AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Exploring Bottom-Up and Top-Down Cues With Attentive Learning for Webly Supervised Object Detection

Zhonghua Wu, Qingyi Tao, Guosheng Lin, Jianfei Cai

CVPR 2020 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised detection · 14 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add attentive classification loss to weight region classification by class-specific attention (ablation)WebSOD · PASCAL VOC 2007, novel/base split 1, novel classesmAP: 58.3 -> 60.5Improved
add attentive classification loss to weight region classification by class-specific attention (ablation)WebSOD · PASCAL VOC 2007, novel/base split 2, novel classesmAP: 52.2 -> 53.0Improved
add attentive classification loss to weight region classification by class-specific attention (ablation)WebSOD · PASCAL VOC 2007, novel/base split 3, novel classesmAP: 58.0 -> 58.9Improved
add residual feature refinement for domain adaptation (ablation)WebSOD + ACL · PASCAL VOC 2007, novel/base split 1, novel classesmAP: 60.5 -> 61.8Improved
add residual feature refinement for domain adaptation (ablation)WebSOD + ACL · PASCAL VOC 2007, novel/base split 2, novel classesmAP: 53.0 -> 54.0Improved
add residual feature refinement for domain adaptation (ablation)WebSOD + ACL · PASCAL VOC 2007, novel/base split 3, novel classesmAP: 58.9 -> 60.0Improved
add residual feature refinement for domain adaptation (ablation)WebSOD + ACL · PASCAL VOC 2007, base classesmAP: 69.0 -> 70.7; 71.2 -> 72.5; 67.3 -> 70.5Improved
fine-tune all feature-learning layers while fixing the web detector, instead of using RFR (ablation)WebSOD + ACL · PASCAL VOC 2007, novel/base split 1, novel classesmAP: 60.5 -> 58.2Hurt
fine-tune all feature-learning layers while fixing the web detector, instead of using RFR (ablation)WebSOD + ACL · PASCAL VOC 2007, novel/base split 1, base classesmAP: 69.0 -> 74.6Improved
use bottom-up regions from a base-class detector to train on web imagesWebSOD · PASCAL VOC 2007, novel/base split 1, novel classesmAP: 32.4 -> 58.3Improved
use WebSOD instead of ZAODNovel-class detection · PASCAL VOC 2007, novel/base split 1, novel classesmAP: 32.4 -> 61.8Improved
use WebSOD instead of Uijlings et al.ILSVRC13 val2, 100 novel classes · ILSVRC13 val2, 100 novel classes, IoU > 0.5mAP: 36.9 -> 37.1Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy