paper-with-me

Papers

Reduced Focal Loss: 1st Place Solution to xView object detection in Satellite Imagery

2019-03-04 · Nikolay Sergievskiy, Alexander Ponamarev

This paper describes our approach to the DIUx xView 2018 Detection Challenge [1]. This challenge focuses on a new satellite imagery dataset. The dataset contains 60 object classes that are highly imbalanced. Due to the imbalanced nature of the dataset, the training process becomes significantly more challenging. To address this problem, we introduce a novel Reduced Focal Loss function, which brought us 1st place in the DIUx xView 2018 Detection Challenge.

📄 PDF Abstract BibTeX arXiv:1903.01347

Code (0)

등록된 구현이 없습니다.

Tasks

object-detectionObject Detection

Similar Papers 제목 키워드 기반

A simple, strong baseline for building damage detection on the xBD dataset

2024-01-30 · Sebastian Gerard, Paul Borne-Pons, Josephine Sullivan

We construct a strong baseline method for building damage detection by starting with the highly-engineered winning solution of the xView2 competition, and gradually stripping away components. This way, we obtain a much s…

xFBD: Focused Building Damage Dataset and Analysis

2022-12-23 · Dennis Melamed, Cameron Johnson, Chen Zhao, Russell Blue 외

The xView2 competition and xBD dataset spurred significant advancements in overhead building damage detection, but the competition's pixel level scoring can lead to reduced solution performance in areas with tight cluste…

Building Damage Assessment

Cyclical Focal Loss

2022-02-16 · Leslie N. Smith

The cross-entropy softmax loss is the primary loss function used to train deep neural networks. On the other hand, the focal loss function has been demonstrated to provide improved performance when there is an imbalance …

Combining Transformers and CNNs for Efficient Object Detection in High-Resolution Satellite Imagery

2025-07-15 · Nicolas Drapier, Aladine Chetouani, Aurélien Chateigner arxiv

We present GLOD, a transformer-first architecture for object detection in high-resolution satellite imagery. GLOD replaces CNN backbones with a Swin Transformer for end-to-end feature extraction, combined with novel UpCo…

Computational EfficiencyObject Detection

xView: Objects in Context in Overhead Imagery

2018-02-22 · Darius Lam, Richard Kuzma, Kevin McGee, Samuel Dooley 외

We introduce a new large-scale dataset for the advancement of object detection techniques and overhead object detection research. This satellite imagery dataset enables research progress pertaining to four key computer v…

Objectobject-detectionObject DetectionObject Detection In Aerial Images