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

CVPR 2018 Naoto InoueRyosuke FurutaToshihiko YamasakiKiyoharu Aizawa

Can we detect common objects in a variety of image domains without instance-level annotations? In this paper, we present a framework for a novel task, cross-domain weakly supervised object detection, which addresses this question... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
RESULT LEADERBOARD
Weakly Supervised Object Detection Clipart1k DT+PL MAP 46.0 # 1
Weakly Supervised Object Detection Comic2k DT+PL MAP 37.2 # 1
Weakly Supervised Object Detection Watercolor2k DT+PL MAP 54.3 # 3

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet