xView: Objects in Context in Overhead Imagery

Lam, Darius; Kuzma, Richard; McGee, Kevin; Dooley, Samuel; Laielli, Michael; Klaric, Matthew; Bulatov, Yaroslav; McCord, Brendan

doi:10.48550/arxiv.1802.07856

Cited by 69 publications

(96 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We train a YOLO-based regression model for counting the number of buildings using the xView dataset [12], which provides high-resolution satellite images of 0.3m GSD.…”

Section: Appendix B: Cost Computation Detailsmentioning

confidence: 99%

See 1 more Smart Citation

IS-COUNT: Large-scale Object Counting from Satellite Images with Covariate-based Importance Sampling

Meng¹,

Liu²,

Neiswanger³

et al. 2021

Preprint

View full text Add to dashboard Cite

Object detection in high-resolution satellite imagery is emerging as a scalable alternative to on-the-ground survey data collection in many environmental and socioeconomic monitoring applications. However, performing object detection over large geographies can still be prohibitively expensive due to the high cost of purchasing imagery and compute. Inspired by traditional survey data collection strategies, we propose an approach to estimate object count statistics over large geographies through sampling. Given a cost budget, our method selects a small number of representative areas by sampling from a learnable proposal distribution. Using importance sampling, we are able to accurately estimate object counts after processing only a small fraction of the images compared to an exhaustive approach. We show empirically that the proposed framework achieves strong performance on estimating the number of buildings in the United States and Africa, cars in Kenya, brick kilns in Bangladesh, and swimming pools in the U.S., while requiring as few as 0.01% of satellite images compared to an exhaustive approach.

show abstract

“…We train a YOLO-based regression model for counting the number of buildings using the xView dataset [12], which provides high-resolution satellite images of 0.3m GSD.…”

Section: Appendix B: Cost Computation Detailsmentioning

confidence: 99%

“…We preprocess the xView dataset [12] into image tiles of size 416 × 416pix (i.e. the input size of YOLO-v3).…”

Section: Appendix B: Cost Computation Detailsmentioning

confidence: 99%

IS-COUNT: Large-scale Object Counting from Satellite Images with Covariate-based Importance Sampling

Meng¹,

Liu²,

Neiswanger³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…There exist multiple datasets to train a method for building footprint localisation, such as SpaceNet (spacenet.ai), Open Cities AI Challenge (drivendata.org/competitions/60/ building-segmentation-disaster-resilience), DeepGlobe2018 [Demir et al, 2018] and damaged building datasets such as xView [Lam et al, 2018] and xBD [Gupta et al, 2019].…”

Section: The Crowd-labelled Datasetmentioning

confidence: 99%

Disaster mapping from satellites: damage detection with crowdsourced point labels

Kuzin¹,

Isupova²,

Simmons³

et al. 2021

Preprint

View full text Add to dashboard Cite

High-resolution satellite imagery available immediately after disaster events is crucial for response planning as it facilitates broad situational awareness of critical infrastructure status such as building damage, flooding, and obstructions to access routes. Damage mapping at this scale would require hundreds of expert personhours. However, a combination of crowdsourcing and recent advances in deep learning reduces the effort needed to just a few hours in real time. Asking volunteers to place point marks, as opposed to shapes of actual damaged areas, significantly decreases the required analysis time for response during the disaster. However, different volunteers may be inconsistent in their marking. This work presents methods for aggregating potentially inconsistent damage marks to train a neural network damage detector.35th Conference on Neural Information Processing Systems (NeurIPS 2021).

show abstract

“…We use COCO [28] and xView [22] datasets in our experiments. COCO is a common object detection dataset while xView is a large public dataset of overhead imagery.…”

Section: Evaluation Settingsmentioning

confidence: 99%

Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection

Liu¹,

Levine²,

Lau³

et al. 2021

Preprint

View full text Add to dashboard Cite

Object detection plays a key role in many security-critical systems. Adversarial patch attacks, which are easy to implement in the physical world, pose a serious threat to stateof-the-art object detectors. Developing reliable defenses for object detectors against patch attacks is critical but severely understudied. In this paper, we propose Segment and Complete defense (SAC), a general framework for defending object detectors against patch attacks through detecting and removing adversarial patches. We first train a patch segmenter that outputs patch masks that provide pixel-level localization of adversarial patches. We then propose a self adversarial training algorithm to robustify the patch segmenter. In addition, we design a robust shape completion algorithm, which is guaranteed to remove the entire patch from the images given the outputs of the patch segmenter are within a certain Hamming distance of the ground-truth patch masks. Our experiments on COCO and xView datasets demonstrate that SAC achieves superior robustness even under strong adaptive attacks with no performance drop on clean images, and generalizes well to unseen patch shapes, attack budgets, and unseen attack methods. Furthermore, we present the APRICOT-Mask dataset, which augments the APRICOT dataset with pixel-level annotations of adversarial patches. We show SAC can significantly reduce the targeted attack success rate of physical patch attacks.

show abstract

xView: Objects in Context in Overhead Imagery

Cited by 69 publications

References 23 publications

IS-COUNT: Large-scale Object Counting from Satellite Images with Covariate-based Importance Sampling

IS-COUNT: Large-scale Object Counting from Satellite Images with Covariate-based Importance Sampling

Disaster mapping from satellites: damage detection with crowdsourced point labels

Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection

Contact Info

Product

Resources

About