</> Code with Papers by Syntology

Datasets › PASCAL VOC 2007

PASCAL VOC 2007

archive 2025-07-28

PASCAL VOC 2007 is a dataset for image recognition. The twenty object classes that have been selected are:

Person: person Animal: bird, cat, cow, dog, horse, sheep Vehicle: aeroplane, bicycle, boat, bus, car, motorbike, train Indoor: bottle, chair, dining table, potted plant, sofa, tv/monitor

The dataset can be used for image classification and object detection tasks.

Image Source: Object Detection and Recognition in Images

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 13 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Weakly Supervised Object Detection PASCAL VOC 2007 WeakSAM-MIST-DINO (with SAM) MAP 73.4 WeakSAM: Segment Anything Meets Weakly-supervised... hustvl/weaksam 41 Compare
Object Detection PASCAL VOC 2007 Cascade Eff-B7 NAS-FPN (Copy Paste pre-training, single-scale) MAP 89.3% Simple Copy-Paste is a Strong Data Augmentation Method... PaddlePaddle/PaddleOCR +4 30 Compare
Multi-Label Classification PASCAL VOC 2007 Q2L-CvT(ImageNet-21K pretrained, resolution 384) mAP 97.3 Query2Label: A Simple Transformer Way to Multi-Label... SlongLiu/query2labels +2 17 Compare
Object Counting Pascal VOC 2007 count-test Supervised Density Map m-reIRMSE-nz 0.61 Object Counting and Instance Segmentation with... GuoleiSun/CountSeg +1 8 Compare
Multi-label Image Recognition with Partial Labels PASCAL VOC 2007 DualCoOp+TaI-DPT Average mAP 94.8 Texts as Images in Prompt Tuning for Multi-Label Image... guozix/tai-dpt 6 Compare
Real-Time Object Detection PASCAL VOC 2007 YOLO FPS 46.0 You Only Look Once: Unified, Real-Time Object Detection AlexeyAB/darknet +143 4 Compare
Open World Object Detection PASCAL VOC 2007 ORE (MDef-DETR) Unknown Recall 50.13 Class-agnostic Object Detection with Multi-modal Transformer mmaaz60/mvits_for_class_agnostic_od 2 Compare
Robust Object Detection PASCAL VOC 2007 Faster R-CNN with Stylized Training Data mPC [AP50] 56.2 Benchmarking Robustness in Object Detection: Autonomous... bethgelab/imagecorruptions +3 2 Compare
Semantic Segmentation PASCAL VOC 2007 GALDNet Mean IoU 83 Global Aggregation then Local Distribution in Fully... lxtGH/GALD-DGCNet +1 2 Compare
Image Classification PASCAL VOC 2007 NNCLR Accuracy 83 With a Little Help from My Friends: Nearest-Neighbor... lightly-ai/lightly +3 1 Compare
Object Localization PASCAL VOC 2007 ours CorLoc 41.2 Co-localization with Category-Consistent Features and... — 1 Compare
Unsupervised Object Localization PASCAL VOC 2007 DeepCut CorLoc 69.8 DeepCut: Unsupervised Segmentation using Graph Neural... sampl-weizmann/deepcut 1 Compare
Unsupervised Semantic Segmentation with Language-image Pre-training PASCAL VOC 2007 CLIPpy ViT-B Mean IoU (val) 52.2 Perceptual Grouping in Contrastive Vision-Language Models kahnchana/clippy +1 1 Compare

Papers archive 2025-07-28

30 shown of 96 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 126. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
OmniCount: Multi-label Object Counting with Semantic-Geometric Priors 0 1 8 Mar 2024 not harvested
WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition 1 6 22 Feb 2024 not harvested
YOLO-Former: YOLO Shakes Hand With ViT 0 1 11 Jan 2024 not harvested
Inner-IoU: More Effective Intersection over Union Loss with Auxiliary Bounding Box 1 1 6 Nov 2023 not harvested
Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLO 1 1 2 Nov 2023 not harvested
GKGNet: Group K-Nearest Neighbor based Graph Convolutional Network for Multi-Label Image Recognition 1 1 28 Aug 2023 not harvested
FemtoDet: An Object Detection Baseline for Energy Versus Performance Tradeoffs 1 1 17 Jan 2023 not harvested
DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering 1 1 12 Dec 2022 ran 4 of 8 samples (4 unverified)
Texts as Images in Prompt Tuning for Multi-Label Image Recognition 1 1 23 Nov 2022 not harvested
Perceptual Grouping in Contrastive Vision-Language Models 2 1 18 Oct 2022 not harvested
DPNet: Dual-Path Network for Real-time Object Detection with Lightweight Attention 2 1 28 Sep 2022 not harvested
Combining Metric Learning and Attention Heads For Accurate and Efficient Multilabel Image Classification 1 1 14 Sep 2022 not harvested
Object Discovery via Contrastive Learning for Weakly Supervised Object Detection 1 1 16 Aug 2022 not harvested
DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations 1 1 20 Jun 2022 not harvested
Dual-Perspective Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels 1 1 26 May 2022 not harvested
Heterogeneous Semantic Transfer for Multi-label Recognition with Partial Labels 1 1 23 May 2022 not harvested
Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels 1 1 4 Mar 2022 ran 6 of 7 samples (1 unverified; 7 pointer-only for licence)
Structured Semantic Transfer for Multi-Label Recognition with Partial Labels 1 1 21 Dec 2021 not harvested
Class-agnostic Object Detection with Multi-modal Transformer 1 2 22 Nov 2021 not harvested
Transformer-based Dual Relation Graph for Multi-label Image Recognition 1 1 10 Oct 2021 ran 9 of 12 samples (3 unverified)
M3TR: Multi-modal Multi-label Recognition with Transformer 1 1 1 Oct 2021 not harvested
EEEA-Net: An Early Exit Evolutionary Neural Architecture Search 1 1 13 Aug 2021 not harvested
Query2Label: A Simple Transformer Way to Multi-Label Classification 3 3 22 Jul 2021 ran 2 of 2 samples (0 unverified)
Multi-layered Semantic Representation Network for Multi-label Image Classification 1 1 22 Jun 2021 not harvested
With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations 4 1 29 Apr 2021 ran 4 of 5 samples (1 unverified)
ImageNet-21K Pretraining for the Masses 5 1 22 Apr 2021 ran 1 of 2 samples (1 unverified)
Towards Open World Object Detection 2 1 3 Mar 2021 ran 0 of 2 samples (2 unverified)
Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation 5 1 13 Dec 2020 ran 2 of 2 samples (0 unverified)
Learning Visual Representations for Transfer Learning by Suppressing Texture 1 1 3 Nov 2020 not harvested
Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection 1 1 22 Oct 2020 ran 4 of 6 samples (2 unverified; 6 pointer-only for licence)

The full list of 96 is in the JSON twin.

Dataset loaders archive 2025-07-28

open-mmlab/mmdetectionopen-mmlab/mmdetectionpytorch
open-mmlab/mmsegmentationopen-mmlab/mmsegmentationpytorch
docs.activeloop.ai/datasets/pascal-voc-2007-datasetactiveloopai/Hubtfpytorch
www.tensorflow.org/datasets/catalog/voctensorflow/datasetstfjax

4 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

Image ClassificationObject DetectionSemantic SegmentationMulti-Label ClassificationObject LocalizationCross-Modal RetrievalWeakly Supervised Object DetectionObject CountingUnsupervised Semantic Segmentation with Language-image Pre-trainingUnsupervised Object DetectionReal-Time Object DetectionZero-Shot Object DetectionOpen World Object DetectionRobust Object DetectionUnsupervised Object LocalizationMulti-label Image Recognition with Partial Labels

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

Images

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • PASCAL VOC 2007
  • Pascal VOC 2007 count-test

2 variant names, as the archive lists them.

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