Search Results for author: Burak Uzkent

Found 20 papers, 9 papers with code

Augment the Pairs: Semantics-Preserving Image-Caption Pair Augmentation for Grounding-Based Vision and Language Models

1 code implementation5 Nov 2023 Jingru Yi, Burak Uzkent, Oana Ignat, Zili Li, Amanmeet Garg, Xiang Yu, Linda Liu

While we demonstrate our data augmentation method with MDETR framework, the proposed approach is applicable to common grounding-based vision and language tasks with other frameworks.

Data Augmentation Phrase Grounding +1

GOHSP: A Unified Framework of Graph and Optimization-based Heterogeneous Structured Pruning for Vision Transformer

no code implementations13 Jan 2023 Miao Yin, Burak Uzkent, Yilin Shen, Hongxia Jin, Bo Yuan

We first develop a graph-based ranking for measuring the importance of attention heads, and the extracted importance information is further integrated to an optimization-based procedure to impose the heterogeneous structured sparsity patterns on the ViT models.

Dynamic Inference With Grounding Based Vision and Language Models

no code implementations CVPR 2023 Burak Uzkent, Amanmeet Garg, Wentao Zhu, Keval Doshi, Jingru Yi, Xiaolong Wang, Mohamed Omar

For example, recent image and language models with more than 200M parameters have been proposed to learn visual grounding in the pre-training step and show impressive results on downstream vision and language tasks.

Language Modelling Referring Expression +3

Lite-MDETR: A Lightweight Multi-Modal Detector

no code implementations CVPR 2022 Qian Lou, Yen-Chang Hsu, Burak Uzkent, Ting Hua, Yilin Shen, Hongxia Jin

The key primitive is that Dictionary-Lookup-Transformormations (DLT) is proposed to replace Linear Transformation (LT) in multi-modal detectors where each weight in Linear Transformation (LT) is approximately factorized into a smaller dictionary, index, and coefficient.

object-detection Object Detection +3

Negative Data Augmentation

2 code implementations ICLR 2021 Abhishek Sinha, Kumar Ayush, Jiaming Song, Burak Uzkent, Hongxia Jin, Stefano Ermon

Empirically, models trained with our method achieve improved conditional/unconditional image generation along with improved anomaly detection capabilities.

Action Recognition Anomaly Detection +9

Efficient Conditional Pre-training for Transfer Learning

no code implementations20 Nov 2020 Shuvam Chakraborty, Burak Uzkent, Kumar Ayush, Kumar Tanmay, Evan Sheehan, Stefano Ermon

Finally, we improve standard ImageNet pre-training by 1-3% by tuning available models on our subsets and pre-training on a dataset filtered from a larger scale dataset.

Transfer Learning

Geography-Aware Self-Supervised Learning

1 code implementation ICCV 2021 Kumar Ayush, Burak Uzkent, Chenlin Meng, Kumar Tanmay, Marshall Burke, David Lobell, Stefano Ermon

Contrastive learning methods have significantly narrowed the gap between supervised and unsupervised learning on computer vision tasks.

 Ranked #1 on Semantic Segmentation on SpaceNet 1 (using extra training data)

Contrastive Learning Image Classification +4

Predicting Livelihood Indicators from Community-Generated Street-Level Imagery

1 code implementation15 Jun 2020 Jihyeon Lee, Dylan Grosz, Burak Uzkent, Sicheng Zeng, Marshall Burke, David Lobell, Stefano Ermon

Major decisions from governments and other large organizations rely on measurements of the populace's well-being, but making such measurements at a broad scale is expensive and thus infrequent in much of the developing world.

Efficient Poverty Mapping using Deep Reinforcement Learning

no code implementations7 Jun 2020 Kumar Ayush, Burak Uzkent, Kumar Tanmay, Marshall Burke, David Lobell, Stefano Ermon

The combination of high-resolution satellite imagery and machine learning have proven useful in many sustainability-related tasks, including poverty prediction, infrastructure measurement, and forest monitoring.

object-detection Object Detection +2

Farmland Parcel Delineation Using Spatio-temporal Convolutional Networks

no code implementations11 Apr 2020 Han Lin Aung, Burak Uzkent, Marshall Burke, David Lobell, Stefano Ermon

Using satellite imaging can be a scalable and cost effective manner to perform the task of farm parcel delineation to collect this valuable data.

Segmentation

Learning When and Where to Zoom with Deep Reinforcement Learning

2 code implementations CVPR 2020 Burak Uzkent, Stefano Ermon

While high resolution images contain semantically more useful information than their lower resolution counterparts, processing them is computationally more expensive, and in some applications, e. g. remote sensing, they can be much more expensive to acquire.

reinforcement-learning Reinforcement Learning (RL)

Generating Interpretable Poverty Maps using Object Detection in Satellite Images

no code implementations5 Feb 2020 Kumar Ayush, Burak Uzkent, Marshall Burke, David Lobell, Stefano Ermon

Accurate local-level poverty measurement is an essential task for governments and humanitarian organizations to track the progress towards improving livelihoods and distribute scarce resources.

Feature Importance Humanitarian +2

Cloud Removal in Satellite Images Using Spatiotemporal Generative Networks

3 code implementations14 Dec 2019 Vishnu Sarukkai, Anirudh Jain, Burak Uzkent, Stefano Ermon

In contrast, we cast the problem of cloud removal as a conditional image synthesis challenge, and we propose a trainable spatiotemporal generator network (STGAN) to remove clouds.

Cloud Removal Image Generation +2

Efficient Object Detection in Large Images using Deep Reinforcement Learning

3 code implementations9 Dec 2019 Burak Uzkent, Christopher Yeh, Stefano Ermon

Traditionally, an object detector is applied to every part of the scene of interest, and its accuracy and computational cost increases with higher resolution images.

object-detection Object Detection +2

Learning to Interpret Satellite Images in Global Scale Using Wikipedia

3 code implementations7 May 2019 Burak Uzkent, Evan Sheehan, Chenlin Meng, Zhongyi Tang, Marshall Burke, David Lobell, Stefano Ermon

Despite recent progress in computer vision, finegrained interpretation of satellite images remains challenging because of a lack of labeled training data.

Predicting Economic Development using Geolocated Wikipedia Articles

no code implementations5 May 2019 Evan Sheehan, Chenlin Meng, Matthew Tan, Burak Uzkent, Neal Jean, David Lobell, Marshall Burke, Stefano Ermon

Progress on the UN Sustainable Development Goals (SDGs) is hampered by a persistent lack of data regarding key social, environmental, and economic indicators, particularly in developing countries.

Learning to Interpret Satellite Images Using Wikipedia

no code implementations19 Sep 2018 Evan Sheehan, Burak Uzkent, Chenlin Meng, Zhongyi Tang, Marshall Burke, David Lobell, Stefano Ermon

Despite recent progress in computer vision, fine-grained interpretation of satellite images remains challenging because of a lack of labeled training data.

EnKCF: Ensemble of Kernelized Correlation Filters for High-Speed Object Tracking

2 code implementations20 Jan 2018 Burak Uzkent, Young-Woo Seo

Experimental results showed that the performance of ours is, on average, 70. 10% for precision at 20 pixels, 53. 00% for success rate for the OTB100 data, and 54. 50% and 40. 2% for the UAV123 data.

Object Tracking Vocal Bursts Intensity Prediction

Tracking in Aerial Hyperspectral Videos using Deep Kernelized Correlation Filters

no code implementations20 Nov 2017 Burak Uzkent, Aneesh Rangnekar, Matthew J. Hoffman

Hyperspectral imaging holds enormous potential to improve the state-of-the-art in aerial vehicle tracking with low spatial and temporal resolutions.

General Classification Image Generation +1

Aerial Vehicle Tracking by Adaptive Fusion of Hyperspectral Likelihood Maps

no code implementations12 Jul 2017 Burak Uzkent, Aneesh Rangnekar, M. J. Hoffman

Hyperspectral cameras can provide unique spectral signatures for consistently distinguishing materials that can be used to solve surveillance tasks.

object-detection Object Detection +1

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