Investigating the Challenges of Class Imbalance and Scale Variation in Object Detection in Aerial Images

2022-02-05 · Ahmed Elhagry, Mohamed Saeed

While object detection is a common problem in computer vision, it is even more challenging when dealing with aerial satellite images. The variety in object scales and orientations can make them difficult to identify. In addition, there can be large amounts of densely packed small objects such as cars. In this project, we propose a few changes to the Faster-RCNN architecture. First, we experiment with different backbones to extract better features. We also modify the data augmentations and generated anchor sizes for region proposals in order to better handle small objects. Finally, we investigate the effects of different loss functions. Our proposed design achieves an improvement of 4.7 mAP over the baseline which used a vanilla Faster R-CNN with a ResNet-101 FPN backbone.

📄 PDF Abstract BibTeX arXiv:2202.02489

Code (0)

등록된 구현이 없습니다.

Tasks

Objectobject-detection Object Detection Object Detection In Aerial Images

Methods 이 논문이 사용한 방법론

FPN 설명 없음

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

RoIPool 설명 없음

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

RPN A Region Proposal Network, or RPN, is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Faster R-CNN Faster R-CNN is an object detection model that improves on Fast R-CNN by utilising a region proposal network…

Investigating Group Distributionally Robust Optimization for Deep Imbalanced Learning: A Case Study of Binary Tabular Data Classification

2023-03-04 · Ismail. B. Mustapha, Shafaatunnur Hasan, Hatem S Y Nabbus, Mohamed Mostafa Ali Montaser 외

One of the most studied machine learning challenges that recent studies have shown the susceptibility of deep neural networks to is the class imbalance problem. While concerted research efforts in this direction have bee…

SGMA: Semantic-Guided Modality-Aware Segmentation for Remote Sensing with Incomplete Multimodal Data

2026-03-03 · Lekang Wen, Liang Liao, Jing Xiao, Mi Wang arxiv

Multimodal semantic segmentation integrates complementary information from diverse sensors for remote sensing Earth observation. However, practical systems often encounter missing modalities due to sensor failures or inc…

Semantic Segmentation Contrastive Learning

Geo-Spatiotemporal Features and Shape-Based Prior Knowledge for Fine-grained Imbalanced Data Classification

2021-03-21 · Charles A. Kantor, Marta Skreta, Brice Rauby, Léonard Boussioux 외

Fine-grained classification aims at distinguishing between items with similar global perception and patterns, but that differ by minute details. Our primary challenges come from both small inter-class variations and larg…

Classification General Classification

VIGraph: Generative Self-supervised Learning for Class-Imbalanced Node Classification

2023-11-02 · Yulan Hu, Sheng Ouyang, Zhirui Yang, Yong liu

Class imbalance in graph data presents significant challenges for node classification. While existing methods, such as SMOTE-based approaches, partially mitigate this issue, they still exhibit limitations in constructing…

Contrastive Learning Node Classification Self-Supervised Learning Variational Inference

Training-Free Dataset Pruning for Instance Segmentation

2025-03-02 · Yalun Dai, Lingao Xiao, Ivor W. Tsang, Yang He

Existing dataset pruning techniques primarily focus on classification tasks, limiting their applicability to more complex and practical tasks like instance segmentation. Instance segmentation presents three key challenge…

Instance Segmentation Segmentation Semantic Segmentation