Meta-tuning Loss Functions and Data Augmentation for Few-shot Object Detection

Date

2023-06-21

Author

Demirel, Berkan
Baran, Orhun Buğra
Cinbiş, Ramazan Gökberk

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

121
views

140
downloads

Cite This

Few-shot object detection, the problem of modelling novel object detection categories with few training instances, is an emerging topic in the area of few-shot learning and ob- ject detection. Contemporary techniques can be divided into two groups: fine-tuning based and meta-learning based approaches. While meta-learning approaches aim to learn dedicated meta-models for mapping samples to novel class models, fine-tuning approaches tackle few-shot detection in a simpler manner, by adapting the detection model to novel classes through gradient based optimization. Despite their simplicity, fine-tuning based approaches typically yield competitive detection results. Based on this observation, we focus on the role of loss functions and augmentations as the force driving the fine-tuning process, and propose to tune their dynamics through meta-learning principles. The pro- posed training scheme, therefore, allows learning inductive biases that can boost few-shot detection, while keeping the advantages of fine-tuning based approaches. In addition, the proposed approach yields interpretable loss functions, as opposed to highly parametric and complex few-shot meta- models. The experimental results highlight the merits of the proposed scheme, with significant improvements over the strong fine-tuning based few-shot detection baselines on benchmark Pascal VOC and MS-COCO datasets, in terms of both standard and generalized few-shot performance metrics.

URI

https://openaccess.thecvf.com/content/CVPR2023/papers/Demirel_Meta-Tuning_Loss_Functions_and_Data_Augmentation_for_Few-Shot_Object_Detection_CVPR_2023_paper.pdf
https://hdl.handle.net/11511/104933

Collections

Department of Computer Engineering, Conference / Seminar