Scholar
Ramazan Gokberk Cinbis
Google Scholar ID: Za7uka8AAAAJ
Middle East Technical University (METU)
Citations & Impact
Citations
1,810
H-index
19
i10-index
27
Publications
20
Co-authors
39
list available
Publications
Resume
Academic Achievements
- 2025: Preprint 'Exploring Sparsity for Parameter Efficient Fine Tuning Using Wavelets'
- 2025: Paper accepted at ICML'25: 'Interchangeable Token Embeddings for Extendable Vocabulary and Alpha-Equivalence'
- 2025: Preprint 'Meta-LoRA: Meta-Learning LoRA Components for Domain-Aware ID Personalization'
- 2024: Recipient of the Science Academy Young Scientist Award (BAGEP 2024)
- 2024: Area Chair for BMVC 2024
- 2024: Published paper 'Utilizing Class-Agnostic Point-to-Box Regressors as Object Proposal Generators'
- 2024: Published SAR2ET paper on ET estimation without optical satellite data under cloudy conditions
- 2024: Published 'Shadow-aware terrain classification: advancing hyperspectral image sensing through GANs and correlated sample synthesis'
- 2023: CVPR 2023 paper 'Meta-tuning Loss Functions and Data Augmentation for Few-shot Object Detection'
- 2023: ICCV 2023 paper 'HybridAugment++: Unified Frequency Spectra Perturbations for Model Robustness'
- 2023: Area Chair for BMVC 2023
- 2022: ECCV 2022 paper 'StreamDEQ: Streaming Multiscale Deep Equilibrium Models'
- 2022: Published in Image and Vision Computing: 'Caption Generation on Scenes with Seen and Unseen Object Categories'
- 2022: IEEE TPAMI paper 'Tow...' (title incomplete)
- 2022: Neurocomputing paper 'Semantics-driven Attentive Few-shot Learning over Clean and Noisy Samples'
- 2022: Image and Vision Computing paper 'How robust are discriminatively trained zero-shot learning models?'
- 2022: ICLR 2022 paper 'Closed-form Sample Probing for Learning Generative Models in Zero-shot Learning'
- Organized the 1st VISION Workshop @ CVPR 2023 and 2nd VISION Workshop @ ECCV 2024
Background
- Research interests include data-efficient machine learning with minimal supervision (zero-shot, few-shot, weakly-supervised, self-supervised learning)
- Generative models
- Learning to learn (meta-learning)
- Vision-language integration
- Large-scale image/video understanding
