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

Demirel, Berkan
Baran, Orhun Buğra
Cinbiş, Ramazan Gökberk
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.
IEEE/CVF Conference on Computer Vision & Pattern Recognition
Citation Formats
B. Demirel, O. B. Baran, and R. G. Cinbiş, “Meta-tuning Loss Functions and Data Augmentation for Few-shot Object Detection,” presented at the IEEE/CVF Conference on Computer Vision & Pattern Recognition, Kanada, 2023, Accessed: 00, 2023. [Online]. Available: