CAMO-FS

Introduced in The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentation2024

About this Dataset

CAMO-FS Dataset comes with the paper entitled The Art of Camouflage: Few-shot Learning for Animal Detection and Segmentation.

DOI: https://doi.org/10.1109/ACCESS.2024.3432873

Official GitHub: https://github.com/danhntd/FS-CDIS

The dataset includes camouflaged images and the annotations under COCO JSON format.

Source: The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentation

Dataset Variants

CAMO-FS

Papers1

The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentation

This work proposes FS-CDIS, a framework to efficiently detect and segment camouflaged instances via two loss functions contributing to the training process, and achieves state-of-the-art performance on the newly collected dataset.

Tasks

EDIT

Few-Shot Object Detection Few-shot Instance Segmentation

Similar Datasets

MNIST

CelebA

GLUE

Statistics

Papers

1

Tasks

32

Introduced

2024

License

Apache-2.0 license