AI Paper Atlas

Research map / Benchmarks / PASCAL VOC 2012 trainval

PASCAL VOC 2012 trainval leaderboard

13 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on PASCAL VOC 2012 trainval. Best CorLoc: 73.7 (LBBA (Ours, multi-scale), ICCV 2021).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

PASCAL VOC 2012 trainval · CorLoc

13 papers, each with its best reported number for its own method; higher is better.

#CorLoc ↑MethodPaperTopic
173.7LBBA (Ours, multi-scale)Boosting Weakly Supervised Object Detection via Learning Bounding Box Adjusters
ICCV 2021 · Table 2
Weakly supervised detection and segmentation
272.6CBL (Ours)
VGG16
Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection
ICCV 2023 · Appendix VOC 2012 table
Weakly supervised detection and segmentation
371.9GradingNet-C-MIL
C-MIL
GradingNet: Towards Providing Reliable Supervisions for Weakly Supervised Object Detection by Grading the Box Candidates
AAAI 2021 · Table 3
Weakly supervised detection and segmentation
471.9WSOD2
VGG16
WSOD2: Learning Bottom-Up and Top-Down Objectness Distillation for Weakly-Supervised Object Detection
ICCV 2019 · Table 4
Weakly supervised detection and segmentation
571.2C-MIDN
VGG16
C-MIDN: Coupled Multiple Instance Detection Network With Segmentation Guidance for Weakly Supervised Object Detection
ICCV 2019 · Table 3
Weakly supervised detection and segmentation
670.2Pred Net (Ens)
VGG11, VGG13, VGG16
Dissimilarity Coefficient Based Weakly Supervised Object Detection
CVPR 2019 · Table: VOC 2012 CorLoc
Weakly supervised detection and segmentation
769.6IM-CFB
VGG16
Instance Mining with Class Feature Banks for Weakly Supervised Object Detection
AAAI 2021 · Table 3
Weakly supervised detection and segmentation
869.5WS-JDS FRCNN
Fast-RCNN
Cyclic Guidance for Weakly Supervised Joint Detection and Segmentation
CVPR 2019 · Table 4
Weakly supervised detection and segmentation
969.4WSD+PGE+PGA+FSD2
VGG16
W2F: A Weakly-Supervised to Fully-Supervised Framework for Object Detection
CVPR 2018 · Table 4
Weakly supervised detection and segmentation
1069.2SLV(VGG)
VGG16
SLV: Spatial Likelihood Voting for Weakly Supervised Object Detection
CVPR 2020 · Table: PASCAL VOC 2012 results
Weakly supervised detection and segmentation
3 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.