463 citations · 790 across the 24 of their papers we have counts for
29 papers
LuMon: A Comprehensive Benchmark and Development Suite with Novel Datasets for Lunar Monocular Depth Estimation
Aytaç Sekmen, Fatih Emre Gunes, Furkan Horoz +9
Monocular Depth Estimation (MDE) is crucial for autonomous lunar rover navigation using electro-optical cameras. However, deploying terrestrial MDE networks to the Moon brings a se…
Policy-based Tuning of Autoregressive Image Models with Instance- and Distribution-Level Rewards
Orhun Bugra Baran, Melih Kandemir, Ramazan Gokberk Cinbis
Autoregressive (AR) models are highly effective for image generation, yet their standard maximum-likelihood estimation training lacks direct optimization for sample quality and div…
Exploring Sparsity for Parameter Efficient Fine Tuning Using Wavelets for Vision
Ahmet Bilican, M. Akın Yılmaz, A. Murat Tekalp +1
Efficiently adapting large pretrained models is critical under tight compute and memory budgets. While Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA achieve efficiency t…
Meta-LoRA: Meta-Learning LoRA Components for Domain-Aware ID Personalization
Barış Batuhan Topal, Umut Özyurt, Zafer Doğan Budak +1
Recent advancements in text-to-image generative models, particularly latent diffusion models (LDMs), have demonstrated remarkable capabilities in synthesizing high-quality images f…
Interchangeable Token Embeddings for Extendable Vocabulary and Alpha-Equivalence
İlker Işık, Ramazan Gokberk Cinbis, Ebru Aydin Gol
Language models lack the notion of interchangeable tokens: symbols that are semantically equivalent yet distinct, such as bound variables in formal logic. This limitation prevents…
Learning to Estimate System Specifications in Linear Temporal Logic using Transformers and Mamba
İlker Işık, Ebru Aydin Gol, Ramazan Gokberk Cinbis
Temporal logic is a framework for representing and reasoning about propositions that evolve over time. It is commonly used for specifying requirements in various domains, including…
HybridAugment++: Unified Frequency Spectra Perturbations for Model Robustness
Mehmet Kerim Yucel, Ramazan Gokberk Cinbis, Pinar Duygulu
Convolutional Neural Networks (CNN) are known to exhibit poor generalization performance under distribution shifts. Their generalization have been studied extensively, and one line…
VISION Datasets: A Benchmark for Vision-based InduStrial InspectiON
Haoping Bai, Shancong Mou, Tatiana Likhomanenko +6
Despite progress in vision-based inspection algorithms, real-world industrial challenges -- specifically in data availability, quality, and complex production requirements -- often…
Meta-tuning Loss Functions and Data Augmentation for Few-shot Object Detection
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…
Representation Recycling for Streaming Video Analysis
Can Ufuk Ertenli, Ramazan Gokberk Cinbis, Emre Akbas
We present StreamDEQ, a method that aims to infer frame-wise representations on videos with minimal per-frame computation. Conventional deep networks perform feature extraction fro…
How Robust are Discriminatively Trained Zero-Shot Learning Models?
Mehmet Kerim Yucel, Ramazan Gokberk Cinbis, Pinar Duygulu
Data shift robustness has been primarily investigated from a fully supervised perspective, and robustness of zero-shot learning (ZSL) models have been largely neglected. In this pa…
Towards Zero-shot Sign Language Recognition
Yunus Can Bilge, Ramazan Gokberk Cinbis, Nazli Ikizler-Cinbis
This paper tackles the problem of zero-shot sign language recognition (ZSSLR), where the goal is to leverage models learned over the seen sign classes to recognize the instances of…
MaskSplit: Self-supervised Meta-learning for Few-shot Semantic Segmentation
Mustafa Sercan Amac, Ahmet Sencan, Orhun Bugra Baran +2
Just like other few-shot learning problems, few-shot segmentation aims to minimize the need for manual annotation, which is particularly costly in segmentation tasks. Even though t…
Caption Generation on Scenes with Seen and Unseen Object Categories
Berkan Demirel, Ramazan Gokberk Cinbis
Image caption generation is one of the most challenging problems at the intersection of vision and language domains. In this work, we propose a realistic captioning task where the…
Weakly Supervised Instance Attention for Multisource Fine-Grained Object Recognition with an Application to Tree Species Classification
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…
Red Carpet to Fight Club: Partially-supervised Domain Transfer for Face Recognition in Violent Videos
Yunus Can Bilge, Mehmet Kerim Yucel, Ramazan Gokberk Cinbis +2
In many real-world problems, there is typically a large discrepancy between the characteristics of data used in training versus deployment. A prime example is the analysis of aggre…
A Deep Dive into Adversarial Robustness in Zero-Shot Learning
Mehmet Kerim Yucel, Ramazan Gokberk Cinbis, Pinar Duygulu
Machine learning (ML) systems have introduced significant advances in various fields, due to the introduction of highly complex models. Despite their success, it has been shown mul…
Key Protected Classification for Collaborative Learning
Mert Bülent Sarıyıldız, Ramazan Gökberk Cinbiş, Erman Ayday
Large-scale datasets play a fundamental role in training deep learning models. However, dataset collection is difficult in domains that involve sensitive information. Collaborative…
Image Captioning with Unseen Objects
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. A number of recently proposed approaches…
Zero-Shot Sign Language Recognition: Can Textual Data Uncover Sign Languages?
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 o…
Learning Visually Consistent Label Embeddings for Zero-Shot Learning
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 embeddi…
Cross-task weakly supervised learning from instructional videos
Dimitri Zhukov, Jean-Baptiste Alayrac, Ramazan Gokberk Cinbis +3
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 stro…
Multisource Region Attention Network for Fine-Grained Object Recognition in Remote Sensing Imagery
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. Multisource data analysis, that aims to…
Wildest Faces: Face Detection and Recognition in Violent Settings
Mehmet Kerim Yucel, Yunus Can Bilge, Oguzhan Oguz +3
With the introduction of large-scale datasets and deep learning models capable of learning complex representations, impressive advances have emerged in face detection and recogniti…