1 code implementation • ICCV 2023 • Mehmet Kerim Yucel, Ramazan Gokberk Cinbis, Pinar Duygulu
First, inspired by these observations, we propose a simple yet effective data augmentation method HybridAugment that reduces the reliance of CNNs on high-frequency components, and thus improves their robustness while keeping their clean accuracy high.
no code implementations • 13 Jun 2023 • Haoping Bai, Shancong Mou, Tatiana Likhomanenko, Ramazan Gokberk Cinbis, Oncel Tuzel, Ping Huang, Jiulong Shan, Jianjun Shi, Meng Cao
We introduce the VISION Datasets, a diverse collection of 14 industrial inspection datasets, uniquely poised to meet these challenges.
no code implementations • CVPR 2023 • Berkan Demirel, Orhun Buğra Baran, Ramazan Gokberk Cinbis
Few-shot object detection, the problem of modelling novel object detection categories with few training instances, is an emerging topic in the area of few-shot learning and object detection.
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
1 code implementation • 26 Jan 2022 • Mehmet Kerim Yucel, Ramazan Gokberk Cinbis, Pinar Duygulu
In this paper, we present novel analyses on the robustness of discriminative ZSL to image corruptions.
no code implementations • 15 Jan 2022 • Yunus Can Bilge, Ramazan Gokberk Cinbis, Nazli Ikizler-Cinbis
For this novel problem setup, we introduce three benchmark datasets with their accompanying textual and attribute descriptions to analyze the problem in detail.
1 code implementation • 23 Oct 2021 • Mustafa Sercan Amac, Ahmet Sencan, Orhun Bugra Baran, Nazli Ikizler-Cinbis, Ramazan Gokberk Cinbis
To alleviate this need, we propose a self-supervised training approach for learning few-shot segmentation models.
1 code implementation • ICLR 2022 • Samet Cetin, Orhun Buğra Baran, Ramazan Gokberk Cinbis
In our approach, at each generative model update step, we fit a task-specific closed-form ZSL model from generated samples, and measure its loss on novel samples all within the compute graph, a procedure that we refer to as sample probing.
no code implementations • 13 Aug 2021 • Berkan Demirel, Ramazan Gokberk Cinbis
For this problem, we propose a detection-driven approach that consists of a single-stage generalized zero-shot detection model to recognize and localize instances of both seen and unseen classes, and a template-based captioning model that transforms detections into sentences.
no code implementations • 23 May 2021 • Bulut Aygunes, Ramazan Gokberk Cinbis, Selim Aksoy
Multisource image analysis that leverages complementary spectral, spatial, and structural information benefits fine-grained object recognition that aims to classify an object into one of many similar subcategories.
no code implementations • 16 Sep 2020 • Yunus Can Bilge, Mehmet Kerim Yucel, Ramazan Gokberk Cinbis, Nazli Ikizler-Cinbis, Pinar Duygulu
To mimic such scenarios, we formulate a realistic domain-transfer problem, where the goal is to transfer the recognition model trained on clean posed images to the target domain of violent videos, where training videos are available only for a subset of subjects.
2 code implementations • 17 Aug 2020 • Mehmet Kerim Yucel, Ramazan Gokberk Cinbis, Pinar Duygulu
In constrast, Zero-shot Learning (ZSL) and Generalized Zero-shot Learning (GZSL) tasks inherently lack supervision across all classes.
no code implementations • 31 Jul 2019 • Berkan Demirel, Ramazan Gokberk Cinbis, Nazli Ikizler-Cinbis
Image caption generation is a long standing and challenging problem at the intersection of computer vision and natural language processing.
no code implementations • 24 Jul 2019 • Yunus Can Bilge, Nazli Ikizler-Cinbis, Ramazan Gokberk Cinbis
We introduce the problem of zero-shot sign language recognition (ZSSLR), where the goal is to leverage models learned over the seen sign class examples to recognize the instances of unseen signs.
no code implementations • 16 May 2019 • Berkan Demirel, Ramazan Gokberk Cinbis, Nazli Ikizler-Cinbis
In this work, we propose a zero-shot learning method to effectively model knowledge transfer between classes via jointly learning visually consistent word vectors and label embedding model in an end-to-end manner.
2 code implementations • CVPR 2019 • Dimitri Zhukov, Jean-Baptiste Alayrac, Ramazan Gokberk Cinbis, David Fouhey, Ivan Laptev, Josef Sivic
In this paper we investigate learning visual models for the steps of ordinary tasks using weak supervision via instructional narrations and an ordered list of steps instead of strong supervision via temporal annotations.
Ranked #5 on Temporal Action Localization on CrossTask
no code implementations • 18 Jan 2019 • Gencer Sumbul, Ramazan Gokberk Cinbis, Selim Aksoy
Fine-grained object recognition concerns the identification of the type of an object among a large number of closely related sub-categories.
no code implementations • 19 May 2018 • Mehmet Kerim Yucel, Yunus Can Bilge, Oguzhan Oguz, Nazli Ikizler-Cinbis, Pinar Duygulu, Ramazan Gokberk Cinbis
With the introduction of large-scale datasets and deep learning models capable of learning complex representations, impressive advances have emerged in face detection and recognition tasks.
2 code implementations • 16 May 2018 • Berkan Demirel, Ramazan Gokberk Cinbis, Nazli Ikizler-Cinbis
Object detection is considered as one of the most challenging problems in computer vision, since it requires correct prediction of both classes and locations of objects in images.
Ranked #7 on Zero-Shot Object Detection on PASCAL VOC'07
no code implementations • 9 Dec 2017 • Gencer Sumbul, Ramazan Gokberk Cinbis, Selim Aksoy
Fine-grained object recognition that aims to identify the type of an object among a large number of subcategories is an emerging application with the increasing resolution that exposes new details in image data.
1 code implementation • ICCV 2017 • Berkan Demirel, Ramazan Gokberk Cinbis, Nazli Ikizler-Cinbis
We propose a novel approach for unsupervised zero-shot learning (ZSL) of classes based on their names.
no code implementations • 3 Oct 2015 • Ramazan Gokberk Cinbis, Jakob Verbeek, Cordelia Schmid
It has been experimentally observed that the performance of BoW and FV representations can be improved by employing discounting transformations such as power normalization.
no code implementations • 3 Mar 2015 • Ramazan Gokberk Cinbis, Jakob Verbeek, Cordelia Schmid
In this case, the supervised information is restricted to binary labels that indicate the absence/presence of object instances in the image, without their locations.
no code implementations • CVPR 2014 • Ramazan Gokberk Cinbis, Jakob Verbeek, Cordelia Schmid
In this case, the supervised information is restricted to binary labels that indicate the absence/presence of object instances in the image, without their locations.