Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detection

CVPR 2020 Zhongzheng RenZhiding YuXiaodong YangMing-Yu LiuYong Jae LeeAlexander G. SchwingJan Kautz

Weakly supervised learning has emerged as a compelling tool for object detection by reducing the need for strong supervision during training. However, major challenges remain: (1) differentiation of object instances can be ambiguous; (2) detectors tend to focus on discriminative parts rather than entire objects; (3) without ground truth, object proposals have to be redundant for high recalls, causing significant memory consumption... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
RESULT LEADERBOARD
Weakly Supervised Object Detection COCO test-dev wetectron(single-model, VGG16) AP50 24.8 # 1
Weakly Supervised Object Detection PASCAL VOC 2007 wetectron(single-model) MAP 54.9 # 2
Weakly Supervised Object Detection PASCAL VOC 2007 wetectron (single mode, 07+12) MAP 58.1 # 1
Weakly Supervised Object Detection PASCAL VOC 2012 test wetectron(single-model) MAP 52.1 # 1

Methods used in the Paper