no code implementations • 15 Apr 2024 • Önder Tuzcuoğlu, Aybora Köksal, Buğra Sofu, Sinan Kalkan, A. Aydin Alatan
We introduce, XoFTR, a cross-modal cross-view method for local feature matching between thermal infrared (TIR) and visible images.
no code implementations • 4 Mar 2024 • Bedrettin Cetinkaya, Sinan Kalkan, Emre Akbas
Detecting edges in images suffers from the problems of (P1) heavy imbalance between positive and negative classes as well as (P2) label uncertainty owing to disagreement between different annotators.
no code implementations • 28 Dec 2023 • Barış Can Çam, Kemal Öksüz, Fehmi Kahraman, Zeynep Sonat Baltaci, Sinan Kalkan, Emre Akbaş
This paper introduces Generalized Mask-aware Intersection-over-Union (GmaIoU) as a new measure for positive-negative assignment of anchor boxes during training of instance segmentation methods.
no code implementations • 18 Dec 2023 • Selim Kuzucu, Jiaee Cheong, Hatice Gunes, Sinan Kalkan
Unfair predictions of machine learning (ML) models impede their broad acceptance in real-world settings.
1 code implementation • 3 Jan 2023 • Fehmi Kahraman, Kemal Oksuz, Sinan Kalkan, Emre Akbas
(ii) Motivated by our observations, e. g., that NMS-free detectors can also benefit from correlation, we propose Correlation Loss, a novel plug-in loss function that improves the performance of various object detectors by directly optimizing correlation coefficients: E. g., Correlation Loss on Sparse R-CNN, an NMS-free method, yields 1. 6 AP gain on COCO and 1. 8 AP gain on Cityscapes dataset.
1 code implementation • 15 Sep 2022 • Özgür Aslan, Burak Bolat, Batuhan Bal, Tuğba Tümer, Erol Şahin, Sinan Kalkan
The rise of simulation environments has enabled learning-based approaches for assembly planning, which is otherwise a labor-intensive and daunting task.
no code implementations • 6 Sep 2022 • Feyza Yavuz, Sinan Kalkan
Logo retrieval is a challenging problem since the definition of similarity is more subjective compared to image retrieval tasks and the set of known similarities is very scarce.
no code implementations • 13 Apr 2022 • Bedrettin Cetinkaya, Sinan Kalkan, Emre Akbas
Ground-truth depth, when combined with color data, helps improve object detection accuracy over baseline models that only use color.
1 code implementation • 19 Oct 2021 • Kemal Oksuz, Baris Can Cam, Fehmi Kahraman, Zeynep Sonat Baltaci, Sinan Kalkan, Emre Akbas
We present the effectiveness of maIoU on a state-of-the-art (SOTA) assigner, ATSS, by replacing IoU operation by our maIoU and training YOLACT, a SOTA real-time instance segmentation method.
Ranked #9 on Real-time Instance Segmentation on MSCOCO
3 code implementations • ICCV 2021 • Kemal Oksuz, Baris Can Cam, Emre Akbas, Sinan Kalkan
RS Loss supervises the classifier, a sub-network of these methods, to rank each positive above all negatives as well as to sort positives among themselves with respect to (wrt.)
2 code implementations • 21 Nov 2020 • Kemal Oksuz, Baris Can Cam, Sinan Kalkan, Emre Akbas
Despite being widely used as a performance measure for visual detection tasks, Average Precision (AP) is limited in (i) reflecting localisation quality, (ii) interpretability and (iii) robustness to the design choices regarding its computation, and its applicability to outputs without confidence scores.
no code implementations • 17 Nov 2020 • Nikhil Churamani, Sinan Kalkan, Hatice Gunes
In real-world interactions, however, facial expressions are usually more subtle and evolve in a temporal manner requiring AU detection models to learn spatial as well as temporal information.
no code implementations • 13 Nov 2020 • Faisal Alamri, Sinan Kalkan, Nicolas Pugeault
Deep neural network approaches have demonstrated high performance in object recognition (CNN) and detection (Faster-RCNN) tasks, but experiments have shown that such architectures are vulnerable to adversarial attacks (FFF, UAP): low amplitude perturbations, barely perceptible by the human eye, can lead to a drastic reduction in labeling performance.
3 code implementations • NeurIPS 2020 • Kemal Oksuz, Baris Can Cam, Emre Akbas, Sinan Kalkan
We propose average Localisation-Recall-Precision (aLRP), a unified, bounded, balanced and ranking-based loss function for both classification and localisation tasks in object detection.
Ranked #75 on Object Detection on COCO test-dev
1 code implementation • 3 Aug 2020 • M. Esat Kalfaoglu, Sinan Kalkan, A. Aydin Alatan
In this work, we combine 3D convolution with late temporal modeling for action recognition.
Ranked #1 on Action Recognition on UCF 101
no code implementations • 20 Jul 2020 • Tian Xu, Jennifer White, Sinan Kalkan, Hatice Gunes
Recognition of expressions of emotions and affect from facial images is a well-studied research problem in the fields of affective computing and computer vision with a large number of datasets available containing facial images and corresponding expression labels.
1 code implementation • 25 Oct 2019 • Fatih Can Kurnaz, Burak Hocaoğlu, Mert Kaan Yılmaz, İdil Sülo, Sinan Kalkan
Robots collaborating with humans in realistic environments will need to be able to detect the tools that can be used and manipulated.
1 code implementation • 21 Sep 2019 • Kemal Oksuz, Baris Can Cam, Emre Akbas, Sinan Kalkan
Using our generator as an analysis tool, we show that (i) IoU imbalance has an adverse effect on performance, (ii) hard positive example mining improves the performance only for certain input IoU distributions, and (iii) the imbalance among the foreground classes has an adverse effect on performance and that it can be alleviated at the batch level.
Ranked #194 on Object Detection on COCO minival
1 code implementation • 31 Aug 2019 • Kemal Oksuz, Baris Can Cam, Sinan Kalkan, Emre Akbas
In this paper, we present a comprehensive review of the imbalance problems in object detection.
1 code implementation • 3 Aug 2019 • Hazan Anayurt, Sezai Artun Ozyegin, Ulfet Cetin, Utku Aktas, Sinan Kalkan
Especially in ambiguous settings, humans prefer expressions (called relational referring expressions) that describe an object with respect to a distinguishing, unique object.
no code implementations • 15 Apr 2019 • Fethiye Irmak Doğan, Sinan Kalkan, Iolanda Leite
Referring to objects in a natural and unambiguous manner is crucial for effective human-robot interaction.
3 code implementations • ECCV 2018 • Kemal Oksuz, Baris Can Cam, Emre Akbas, Sinan Kalkan
Moreover, we present LRP results of a simple online video object detector which uses a SOTA still image object detector and show that the class-specific optimized thresholds increase the accuracy against the common approach of using a general threshold for all classes.
1 code implementation • 2 Jul 2018 • Ilker Bozcan, Sinan Kalkan
For this end, we introduce a hybrid version of BMs where relations and affordances are introduced with shared, tri-way connections into the model.
no code implementations • 16 Oct 2017 • İlker Bozcan, Yağmur Oymak, İdil Zeynep Alemdar, Sinan Kalkan
Scene models allow robots to reason about what is in the scene, what else should be in it, and what should not be in it.
no code implementations • 13 Oct 2017 • Fethiye Irmak Doğan, İlker Bozcan, Mehmet Çelik, Sinan Kalkan
There have been several attempts at modeling context in robots.
no code implementations • 13 Oct 2017 • Fethiye Irmak Doğan, Hande Çelikkanat, Sinan Kalkan
Context is an essential capability for robots that are to be as adaptive as possible in challenging environments.
no code implementations • 18 Jun 2017 • Cemal Aker, Sinan Kalkan
Drone detection is the problem of finding the smallest rectangle that encloses the drone(s) in a video sequence.
2 code implementations • 20 Jan 2017 • Osman Tursun, Cemal Aker, Sinan Kalkan
In this paper, we provide a large-scale dataset with benchmark queries with which different TR approaches can be evaluated systematically.