Watercolor2k

Introduced in Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation2018

About this Dataset

Watercolor2k is a dataset used for cross-domain object detection which contains 2k watercolor images with image and instance-level annotations.

Source: Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation

Dataset Variants

Watercolor2k

Papers1

Cross-Domain Weakly-Supervised Object Detection Through Progressive Domain Adaptation

This paper proposes a two-step progressive domain adaptation technique by fine-tuning the detector on two types of artificially and automatically generated samples, and achieves an improvement of approximately 5 to 20 percentage points in terms of mean average precision (mAP) compared to the best-performing baselines.

Tasks

EDIT

Object Detection Weakly Supervised Object Detection Unsupervised Object Detection Body Detection

Similar Datasets

MNIST

CelebA

JFT-300M

Statistics

Papers

1

Tasks

0

Introduced

2018