A Closer Look at Data Augmentation Strategies for Finetuning-Based Low/Few-Shot Object Detection
Not on the map. Why?
Abstract (arXiv)
Current methods for low- and few-shot object detection have primarily focused on enhancing model performance for detecting objects. One common approach to achieve this is by combining model finetuning with data augmentation strategies. However, little attention has been given to the energy efficiency of these approaches in data-scarce regimes. This paper seeks to conduct a comprehensive empirical study that examines both model performance and energy efficiency of custom data augmentations and automated data augmentation selection strategies when combined with a lightweight object detector. The methods are evaluated in three different benchmark datasets in terms of their performance and energy consumption, and the Efficiency Factor is employed to gain insights into their effectiveness considering both performance and efficiency. Consequently, it is shown that in many cases, the performance gains of data augmentation strategies are overshadowed by their increased energy usage, necessitating the development of more energy efficient data augmentation strategies to address data scarcity.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 20 of its 25 references that are in the map. First posted on arXiv 20 Aug 2024.
Builds on
20 of 25 references.
References · 20
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
- 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
- 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
- 2019Green AIcited by 620
- 2018Albumentations: fast and flexible image augmentationscited by 558
- 2020Frustratingly Simple Few-Shot Object Detectioncited by 280
- 2018Few-shot Object Detection via Feature Reweightingcited by 265
- 2018Deep Learning: A Critical Appraisalcited by 214
- 2018Low-Shot Learning from Imaginary Datacited by 181
- 2021FSCE: Few-Shot Object Detection via Contrastive Proposal Encodingcited by 168
- 2020Multi-Scale Positive Sample Refinement for Few-Shot Object Detectioncited by 116
- 2021DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detectioncited by 106
8 more
- 2021Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignmentcited by 57
- 2021Hallucination Improves Few-Shot Object Detectioncited by 50
- 2022Meta-DETR: Image-Level Few-Shot Detection with Inter-Class Correlation Exploitationcited by 48
- 2023Generating Features with Increased Crop-related Diversity for Few-Shot Object Detectioncited by 21
- 2018Designing Adaptive Neural Networks for Energy-Constrained Image Classificationcited by 18
- 2018ECC: Platform-Independent Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Modelcited by 15
- 2023FemtoDet: An Object Detection Baseline for Energy Versus Performance Tradeoffscited by 5
- 2024Evaluating the Energy Efficiency of Few-Shot Learning for Object Detection in Industrial Settingscited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.