the models without residual modules and achieves similar results when compared with other state-of-the-art methods.

Reyhan Kevser Keser, Aydin Ayanzadeh, Omid Abdollahi Aghdam et al.

One of the most efficient methods for model compression is hint distillation, where the student model is injected with information (hints) from several different layers of the teacher model. Although the selection of hint points can drastically alter the compression performance, conventional distillation approaches overlook this fact and use the same hint points as in the early studies. Therefore, we propose a clustering based hint selection methodology, where the layers of teacher model are clustered with respect to several metrics and the cluster centers are used as the hint points. Our method is applicable for any student network, once it is applied on a chosen teacher network. The proposed approach is validated in CIFAR-100 and ImageNet datasets, using various teacher-student pairs and numerous hint distillation methods. Our results show that hint points selected by our algorithm results in superior compression performance compared to state-of-the-art knowledge distillation algorithms on the same student models and datasets.

Süleyman Aslan, Uğur Güdükbay, B. Uğur Töreyin et al.

Real-time flame detection is crucial in video based surveillance systems. We propose a vision-based method to detect flames using Deep Convolutional Generative Adversarial Neural Networks (DCGANs). Many existing supervised learning approaches using convolutional neural networks do not take temporal information into account and require substantial amount of labeled data. In order to have a robust representation of sequences with and without flame, we propose a two-stage training of a DCGAN exploiting spatio-temporal flame evolution. Our training framework includes the regular training of a DCGAN with real spatio-temporal images, namely, temporal slice images, and noise vectors, and training the discriminator separately using the temporal flame images without the generator. Experimental results show that the proposed method effectively detects flame in video with negligible false positive rates in real-time.

Abdulkadir Albayrak, Asli Unlu, Nurullah Calik et al.

The cervical cancer developing from the precancerous lesions caused by the Human Papilloma Virus (HPV) has been one of the preventable cancers with the help of periodic screening. There are two types of grading conventions widely accepted among pathologists. On the other hand, inter-observer variability is an important issue for final diagnosis. In this paper, a whole-slide image grading benchmark for cervical cancer precursor lesions is introduced. The papillae of the cervical epithelium and overlapping cell problems are handled and a tissue classification method with a novel morphological feature exploiting the relative orientation between the BM and the major axis of all nuclei is developed and its performance is evaluated. Besides, the inter-observer variability is also revealed by a thorough comparison among pathologists' decisions, as well as, the final diagnosis.