Search Results for author: Ramazan Gokberk Cinbis

Found 25 papers, 9 papers with code

Learning to Estimate System Specifications in Linear Temporal Logic using Transformers and Mamba

no code implementations31 May 2024 İlker Işık, Ebru Aydin Gol, Ramazan Gokberk Cinbis

Specification mining or formula generation involves extracting temporal logic formulae from system traces and has numerous applications, such as detecting bugs and improving interpretability.

Decoder

HybridAugment++: Unified Frequency Spectra Perturbations for Model Robustness

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.

Adversarial Robustness Data Augmentation +1

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

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.

Data Augmentation Few-Shot Learning +4

Representation Recycling for Streaming Video Analysis

1 code implementation28 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.

object-detection Pose Estimation +3

How Robust are Discriminatively Trained Zero-Shot Learning Models?

1 code implementation26 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.

Zero-Shot Learning

Towards Zero-shot Sign Language Recognition

no code implementations15 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.

Attribute Descriptive +3

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

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.

Generalized Zero-Shot Learning Sample Probing

Caption Generation on Scenes with Seen and Unseen Object Categories

no code implementations13 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.

Caption Generation Language Modelling

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

no code implementations23 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.

Object Object Recognition +1

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

no code implementations16 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.

Face Recognition

A Deep Dive into Adversarial Robustness in Zero-Shot Learning

2 code implementations17 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.

Adversarial Robustness BIG-bench Machine Learning +1

Image Captioning with Unseen Objects

no code implementations31 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.

Caption Generation Image Captioning +6

Zero-Shot Sign Language Recognition: Can Textual Data Uncover Sign Languages?

no code implementations24 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.

Descriptive Object Recognition +3

Learning Visually Consistent Label Embeddings for Zero-Shot Learning

no code implementations16 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.

Transfer Learning Zero-Shot Learning

Cross-task weakly supervised learning from instructional videos

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.

Weakly-supervised Learning

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

no code implementations18 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.

General Classification Object Recognition

Wildest Faces: Face Detection and Recognition in Violent Settings

no code implementations19 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.

Face Detection Face Recognition

Zero-Shot Object Detection by Hybrid Region Embedding

2 code implementations16 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.

Object object-detection +1

Fine-Grained Object Recognition and Zero-Shot Learning in Remote Sensing Imagery

no code implementations9 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.

Language Modelling Object Recognition +2

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

no code implementations3 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.

Image Categorization

Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning

no code implementations3 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.

Multiple Instance Learning Object +2

Multi-fold MIL Training for Weakly Supervised Object Localization

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.

Multiple Instance Learning Object +2

Cannot find the paper you are looking for? You can Submit a new open access paper.