Alptekin Temizel

Fatih Cagatay Akyon, Alptekin Temizel

Rating a video based on its content is an important step for classifying video age categories. Movie content rating and TV show rating are the two most common rating systems established by professional committees. However, manually reviewing and evaluating scene/film content by a committee is a tedious work and it becomes increasingly difficult with the ever-growing amount of online video content. As such, a desirable solution is to use computer vision based video content analysis techniques to automate the evaluation process. In this paper, related works are summarized for action recognition, multi-modal learning, movie genre classification, and sensitive content detection in the context of content moderation and movie content rating. The project page is available at https://github.com/fcakyon/content-moderation-deep-learning.

Ayberk Aydin, Alptekin Temizel

Deep neural networks are known to be vulnerable to adversarial perturbations. The amount of these perturbations are generally quantified using $L_p$ metrics, such as $L_0$, $L_2$ and $L_\infty$. However, even when the measured perturbations are small, they tend to be noticeable by human observers since $L_p$ distance metrics are not representative of human perception. On the other hand, humans are less sensitive to changes in colorspace. In addition, pixel shifts in a constrained neighborhood are hard to notice. Motivated by these observations, we propose a method that creates adversarial examples by applying spatial transformations, which creates adversarial examples by changing the pixel locations independently to chrominance channels of perceptual colorspaces such as $YC_{b}C_{r}$ and $CIELAB$, instead of making an additive perturbation or manipulating pixel values directly. In a targeted white-box attack setting, the proposed method is able to obtain competitive fooling rates with very high confidence. The experimental evaluations show that the proposed method has favorable results in terms of approximate perceptual distance between benign and adversarially generated images. The source code is publicly available at https://github.com/ayberkydn/stadv-torch

Ümit Mert Çağlar, Alptekin Temizel

Semantic segmentation of remote sensing imagery requires models that capture both global context and local detail under tight computational budgets. Prior work typically optimizes for one of these axes: attention for global context, convolution for local detail, or compactness for efficiency. While hybrid approaches aim to capture both, they require architectural changes and encoder backbones with computational overhead, limiting efficiency and performance. We present LALE (Lightweight-transformer Architecture for Land-cover Estimation), an end-to-end remote sensing image segmentation architecture, that bifurcates its encoder by resolution: lightweight ConvMixer stages handle high-resolution local features, while transformer stages handle low-resolution global context, confining the quadratic cost of self-attention to deep, downsampled feature maps. An all-MLP multi-scale decoder, together with RMSNorm and StarReLU throughout, further reduces compute and parameter count. On the large-scale ARAS400k remote-sensing segmentation benchmark, LALE establishes a strong efficiency-performance trade-off against CNN, transformer, and hybrid baselines. Our smallest variant, (just 1.6M parameters), reaches within 2.6 F1 points of the best baseline (UPerNet) while using 4.5x fewer parameters, 7x less storage, 17x fewer GMACs, and delivering 1.8x higher throughput.

Ümit Mert Çağlar, Alptekin Temizel

Deep learning models benefit from increasing data diversity and volume, motivating synthetic data augmentation to improve existing datasets. However, existing evaluation metrics for synthetic data typically calculate latent feature similarity, which is difficult to interpret and does not always correlate with the contribution to downstream tasks. We propose a vision-language grounded framework for interpretable synthetic data augmentation and evaluation in remote sensing. Our approach combines generative models, semantic segmentation and image captioning with vision and language models. Based on this framework, we introduce ARAS400k: A large-scale Remote sensing dataset Augmented with Synthetic data for segmentation and captioning, containing 100k real images and 300k synthetic images, each paired with segmentation maps and descriptions. ARAS400k enables the automated evaluation of synthetic data by analyzing semantic composition, minimizing caption redundancy, and verifying cross-modal consistency between visual structures and language descriptions. Experimental results indicate that while models trained exclusively on synthetic data reach competitive performance levels, those trained with augmented data (a combination of real and synthetic images) consistently outperform real-data baselines. Consequently, this work establishes a scalable benchmark for remote sensing tasks, specifically in semantic segmentation and image captioning. The dataset is available at zenodo.org/records/18890661 and the code base at github.com/caglarmert/ARAS400k.

Fatih Cagatay Akyon, Erdem Akagunduz, Sinan Onur Altinuc et al.

Drone detection has become an essential task in object detection as drone costs have decreased and drone technology has improved. It is, however, difficult to detect distant drones when there is weak contrast, long range, and low visibility. In this work, we propose several sequence classification architectures to reduce the detected false-positive ratio of drone tracks. Moreover, we propose a new drone vs. bird sequence classification dataset to train and evaluate the proposed architectures. 3D CNN, LSTM, and Transformer based sequence classification architectures have been trained on the proposed dataset to show the effectiveness of the proposed idea. As experiments show, using sequence information, bird classification and overall F1 scores can be increased by up to 73% and 35%, respectively. Among all sequence classification models, R(2+1)D-based fully convolutional model yields the best transfer learning and fine-tuning results.

M. Esat Kalfaoglu, Halil Ibrahim Ozturk, Ozsel Kilinc et al.

Recently, the centerline has become a popular representation of lanes due to its advantages in solving the road topology problem. To enhance centerline prediction, we have developed a new approach called TopoMask. Unlike previous methods that rely on keypoints or parametric methods, TopoMask utilizes an instance-mask-based formulation coupled with a masked-attention-based transformer architecture. We introduce a quad-direction label representation to enrich the mask instances with flow information and design a corresponding post-processing technique for mask-to-centerline conversion. Additionally, we demonstrate that the instance-mask formulation provides complementary information to parametric Bezier regressions, and fusing both outputs leads to improved detection and topology performance. Moreover, we analyze the shortcomings of the pillar assumption in the Lift Splat technique and adapt a multi-height bin configuration. Experimental results show that TopoMask achieves state-of-the-art performance in the OpenLane-V2 dataset, increasing from 44.1 to 49.4 for Subset-A and 44.7 to 51.8 for Subset-B in the V1.1 OLS baseline.

M. Esat Kalfaoglu, Halil Ibrahim Ozturk, Ozsel Kilinc et al.

Driving scene understanding task involves detecting static elements such as lanes, traffic signs, and traffic lights, and their relationships with each other. To facilitate the development of comprehensive scene understanding solutions using multiple camera views, a new dataset called Road Genome (OpenLane-V2) has been released. This dataset allows for the exploration of complex road connections and situations where lane markings may be absent. Instead of using traditional lane markings, the lanes in this dataset are represented by centerlines, which offer a more suitable representation of lanes and their connections. In this study, we have introduced a new approach called TopoMask for predicting centerlines in road topology. Unlike existing approaches in the literature that rely on keypoints or parametric methods, TopoMask utilizes an instance-mask based formulation with a transformer-based architecture and, in order to enrich the mask instances with flow information, a direction label representation is proposed. TopoMask have ranked 4th in the OpenLane-V2 Score (OLS) and ranked 2nd in the F1 score of centerline prediction in OpenLane Topology Challenge 2023. In comparison to the current state-of-the-art method, TopoNet, the proposed method has achieved similar performance in Frechet-based lane detection and outperformed TopoNet in Chamfer-based lane detection without utilizing its scene graph neural network.

Ümit Mert Çağlar, Alperen İnci, Oğuz Hanoğlu et al.

Endoscopic imaging is commonly used to diagnose Ulcerative Colitis (UC) and classify its severity. It has been shown that deep learning based methods are effective in automated analysis of these images and can potentially be used to aid medical doctors. Unleashing the full potential of these methods depends on the availability of large amount of labeled images; however, obtaining and labeling these images are quite challenging. In this paper, we propose a active learning based generative augmentation method. The method involves generating a large number of synthetic samples by training using a small dataset consisting of real endoscopic images. The resulting data pool is narrowed down by using active learning methods to select the most informative samples, which are then used to train a classifier. We demonstrate the effectiveness of our method through experiments on a publicly available endoscopic image dataset. The results show that using synthesized samples in conjunction with active learning leads to improved classification performance compared to using only the original labeled examples and the baseline classification performance of 68.1% increases to 74.5% in terms of Quadratic Weighted Kappa (QWK) Score. Another observation is that, attaining equivalent performance using only real data necessitated three times higher number of images.

Fatih Cagatay Akyon, Alptekin Temizel

Content moderation systems classify images as safe or unsafe but lack spatial grounding and interpretability: they cannot explain what sensitive behavior was detected, who is involved, or where it occurs. We introduce the Sensitive Benchmark (SenBen), the first large-scale scene graph benchmark for sensitive content, comprising 13,999 frames from 157 movies annotated with Visual Genome-style scene graphs (25 object classes, 28 attributes including affective states such as pain, fear, aggression, and distress, 14 predicates) and 16 sensitivity tags across 5 categories. We distill a frontier VLM into a compact 241M student model using a multi-task recipe that addresses vocabulary imbalance in autoregressive scene graph generation through suffix-based object identity, Vocabulary-Aware Recall (VAR) Loss, and a decoupled Query2Label tag head with asymmetric loss, yielding a +6.4 percentage point improvement in SenBen Recall over standard cross-entropy training. On grounded scene graph metrics, our student model outperforms all evaluated VLMs except Gemini models and all commercial safety APIs, while achieving the highest object detection and captioning scores across all models, at $7.6\times$ faster inference and $16\times$ less GPU memory.

Qurat Ul Ain, Alptekin Temizel, Soyiba Jawed

Attention Deficit Hyperactivity Disorder (ADHD) is a prevalent neurodevelopmental disorder whose neuroimaging-based diagnosis remains challenging due to complex time-varying disruptions in brain connectivity. Functional MRI (fMRI) provides a powerful non-invasive modality for identifying functional alterations. Existing deep learning (DL) studies employ diverse neuroimaging features; however, static functional connectivity remains widely used, whereas dynamic connectivity modeling is comparatively underexplored. Moreover, many DL models lack interpretability. In this work, we propose D-GATNet, an interpretable temporal graph-based framework for automated ADHD classification using dynamic functional connectivity (dFC). Sliding-window Pearson correlation constructs sequences of functional brain graphs with regions of interest as nodes and connectivity strengths as edges. Spatial dependencies are learned via a multi-layer Graph Attention Network, while temporal dynamics are modeled using 1D convolution followed by temporal attention. Interpretability is achieved through graph attention weights revealing dominant ROI interactions, ROI importance scores identifying influential regions, and temporal attention emphasizing informative connectivity segments. Experiments on the Peking University site of the ADHD-200 dataset using stratified 10-fold cross-validation with a 5-seed ensemble achieved 85.18% +_5.64 balanced accuracy and 0.881 AUC, outperforming state-of-the-art methods. Attention analysis reveals cerebellar and default mode network disruptions, indicating potential neuroimaging biomarkers.

Qurat Ul Ain, Alptekin Temizel, Soyiba Jawed

Attention Deficit Hyperactivity Disorder (ADHD) is a highly prevalent neurodevelopmental condition; however, its neurobiological diagnosis remains challenging due to the lack of reliable imaging-based biomarkers, particularly anatomical markers. Structural MRI (sMRI) provides a non-invasive modality for investigating brain alterations associated with ADHD; nevertheless, most deep learning approaches function as black-box systems, limiting clinical trust and interpretability. In this work, we propose DuSCN-FusionNet, an interpretable sMRI-based framework for ADHD classification that leverages dual-channel Structural Covariance Networks (SCNs) to capture inter-regional morphological relationships. ROI-wise mean intensity and intra-regional variability descriptors are used to construct intensity-based and heterogeneity-based SCNs, which are processed through an SCN-CNN encoder. In parallel, auxiliary ROI-wise variability features and global statistical descriptors are integrated via late-stage fusion to enhance performance. The model is evaluated using stratified 10-fold cross-validation with a 5-seed ensemble strategy, achieving a mean balanced accuracy of 80.59% and an AUC of 0.778 on the Peking University site of the ADHD-200 dataset. DuSCN-FusionNet further achieves precision, recall, and F1-scores of 81.66%, 80.59%, and 80.27%, respectively. Moreover, Grad-CAM is adapted to the SCN domain to derive ROI-level importance scores, enabling the identification of structurally relevant brain regions as potential biomarkers.

Muhammet Esat Kalfaoglu, Halil Ibrahim Ozturk, Ozsel Kilinc et al.

Mask-based paradigms for road topology understanding, such as TopoMaskV2, offer a complementary alternative to query-based methods by generating centerlines via a dense rasterized intermediate representation. However, prior work was limited to 2D predictions and suffered from severe discretization artifacts, necessitating fusion with parametric heads. We introduce TopoMaskV3, which advances this pipeline into a robust, standalone 3D predictor via two novel dense prediction heads: a dense offset field for sub-grid discretization correction within the existing BEV resolution, and a dense height map for direct 3D estimation. Beyond the architecture, we are the first to address geographic data leakage in road topology evaluation by introducing (1) geographically distinct splits to prevent memorization and ensure fair generalization, and (2) a long-range (+/-100 m) benchmark. TopoMaskV3 achieves state-of-the-art 28.5 OLS on this geographically disjoint benchmark, surpassing all prior methods. Our analysis shows that the mask representation is more robust to geographic overfitting than Bezier, while LiDAR fusion is most beneficial at long range and exhibits larger relative gains on the overlapping original split, suggesting overlap-induced memorization effects.

Umut Dundar, Alptekin Temizel

Synthesizing longitudinal medical images at controllable disease stages while preserving patient-specific anatomy is hindered by the entanglement of pathological textures and structural features. We address this challenge for ulcerative colitis (UC) endoscopy, where severity follows a continuous ordinal progression along the Mayo Endoscopic Score (MES). Our framework, Disentangled Anatomy-Disease Diffusion (DADD), conditions a latent diffusion model on two complementary embeddings: a pretrained image encoder for patient anatomy and a separately trained ordinal embedder for cumulative disease severity. Since image embeddings inevitably capture disease information, we introduce a Feature Purifier, a cross-attention-based erasure mechanism that identifies and suppresses disease-correlated channels, yielding purified anatomical representations. These cleaned anatomy tokens and target disease tokens are injected into the denoising network via a Triple-Pathway Cross-Attention mechanism with resolution-dependent routing gates. This architecture leverages the U-Net hierarchy, in which different network depths encode global structure versus fine-grained pathological texture. Furthermore, we introduce Delta Steering, a training-free directional signal derived from the ordinal embeddings that enables explicit, single-pass control over disease transitions at inference without requiring additional forward passes. Validated on the LIMUC dataset, our approach produces high-fidelity images across all severity levels and effectively rebalances skewed class distributions, enhancing performance for downstream classification tasks. The dataset is available at zenodo.org/records/5827695 and the code base at github.com/umutdundar99/progressive-stable-diffusion

Fatih Cagatay Akyon, Alptekin Temizel

This paper presents a comparative analysis of existing nudity classification techniques for classifying images based on the presence of nudity, with a focus on their application in content moderation. The evaluation focuses on CNN-based models, vision transformer, and popular open-source safety checkers from Stable Diffusion and Large-scale Artificial Intelligence Open Network (LAION). The study identifies the limitations of current evaluation datasets and highlights the need for more diverse and challenging datasets. The paper discusses the potential implications of these findings for developing more accurate and effective image classification systems on online platforms. Overall, the study emphasizes the importance of continually improving image classification models to ensure the safety and well-being of platform users. The project page, including the demonstrations and results is publicly available at https://github.com/fcakyon/content-moderation-deep-learning.

Fatih Cagatay Akyon, Sinan Onur Altinuc, Alptekin Temizel

Detection of small objects and objects far away in the scene is a major challenge in surveillance applications. Such objects are represented by small number of pixels in the image and lack sufficient details, making them difficult to detect using conventional detectors. In this work, an open-source framework called Slicing Aided Hyper Inference (SAHI) is proposed that provides a generic slicing aided inference and fine-tuning pipeline for small object detection. The proposed technique is generic in the sense that it can be applied on top of any available object detector without any fine-tuning. Experimental evaluations, using object detection baselines on the Visdrone and xView aerial object detection datasets show that the proposed inference method can increase object detection AP by 6.8%, 5.1% and 5.3% for FCOS, VFNet and TOOD detectors, respectively. Moreover, the detection accuracy can be further increased with a slicing aided fine-tuning, resulting in a cumulative increase of 12.7%, 13.4% and 14.5% AP in the same order. Proposed technique has been integrated with Detectron2, MMDetection and YOLOv5 models and it is publicly available at https://github.com/obss/sahi.git .

Fatih Cagatay Akyon, Devrim Cavusoglu, Cemil Cengiz et al.

While exam-style questions are a fundamental educational tool serving a variety of purposes, manual construction of questions is a complex process that requires training, experience and resources. Automatic question generation (QG) techniques can be utilized to satisfy the need for a continuous supply of new questions by streamlining their generation. However, compared to automatic question answering (QA), QG is a more challenging task. In this work, we fine-tune a multilingual T5 (mT5) transformer in a multi-task setting for QA, QG and answer extraction tasks using Turkish QA datasets. To the best of our knowledge, this is the first academic work that performs automated text-to-text question generation from Turkish texts. Experimental evaluations show that the proposed multi-task setting achieves state-of-the-art Turkish question answering and question generation performance on TQuADv1, TQuADv2 datasets and XQuAD Turkish split. The source code and the pre-trained models are available at https://github.com/obss/turkish-question-generation.

Mete Can Kaya, Alperen İnci, Alptekin Temizel

Binary convolutional networks have lower computational load and lower memory foot-print compared to their full-precision counterparts. So, they are a feasible alternative for the deployment of computer vision applications on limited capacity embedded devices. Once trained on less resource-constrained computational environments, they can be deployed for real-time inference on such devices. In this study, we propose an implementation of binary convolutional network inference on GPU by focusing on optimization of XNOR convolution. Experimental results show that using GPU can provide a speed-up of up to $42.61\times$ with a kernel size of $3\times3$. The implementation is publicly available at https://github.com/metcan/Binary-Convolutional-Neural-Network-Inference-on-GPU

Kaan Furkan Altınok, Afşin Peker, Alptekin Temizel

Triple DES (3DES) is a standard fundamental encryption algorithm, used in several electronic payment applications and web browsers. In this paper, we propose a parallel implementation of 3DES on GPU. Since 3DES encrypts data with 64-bit blocks, our approach considers each 64-bit block a kernel block and assign a separate thread to process each bit. Algorithm's permutation operations, XOR operations, and S-box operations are done in parallel within these kernel blocks. The implementation benefits from the use of constant and shared memory types to optimize memory access. The results show an average 10.70x speed-up against the baseline multi-threaded CPU implementation. The implementation is publicly available at https://github.com/kaanfurkan35/3DES_GPU

Kadir Cenk Alpay, Kadir Berkay Aydemir, Alptekin Temizel

High Dynamic Range (HDR) images are generated using multiple exposures of a scene. When a hand-held camera is used to capture a static scene, these images need to be aligned by globally shifting each image in both dimensions. For a fast and robust alignment, the shift amount is commonly calculated using Median Threshold Bitmaps (MTB) and creating an image pyramid. In this study, we optimize these computations using a parallel processing approach utilizing GPU. Experimental evaluation shows that the proposed implementation achieves a speed-up of up to 6.24 times over the baseline multi-threaded CPU implementation on the alignment of one image pair. The source code is available at https://github.com/kadircenk/WardMTBCuda

Gorkem Polat, Ümit Mert Çağlar, Alptekin Temizel

Assessing disease severity with ordinal classes, where each class reflects increasing severity levels, benefits from loss functions designed for this ordinal structure. Traditional categorical loss functions, like Cross-Entropy (CE), often perform suboptimally in these scenarios. To address this, we propose a novel loss function, Class Distance Weighted Cross-Entropy (CDW-CE), which penalizes misclassifications more severely when the predicted and actual classes are farther apart. We evaluated CDW-CE using various deep architectures, comparing its performance against several categorical and ordinal loss functions. To assess the quality of latent representations, we used t-distributed stochastic neighbor embedding (t-SNE) and uniform manifold approximation and projection (UMAP) visualizations, quantified the clustering quality using the Silhouette Score, and compared Class Activation Maps (CAM) generated by models trained with CDW-CE and CE loss. Feedback from domain experts was incorporated to evaluate how well model attention aligns with expert opinion. Our results show that CDW-CE consistently improves performance in ordinal image classification tasks. It achieves higher Silhouette Scores, indicating better class discrimination capability, and its CAM visualizations show a stronger focus on clinically significant regions, as validated by domain experts. Receiver operator characteristics (ROC) curves and the area under the curve (AUC) scores highlight that CDW-CE outperforms other loss functions, including prominent ordinal loss functions from the literature.

Muhammet Esat Kalfaoglu, Halil Ibrahim Ozturk, Ozsel Kilinc et al.

Understanding road topology is crucial for autonomous driving. This paper introduces TopoBDA (Topology with Bezier Deformable Attention), a novel approach that enhances road topology comprehension by leveraging Bezier Deformable Attention (BDA). TopoBDA processes multi-camera 360-degree imagery to generate Bird's Eye View (BEV) features, which are refined through a transformer decoder employing BDA. BDA utilizes Bezier control points to drive the deformable attention mechanism, improving the detection and representation of elongated and thin polyline structures, such as lane centerlines. Additionally, TopoBDA integrates two auxiliary components: an instance mask formulation loss and a one-to-many set prediction loss strategy, to further refine centerline detection and enhance road topology understanding. Experimental evaluations on the OpenLane-V2 dataset demonstrate that TopoBDA outperforms existing methods, achieving state-of-the-art results in centerline detection and topology reasoning. TopoBDA also achieves the best results on the OpenLane-V1 dataset in 3D lane detection. Further experiments on integrating multi-modal data -- such as LiDAR, radar, and SDMap -- show that multimodal inputs can further enhance performance in road topology understanding.

Ant Duru, Alptekin Temizel

Data augmentation is a critical component of deep learning pipelines, enhancing model generalization by increasing dataset diversity. Traditional augmentation strategies rely on manually designed transformations, stochastic sampling, or automated search-based approaches. Although automated methods improve performance, they often require extensive computational resources and are specifically designed for certain datasets. In this work, we propose a Large Language Model (LLM)-guided augmentation optimization strategy that refines augmentation policies based on model performance feedback. We propose two approaches: (1) LLM-Guided Augmentation Policy Optimization, where augmentation policies selected by LLM are refined iteratively across training cycles, and (2) Adaptive LLM-Guided Augmentation Policy Optimization, which adjusts policies at each iteration based on performance metrics. This in-training approach eliminates the need for full model retraining before getting LLM feedback, reducing computational costs while increasing performance. Our methodology employs an LLM to dynamically select augmentation transformations based on dataset characteristics, model architecture, and prior training performance. Leveraging LLMs' contextual knowledge, especially in domain-specific tasks like medical imaging, our method selects augmentations tailored to dataset characteristics and model performance. Experiments across domain-specific image classification datasets show consistent accuracy improvements over traditional methods.

Alper Bahcekapili, Duygu Arslan, Umut Ozdemir et al.

Colorectal cancer (CRC) is the third most diagnosed cancer and the second leading cause of cancer-related death worldwide. Accurate histopathological grading of CRC is essential for prognosis and treatment planning but remains a subjective process prone to observer variability and limited by global shortages of trained pathologists. To promote automated and standardized solutions, we organized the ICIP Grand Challenge on Colorectal Cancer Tumor Grading and Segmentation using the publicly available METU CCTGS dataset. The dataset comprises 103 whole-slide images with expert pixel-level annotations for five tissue classes. Participants submitted segmentation masks via Codalab, evaluated using metrics such as macro F-score and mIoU. Among 39 participating teams, six outperformed the Swin Transformer baseline (62.92 F-score). This paper presents an overview of the challenge, dataset, and the top-performing methods

Ece Isik-Polat, Gorkem Polat, Altan Kocyigit et al.

Availability of large, diverse, and multi-national datasets is crucial for the development of effective and clinically applicable AI systems in the medical imaging domain. However, forming a global model by bringing these datasets together at a central location, comes along with various data privacy and ownership problems. To alleviate these problems, several recent studies focus on the federated learning paradigm, a distributed learning approach for decentralized data. Federated learning leverages all the available data without any need for sharing collaborators' data with each other or collecting them on a central server. Studies show that federated learning can provide competitive performance with conventional central training, while having a good generalization capability. In this work, we have investigated several federated learning approaches on the brain tumor segmentation problem. We explore different strategies for faster convergence and better performance which can also work on strong Non-IID cases.

Gorkem Polat, Ilkay Ergenc, Haluk Tarik Kani et al.

In scoring systems used to measure the endoscopic activity of ulcerative colitis, such as Mayo endoscopic score or Ulcerative Colitis Endoscopic Index Severity, levels increase with severity of the disease activity. Such relative ranking among the scores makes it an ordinal regression problem. On the other hand, most studies use categorical cross-entropy loss function to train deep learning models, which is not optimal for the ordinal regression problem. In this study, we propose a novel loss function, class distance weighted cross-entropy (CDW-CE), that respects the order of the classes and takes the distance of the classes into account in calculation of the cost. Experimental evaluations show that models trained with CDW-CE outperform the models trained with conventional categorical cross-entropy and other commonly used loss functions which are designed for the ordinal regression problems. In addition, the class activation maps of models trained with CDW-CE loss are more class-discriminative and they are found to be more reasonable by the domain experts.

Ayberk Aydin, Deniz Sen, Berat Tuna Karli et al.

Deep Neural Networks have been shown to be vulnerable to various kinds of adversarial perturbations. In addition to widely studied additive noise based perturbations, adversarial examples can also be created by applying a per pixel spatial drift on input images. While spatial transformation based adversarial examples look more natural to human observers due to absence of additive noise, they still possess visible distortions caused by spatial transformations. Since the human vision is more sensitive to the distortions in the luminance compared to those in chrominance channels, which is one of the main ideas behind the lossy visual multimedia compression standards, we propose a spatial transformation based perturbation method to create adversarial examples by only modifying the color components of an input image. While having competitive fooling rates on CIFAR-10 and NIPS2017 Adversarial Learning Challenge datasets, examples created with the proposed method have better scores with regards to various perceptual quality metrics. Human visual perception studies validate that the examples are more natural looking and often indistinguishable from their original counterparts.

Hilmi Kumdakcı, Cihan Öngün, Alptekin Temizel

Scarcity of training data is one of the prominent problems for deep networks which require large amounts data. Data augmentation is a widely used method to increase the number of training samples and their variations. In this paper, we focus on improving vehicle detection performance in aerial images and propose a generative augmentation method which does not need any extra supervision than the bounding box annotations of the vehicle objects in the training dataset. The proposed method increases the performance of vehicle detection by allowing detectors to be trained with higher number of instances, especially when there are limited number of training instances. The proposed method is generic in the sense that it can be integrated with different generators. The experiments show that the method increases the Average Precision by up to 25.2% and 25.7% when integrated with Pluralistic and DeepFill respectively.

Sharib Ali, Mariia Dmitrieva, Noha Ghatwary et al.

The Endoscopy Computer Vision Challenge (EndoCV) is a crowd-sourcing initiative to address eminent problems in developing reliable computer aided detection and diagnosis endoscopy systems and suggest a pathway for clinical translation of technologies. Whilst endoscopy is a widely used diagnostic and treatment tool for hollow-organs, there are several core challenges often faced by endoscopists, mainly: 1) presence of multi-class artefacts that hinder their visual interpretation, and 2) difficulty in identifying subtle precancerous precursors and cancer abnormalities. Artefacts often affect the robustness of deep learning methods applied to the gastrointestinal tract organs as they can be confused with tissue of interest. EndoCV2020 challenges are designed to address research questions in these remits. In this paper, we present a summary of methods developed by the top 17 teams and provide an objective comparison of state-of-the-art methods and methods designed by the participants for two sub-challenges: i) artefact detection and segmentation (EAD2020), and ii) disease detection and segmentation (EDD2020). Multi-center, multi-organ, multi-class, and multi-modal clinical endoscopy datasets were compiled for both EAD2020 and EDD2020 sub-challenges. The out-of-sample generalization ability of detection algorithms was also evaluated. Whilst most teams focused on accuracy improvements, only a few methods hold credibility for clinical usability. The best performing teams provided solutions to tackle class imbalance, and variabilities in size, origin, modality and occurrences by exploring data augmentation, data fusion, and optimal class thresholding techniques.

Cihan Öngün, Alptekin Temizel

In this paper, we focus on latent modification and generation of 3D point cloud object models with respect to their semantic parts. Different to the existing methods which use separate networks for part generation and assembly, we propose a single end-to-end Autoencoder model that can handle generation and modification of both semantic parts, and global shapes. The proposed method supports part exchange between 3D point cloud models and composition by different parts to form new models by directly editing latent representations. This holistic approach does not need part-based training to learn part representations and does not introduce any extra loss besides the standard reconstruction loss. The experiments demonstrate the robustness of the proposed method with different object categories and varying number of points. The method can generate new models by integration of generative models such as GANs and VAEs and can work with unannotated point clouds by integration of a segmentation module.

Atıl İlerialkan, Alptekin Temizel, Hüseyin Hacıhabiboğlu

Acoustic features extracted from speech are widely used in problems such as biometric speaker identification and first-person activity detection. However, the use of speech for such purposes raises privacy issues as the content is accessible to the processing party. In this work, we propose a method for speaker and posture classification using intraspeech breathing sounds. Instantaneous magnitude features are extracted using the Hilbert-Huang transform (HHT) and fed into a CNN-GRU network for classification of recordings from the open intraspeech breathing sound dataset, BreathBase, that we collected for this study. Using intraspeech breathing sounds, 87% speaker classification, and 98% posture classification accuracy were obtained.

Bilgin Aksoy, Alptekin Temizel

Adversarial images are samples that are intentionally modified to deceive machine learning systems. They are widely used in applications such as CAPTHAs to help distinguish legitimate human users from bots. However, the noise introduced during the adversarial image generation process degrades the perceptual quality and introduces artificial colours; making it also difficult for humans to classify images and recognise objects. In this letter, we propose a method to enhance the perceptual quality of these adversarial images. The proposed method is attack type agnostic and could be used in association with the existing attacks in the literature. Our experiments show that the generated adversarial images have lower Euclidean distance values while maintaining the same adversarial attack performance. Distances are reduced by 5.88% to 41.27% with an average reduction of 22% over the different attack and network types.

Cihan Öngün, Alptekin Temizel

Generative Adversarial Networks (GANs) are shown to be successful at generating new and realistic samples including 3D object models. Conditional GAN, a variant of GANs, allows generating samples in given conditions. However, objects generated for each condition are different and it does not allow generation of the same object in different conditions. In this paper, we first adapt conditional GAN, which is originally designed for 2D image generation, to the problem of generating 3D models in different rotations. We then propose a new approach to guide the network to generate the same 3D sample in different and controllable rotation angles (sample pairs). Unlike previous studies, the proposed method does not require modification of the standard conditional GAN architecture and it can be integrated into the training step of any conditional GAN. Experimental results and visual comparison of 3D models show that the proposed method is successful at generating model pairs in different conditions.

Mehmet Ali Arabacı, Fatih Özkan, Elif Surer et al.

Egocentric activity recognition in first-person videos has an increasing importance with a variety of applications such as lifelogging, summarization, assisted-living and activity tracking. Existing methods for this task are based on interpretation of various sensor information using pre-determined weights for each feature. In this work, we propose a new framework for egocentric activity recognition problem based on combining audio-visual features with multi-kernel learning (MKL) and multi-kernel boosting (MKBoost). For that purpose, firstly grid optical-flow, virtual-inertia feature, log-covariance, cuboid are extracted from the video. The audio signal is characterized using a "supervector", obtained based on Gaussian mixture modelling of frame-level features, followed by a maximum a-posteriori adaptation. Then, the extracted multi-modal features are adaptively fused by MKL classifiers in which both the feature and kernel selection/weighing and recognition tasks are performed together. The proposed framework was evaluated on a number of egocentric datasets. The results showed that using multi-modal features with MKL outperforms the existing methods.

Ayse Elvan Aydemir, Alptekin Temizel, Tugba Taskaya Temizel

Adversarial examples are known to have a negative effect on the performance of classifiers which have otherwise good performance on undisturbed images. These examples are generated by adding non-random noise to the testing samples in order to make classifier misclassify the given data. Adversarial attacks use these intentionally generated examples and they pose a security risk to the machine learning based systems. To be immune to such attacks, it is desirable to have a pre-processing mechanism which removes these effects causing misclassification while keeping the content of the image. JPEG and JPEG2000 are well-known image compression techniques which suppress the high-frequency content taking the human visual system into account. JPEG has been also shown to be an effective method for reducing adversarial noise. In this paper, we propose applying JPEG2000 compression as an alternative and systematically compare the classification performance of adversarial images compressed using JPEG and JPEG2000 at different target PSNR values and maximum compression levels. Our experiments show that JPEG2000 is more effective in reducing adversarial noise as it allows higher compression rates with less distortion and it does not introduce blocking artifacts.

Fatih Ozkan, Mehmet Ali Arabaci, Elif Surer et al.

Activity recognition from first-person (ego-centric) videos has recently gained attention due to the increasing ubiquity of the wearable cameras. There has been a surge of efforts adapting existing feature descriptors and designing new descriptors for the first-person videos. An effective activity recognition system requires selection and use of complementary features and appropriate kernels for each feature. In this study, we propose a data-driven framework for first-person activity recognition which effectively selects and combines features and their respective kernels during the training. Our experimental results show that use of Multiple Kernel Learning (MKL) and Boosted MKL in first-person activity recognition problem exhibits improved results in comparison to the state-of-the-art. In addition, these techniques enable the expansion of the framework with new features in an efficient and convenient way.