1 code implementation • 4 Aug 2014 • Emre Akbas, Miguel P. Eckstein
Similar to the human visual system, the FOD has higher resolution at the fovea and lower resolution at the visual periphery.
1 code implementation • 9 Apr 2017 • Sadegh Eskandari, Emre Akbas
In this paper, we present a new feature selection method that is suitable for both unsupervised and supervised problems.
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.
4 code implementations • ECCV 2018 • Muhammed Kocabas, Salih Karagoz, Emre Akbas
In this paper, we present MultiPoseNet, a novel bottom-up multi-person pose estimation architecture that combines a multi-task model with a novel assignment method.
Ranked #8 on Multi-Person Pose Estimation on MS COCO
1 code implementation • CVPR 2019 • Muhammed Kocabas, Salih Karagoz, Emre Akbas
Training accurate 3D human pose estimators requires large amount of 3D ground-truth data which is costly to collect.
Ranked #1 on Weakly-supervised 3D Human Pose Estimation on Human3.6M (Number of Frames Per View metric)
Self-Supervised Learning Weakly-supervised 3D Human Pose Estimation
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 • 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
4 code implementations • 13 Feb 2020 • Samet Hicsonmez, Nermin Samet, Emre Akbas, Pinar Duygulu
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.
2 code implementations • ECCV 2020 • Nermin Samet, Samet Hicsonmez, Emre Akbas
We further validate the effectiveness of our proposal in another task, namely, "labels to photo" image generation by integrating the voting module of HoughNet to two different GAN models and showing that the accuracy is significantly improved in both cases.
Ranked #101 on Object Detection on COCO minival
1 code implementation • BMVC 2020 • Nermin Samet, Samet Hicsonmez, Emre Akbas
In this paper, we propose a new labeling strategy aimed to reduce the label noise in anchor-free detectors.
Ranked #122 on Object Detection on COCO test-dev
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 #86 on Object Detection on COCO test-dev
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.
1 code implementation • 4 Feb 2021 • Ilke Cugu, Emre Akbas
Convolutional neural networks (CNNs) are able to attain better visual recognition performance than fully connected neural networks despite having much fewer parameters due to their parameter sharing principle.
1 code implementation • 11 Feb 2021 • Samet Hicsonmez, Nermin Samet, Emre Akbas, Pinar Duygulu
Our loss function can be integrated to any baseline GAN model.
no code implementations • 16 Feb 2021 • Adil Kaan Akan, Emre Akbas, Fatos T. Yarman Vural
The noise added to the original image is defined as the gradient of the cost function of the model.
3 code implementations • 14 Apr 2021 • Nermin Samet, Samet Hicsonmez, Emre Akbas
This paper presents HoughNet, a one-stage, anchor-free, voting-based, bottom-up object detection method.
1 code implementation • 8 Jun 2021 • Nermin Samet, Emre Akbas
Differently, in whole-body pose estimation, the locations of fine-grained keypoints (68 on face, 21 on each hand and 3 on each foot) are estimated as well, which creates a scale variance problem that needs to be addressed.
Ranked #1 on Facial Landmark Detection on COCO-WholeBody
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.)
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
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 • 28 Apr 2022 • Can Ufuk Ertenli, Ramazan Gokberk Cinbis, Emre Akbas
Our experiments on video semantic segmentation, video object detection, and human pose estimation in videos show that StreamDEQ achieves on-par accuracy with the baseline while being more than 2-4x faster.
Ranked #53 on Semantic Segmentation on Cityscapes val
no code implementations • 3 Aug 2022 • Gokcen Gokceoglu, Emre Akbas
As a result, it produces a final raster image by drawing the strokes on a canvas, using a minimal number of strokes and dynamically deciding when to stop.
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 • 20 Jan 2023 • Samet Hicsonmez, Nermin Samet, Emre Akbas, Pinar Duygulu
We leverage semantic image segmentation from a general-purpose panoptic segmentation network to generate an additional adversarial loss function.
1 code implementation • 10 Sep 2023 • Aref Miri Rekavandi, Shima Rashidi, Farid Boussaid, Stephen Hoefs, Emre Akbas, Mohammed Bennamoun
Transformers have rapidly gained popularity in computer vision, especially in the field of object recognition and detection.
1 code implementation • 7 Oct 2023 • Samet Hicsonmez, Nermin Samet, Fidan Samet, Oguz Bakir, Emre Akbas, Pinar Duygulu
Current state-of-the-art video-to-video translation models rely on having a video sequence or a single style image to stylize an input video.
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.