News

• Feb. 2024 - New paper at Pattern Recognition: Cross-lingual few-shot sign language recognition
• Feb. 2024 - Paper to appear at ICLR'24 workshop MLGenX: DARKIN: A zero-shot classification benchmark and an evaluation of protein language models
• July 2023 - New paper to appear at ICCV 2023: HybridAugment++: Unified Frequency Spectra Perturbations for Model Robustness
• June 2023 - I will be an area chair at BMVC 2023.
• Mar. 2023 - New paper to appear at CVPR 2023: Meta-tuning Loss Functions and Data Augmentation for Few-shot Object Detection
• Feb. 2023 - We are organizing the 1st workshop on Vision-based InduStrial InspectiON (@CVPR 2023).
• Feb. 2023 - New TUBITAK project on any-shot learning for the dark phosphoproteome (PI: Dr. Oznur Tastan).
• Nov. 2022 - Our work on Semantics-driven Attentive Few-shot Learning over Clean and Noisy Samples will be published at Neurocomputing.
• July 2022 - I will be an area chair at BMVC 2022.
• July 2022 - StreamDEQ (Streaming Multiscale Deep Equilibrium Models) will appear at ECCV 2022.
• July 2022 - New paper accepted for publication at Image and Vision Computing: Caption Generation on Scenes with Seen and Unseen Object Categories.
• Apr. 2022 - New preprint: Streaming Multiscale Deep Equilibrium Models.
• Apr. 2022 - We will be a part of the "Improving Resiliency of Malian Farmers with Yield Estimation" project (together with ITU, Agcurate and OKO Finance), one of 13 projects recently funded by ClimateChange AI.
• Mar. 2022 - New paper published at Image and Vision Computing: How robust are discriminatively trained zero-shot learning models?.
• Jan. 2022 - New paper to appear at ICLR 2022: Closed-form Sample Probing for Learning Generative Models in Zero-shot Learning.
• Jan. 2022 - New IEEE TPAMI paper: Towards Zero-shot Sign Language Recognition.
Jan. 2022 - New arXiv preprint: Semantics-driven Attentive Few-shot Learning over Clean and Noisy Samples.
Jan. 2022 - Our work on drug side effect prediction is accepted for publication at IEEE/ACM Transactions on Computational Biology and Bioinformatics.
Jan. 2022 - New paper to appear at IEEE/CVF WACV 2022: MaskSplit: Self-supervised Meta-learning for Few-shot Semantic Segmentation. [video]
Aug. 2021 - New arXiv preprint: Detection and Captioning with Unseen Object Classes.
July 2021 - I will be an area chair at BMVC 2021.
April 2021 - New paper on Weakly Supervised Instance Attention for Multisource Fine-Grained Object Recognition with an Application to Tree Species Classification will be published in ISPRS Journal of Photogrammetry and Remote Sensing.
Sep 2020 - Our work: Red Carpet to Fight Club: Partially-supervised Domain Transfer for Face Recognition in Violent Videos will appear in WACV 2021. The dataset is available online on the project page.
Aug 2020 - New paper on adversarial robustness in zero-shot learning, to appear in ECCV 2020 Workshop on Adversarial Robustness in the Real World.
July 2020 - We (as METU) have been selected as a Key Innovator, jointly with two other partners, for our activities in the SnapEarth project. [details]
June 2020 - I have been listed as one of the Outstanding Reviewers at CVPR 2020.
June 2020 - I will give lectures at Bilim Akademisi - Bilkent University AI Summer School 2020.
Apr. 2020 - New TUBITAK 1001 research project on meta-learning. Students interested in full-time scholarship positions: please email me. [project page]
Mar. 2020 - Our work on collaborative model training has been accepted to Pattern Recognition. [paper]
Feb. 2020 - I am honored to be one of the recipients of Google Faculty Research Awards 2019-2020!
Jan. 2020 - with Prof Emre Akbas, we are offering the Deep Generative Models course in Spring 2020.
Jan. 2020 - new work to appear at SPIE Medical Imaging 2020 conference: Graph convolutional networks for region of interest classification in breast histopathology.
Dec. 2019 - new H2020 project SnapEarth has started. For more information: [LinkedIn]
Nov. 2019 - new preprint: DeepSide: A Deep Learning Framework for Drug Side Effect Prediction
Sep. 2019 - I have given seminars at VBYO and Google DeepMind.
Aug. 2019 - new preprint on preventing GAN attacks in collaborative learning. [arXiv]
July 2019 - Two papers to appear at BMVC'19: (i) Image Captioning with Unseen Objects, (ii) Zero-Shot Sign Language Recognition: Can Textual Data Uncover Sign Languages?.
June 2019 - GMN source code is now out on Bulent's github page, with updated results: github.com/mbsariyildiz/gmn-zsl
May. 2019 - New ICIP'19 paper: Learning Visually Consistent Label Embeddings for Zero-Shot Learning.
Mar. 2019 - Two papers to appear at CVPR'19: (i) Gradient Matching Generative Networks for Zero-Shot Learning. (ii) Cross-task weakly supervised learning from instructional videos.
Mar. 2019 - New IGARSS'19 paper: Weakly Supervised Deep Convolutional Networks For Fine-grained Object Recognition In Multispectral Images .
Feb. 2019 - offering Introduction to Computer Vision and Advanced Deep Learning courses for Spring'19.
Jan. 2019 - our work on Multisource Region Attention Network for Fine-Grained Object Recognition will be published in IEEE TGRS.
Oct 2018 - our translation of Deep Learning book by Goodfellow et al has been published.
July 2018 - visiting Inria Paris - WILLOW Team, until mid-August.
July 2018 - our work on zero-shot object detection has been accepted to BMVC 2018.
June 2018 - Gencer Sumbul, jointly supervised by Selim Aksoy and me, successfully defended his MSc thesis with very nice results on deep learning for remote sensing. He will continue his PhD study at TU Berlin.
May 2018 - new preprint on face detection and recognition in violent scenes. [arXiv]
May 2018 - new preprint on zero-shot object detection. [arXiv]
Mar. 2018 - I was a panelist at BYORK Big Data and AI Workshop in Ankara.
Feb. 2018 - offering Introduction to Computer Vision and Advanced Deep Learning courses for Spring'18.
Sep. 2017 - joined METU as an assistant professor of computer science.
Sep. 2017 - our work on zero-shot learning and fine-grained classification for remote sensing will be published in IEEE TGRS.
July 2017 - one paper accepted to ICCV'17: Attributes2Classname: A discriminative model for attribute-based unsupervised zero-shot learning.
June 2017 - We are organizing a summer school on artificial intelligence for high-school students.
May 2017 - I will be one of the lecturers at the computer vision and robotics summer school in Ankara, organized by Hacettepe University.
May 2017 - new arXiv preprint on using attributes in deep zero-shot learning of classes with unknown attributes.
Dec. 2016 - Berkan Demirel, co-supervised with Nazli Ikizler-Cinbis, successfully defended his MSc thesis.
Nov. 2016 - new TUBITAK CAREER research grant on learning with weak supervision.
May 2016 - our SIU 2016 paper received Alper Atalay Best Student Paper Award - Third Prize.
Feb. 2016 - starting as an assistant professor at Bilkent University!
Jan. 2016 - new TPAMI paper: "Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning".
Sep. 2015 - new TPAMI paper: "Approximate Fisher Kernels of non-iid Image Models for Image Categorization".
Jun. 2015 - invited talk at ORASIS 2015.
Apr. 2015 - Best PhD Thesis Prize by French Association for Pattern Recognition (AFRIF).

Selected Publications   Google Scholar   All Publications

Cross-lingual few-shot sign language recognition

Y. C. Bilge, N. Ikizler-Cinbis, R. G. Cinbis

Pattern Recognition, 151, pp. 110374, July 2024

HybridAugment++: Unified Frequency Spectra Perturbations for Model Robustness

M. K. Yucel, R. G. Cinbis, P. Duygulu

IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France, October 2023

[video]

VISION Datasets: A Benchmark for Vision-based InduStrial InspectiON

H. Bai, S. Mou, T. Likhomanenko, R. G. Cinbis, O. Tuzel, P. Huang, J. Shan, J. Shi, M. Cao

arXiv:2306.07890, June 2023

Meta-tuning Loss Functions and Data Augmentation for Few-shot Object Detection

B. Demirel, O. B. Baran, R. G. Cinbis

IEEE/CVF Conference on Computer Vision & Pattern Recognition (CVPR), Vancouver, Canada, June 2023

Towards Zero-shot Sign Language Recognition

Y. C. Bilge, R. G. Cinbis, N. Ikizler-Cinbis

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 45, pp. 1217-1232, January 2023

[project]

Semantics-driven Attentive Few-shot Learning over Clean and Noisy Samples

O. B. Baran, R. G. Cinbis

Neurocomputing, 513, pp. 59-69, November 2022

[code]

Streaming Multiscale Deep Equilibrium Models

C. U. Ertenli, E. Akbas*, R. G. Cinbis*

European Conference on Computer Vision (ECCV), October 2022

[code] [project]

Caption Generation on Scenes with Seen and Unseen Object Categories

B. Demirel, R. G. Cinbis

Image and Vision Computing, 124, pp. 104515, August 2022

Closed-form Sample Probing for Learning Generative Models in Zero-shot Learning

S. Cetin, O. B. Baran, R. G. Cinbis

International Conference on Learning Representations (ICLR), April 2022

[code] [poster]

How robust are discriminatively trained zero-shot learning models?

M. K. Yucel, R. G. Cinbis, P. Duygulu

Image and Vision Computing, 119, pp. 104392, March 2022

MaskSplit: Self-supervised Meta-learning for Few-shot Semantic Segmentation

M. S. Amac, A. Sencan, O. B. Baran, N. Ikizler-Cinbis, R. G. Cinbis

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), January 2022

[code] [video]

Weakly Supervised Instance Attention for Multisource Fine-Grained Object Recognition with an Application to Tree Species Classification

B. Aygunes, R. G. Cinbis, S. Aksoy

ISPRS Journal of Photogrammetry and Remote Sensing, 176, pp. 262-274, June 2021

Red Carpet to Fight Club: Partially-supervised Domain Transfer for Face Recognition in Violent Videos

M. K. Yucel, Y. C. Bilge, N. Ikizler-Cinbis, P. Duygulu, R. G. Cinbis

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), January 2021

[project]

Key Protected Classification for Collaborative Learning

M. B. Sariyildiz, R. G. Cinbis, E. Ayday

Pattern Recognition, 104, pp. 107327, August 2020

[code]

Gradient Matching Generative Networks for Zero-Shot Learning

M. B. Sariyildiz, R. G. Cinbis

IEEE/CVF Conference on Computer Vision & Pattern Recognition (CVPR), Long Beach, CA, USA, June 2019 (Oral Presentation)

[code]

Cross-task weakly supervised learning from instructional videos

D. Zhukov, J.-B. Alayrac, R.G. Cinbis, D. Fouhey, I. Laptev, J. Sivic

IEEE/CVF Conference on Computer Vision & Pattern Recognition (CVPR), Long Beach, CA, USA, June 2019

Multisource Region Attention Network for Fine-Grained Object Recognition in Remote Sensing Imagery

G. Sumbul, R. G. Cinbis, S. Aksoy

IEEE Transactions on Geoscience and Remote Sensing (TGRS), 57, pp. 1558-0644, July 2019

Attributes2Classname: A discriminative model for attribute-based unsupervised zero-shot learning

B. Demirel, R. G. Cinbis, N. Ikizler-Cinbis

IEEE International Conference on Computer Vision (ICCV), Venice, Italy, October 2017

[code]

Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning

R. G. Cinbis, J. Verbeek, C. Schmid

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 39(1), pp. 189-203, January 2017

[code]

Approximate Fisher Kernels of non-iid Image Models for Image Categorization

R. G. Cinbis, J. Verbeek, C. Schmid

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 38(6), pp. 1084-1098, June 2016

[code]