# A Closer Look at Data Augmentation Strategies for Finetuning-Based Low/Few-Shot Object Detection

arXiv: https://arxiv.org/abs/2408.10940 · HTML: https://mlsanity.com/paper/2408.10940/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 25 references that are in the map.
- First posted on arXiv 20 Aug 2024.

## Builds on (most cited first, 20 of 20)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Green AI](https://mlsanity.com/paper/1907.10597/) (2019)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [Frustratingly Simple Few-Shot Object Detection](https://mlsanity.com/paper/2003.06957/) (2020)
- [Few-shot Object Detection via Feature Reweighting](https://mlsanity.com/paper/1812.01866/) (2018)
- [Deep Learning: A Critical Appraisal](https://mlsanity.com/paper/1801.00631/) (2018)
- [Low-Shot Learning from Imaginary Data](https://mlsanity.com/paper/1801.05401/) (2018)
- [FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding](https://mlsanity.com/paper/2103.05950/) (2021)
- [Multi-Scale Positive Sample Refinement for Few-Shot Object Detection](https://mlsanity.com/paper/2007.09384/) (2020)
- [DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection](https://mlsanity.com/paper/2108.09017/) (2021)
- [Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment](https://mlsanity.com/paper/2104.07719/) (2021)
- [Hallucination Improves Few-Shot Object Detection](https://mlsanity.com/paper/2105.01294/) (2021)
- [Meta-DETR: Image-Level Few-Shot Detection with Inter-Class Correlation Exploitation](https://mlsanity.com/paper/2208.00219/) (2022)
- [Generating Features with Increased Crop-related Diversity for Few-Shot Object Detection](https://mlsanity.com/paper/2304.05096/) (2023)
- [Designing Adaptive Neural Networks for Energy-Constrained Image Classification](https://mlsanity.com/paper/1808.01550/) (2018)
- [ECC: Platform-Independent Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model](https://mlsanity.com/paper/1812.01803/) (2018)
- [FemtoDet: An Object Detection Baseline for Energy Versus Performance Tradeoffs](https://mlsanity.com/paper/2301.06719/) (2023)
- [Evaluating the Energy Efficiency of Few-Shot Learning for Object Detection in Industrial Settings](https://mlsanity.com/paper/2403.06631/) (2024)

## Built on by (most cited first, 2 of 2)

- [Textile Analysis for Recycling Automation using Transfer Learning and Zero-Shot Foundation Models](https://mlsanity.com/paper/2506.06569/) (2025)
- [Fast Convergence through Distributed Augmentation for Class-Imbalanced Federated Learning](https://mlsanity.com/paper/2610.05279/) (2026)

## 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.