Browse › Computer Vision › Object Detection › PASCAL VOC 2007

Object Detection archive 2025-07-28

PASCAL VOC 2007 Benchmark (Object Detection)

30 rows 29 with code listed 5 metrics Dataset page

Over time archive 2025-07-28

The chart needs JavaScript; the table below carries every value.

Direction inferred from the metric name, not from the archive: MAP (higher is better), mAP@50 (higher is better), mAP@50-95 (higher is better), box AP (higher is better). Not inferred (points only, no best-so-far line): AP50. Points are placed at the row's paper date; 30 of 30 rows carry one.

Results archive 2025-07-28

Archive rows end at the archive snapshot, 2025-07-28: no result published after that date is in this table. Rank is the archive's row order at that snapshot; not re-ranked here. Metric values are the archive's strings. Column headers sort the table in your browser; each row keeps its archive rank.

Paper Code Ran Syntology Report
1 Cascade Eff-B7 NAS-FPN (Copy Paste pre-training, single-scale) 89.3% – Paper Code 2020 2 of 2 ran · 0 unverified report
2 YOLO-Former 86.01% ✓ Paper – 2024 no code linked report
3 DETReg (MDef-DETR) 84.16%84.16 ✓ Paper Code 2021 linked, not harvested report
4 HSD (VGG16, 512x512, single-scale test) 83.0% – Paper Code 2019 linked, not harvested report
5 CoupleNet 82.7% – Paper Code 2017 linked, not harvested report
6 EEEA-Net-C2 (YOLOv4) 81.8% ✓ Paper Code 2021 linked, not harvested report
7 HSD (VGG16, 320x320, single-scale test) 81.7% – Paper Code 2019 linked, not harvested report
8 SSD512 (07+12+COCO) 81.6% ✓ Paper Code 2015 19 of 131 ran · 112 unverified report
9 BlitzNet512 + seg (s8) 81.5% – Paper Code 2017 linked, not harvested report
10 Localize 81.5% – Paper Code 2020 linked, not harvested report
11 CenterNet(DLA34, Flip, 512x512) 80.7% – Paper Code 2019 10 of 130 ran · 120 unverified report
12 PS-KD (ResNet-152, CutMix) 79.7% – Paper Code 2020 4 of 5 ran · 1 unverified report
13 DPNet 79.2% – Paper Code 2022 linked, not harvested report
14 OHEM 78.9% – Paper Code 2016 linked, not harvested report
15 YOLO v2 78.6% ✓ Paper Code 2016 16 of 60 ran · 44 unverified report
16 ThunderNet SNet535 Backbone 78.6% – Paper Code 2019 linked, not harvested report
17 DeNet-101 (skip) 77.1% – Paper Code 2017 linked, not harvested report
18 I+ORE 76.2% – Paper Code 2017 linked, not harvested report
19 Perona Malik (Perona and Malik, 1990) 74.37% – Paper Code 2020 linked, not harvested report
20 FRCN 74.2% – Paper Code 2017 linked, not harvested report
21 VGG-16 + KL Loss + var voting + soft-NMS 71.6% – Paper Code 2018 0 of 4 ran · 4 unverified report
22 Fast R-CNN 70.0% ✓ Paper Code 2015 5 of 8 ran · 3 unverified report
23 subCNN 68.5% – Paper Code 2016 linked, not harvested report
24 YOLO 63.4% ✓ Paper Code 2015 80 of 148 ran · 68 unverified report
25 SPP(combination) 60.9% – Paper Code 2014 0 of 1 ran · 1 unverified report
26 R-CNN 58.5% ✓ Paper Code 2013 1 of 17 ran · 16 unverified report
27 Deformable Parts Model (DeepPyramid) 45.2% – Paper Code 2014 linked, not harvested report
28 TinyissimoYOLO-v8 42.3% – Paper Code 2023 linked, not harvested report
29 FemotoDet 22.90%46.31 – Paper Code 2023 linked, not harvested report
30 YOLOv7+Inner-IoU 64.4438.52 ✓ Paper Code 2023 linked, not harvested report

All 30 rows shown. 30 link to a paper page on this site; 9 are marked as using additional training data in the archive. No GitHub stars are tracked; "Code" is the first repository the archive lists for the row. The archive carries no row tags, review links or community-submitted rows for this table; none are shown. archive 2025-07-28

Syntology Ran reads "N of M ran · U unverified": of the M code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and the other U = M−N are unverified (harvested, no recorded run). It counts code from repositories linked to that row's paper, not this result: the row's number was not reproduced and nothing here is a correctness claim. The other cell texts mean no graph line for the row: "linked, not harvested" (the archive links code, Syntology has not harvested it), "no code linked" (no code link in the archive), "not matched" (the row's paper URL matched no paper on this site). 10 rows have a graph line, from 10 distinct papers; 8 rows (8 papers) have at least one sample that ran. Counting each paper once: Syntology ran 137 of 506 samples; 369 unverified. Separately, 126 of those 506 are pointer-only (licence): the site points at that code rather than redistributing it, a licence property recorded for ran and unverified samples alike; each cell's tooltip carries the row's own pointer-only count. Read from the graph 2026-09-24. Per-sample status is on the paper page.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections