AI Paper Atlas

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

Self Paced Deep Learning for Weakly Supervised Object Detection

Enver Sangineto, Moin Nabi, Dubravko R. Culibrk, Nicu Sebe

TPAMI 2018 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised detection · 117 citations (OpenAlex)

Read the paperCheck 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 self-paced phase (SP) after InitFast-RCNN detector (h^I init) · Pascal VOC 2007 testmAP (%): 24.74 -> 32.1Improved
add self-paced phase (SP) after InitFast-RCNN detector (h^P init) · Pascal VOC 2007 testmAP (%): 31.93 -> 38.11Improved
use self-paced image selection instead of MIL on all images (ablation)SP training · Pascal VOC 2007 testmAP (%): 30.8 -> 38.1Improved
use self-paced image selection instead of MIL on all images (ablation)SP training · ILSVRC 2013 val2mAP (%): 8.59 -> 12.13Improved
use dynamic score selection from current network instead of static Curriculum (ablation)SP training · Pascal VOC 2007 testmAP (%): 31.3 -> 38.1Improved
add class selection (ablation)SP training · Pascal VOC 2007 testmAP (%): 36.9 -> 38.1Improved
add class selection (ablation)SP training · ILSVRC 2013 val2mAP (%): 11.97 -> 12.13Improved
use score-based class selection instead of random class selection (ablation)SP training · Pascal VOC 2007 testmAP (%): 32.7 -> 38.1Improved
use regression layer to choose latent boxes in training (ablation)SP training · Pascal VOC 2007 testmAP (%): 33.5 -> 38.1Improved
use regression layer in training and test (ablation)SP training · Pascal VOC 2007 testmAP (%): 30.7 -> 38.1Improved
use regression layer in training and test (ablation)SP training · ILSVRC 2013 val2mAP (%): 7.57 -> 12.13Improved
restrict to one box per image via inter-classifier competition instead of one per label (SIML) (ablation)SP training · Pascal VOC 2007 testmAP (%): 33.80 -> 38.11Improved

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