paper-with-me

Object Detection 벤치마크

Object Detection on PASCAL VOC 2007

151개 결과 · ⬇ CSV · JSON

MAP

0.5 22.7 44.9 67.1 89.3 2013-11 2026-09 R-CNN — 58.5 (2013-11-11) R-CNN — 58.5 (2013-11-11) R-CNN — 58.5 (2013-11-11) R-CNN — 58.5 (2013-11-11) R-CNN — 58.5 (2013-11-11) SPP(combination) — 60.9 (2014-06-18) SPP(combination) — 60.9 (2014-06-18) SPP(combination) — 60.9 (2014-06-18) SPP(combination) — 60.9 (2014-06-18) SPP(combination) — 60.9 (2014-06-18) Deformable Parts Model (DeepPyramid) — 45.2 (2014-09-18) Deformable Parts Model (DeepPyramid) — 45.2 (2014-09-18) Deformable Parts Model (DeepPyramid) — 45.2 (2014-09-18) Deformable Parts Model (DeepPyramid) — 45.2 (2014-09-18) Deformable Parts Model (DeepPyramid) — 45.2 (2014-09-18) Fast R-CNN — 70.0 (2015-04-30) Fast R-CNN — 70.0 (2015-04-30) Fast R-CNN — 70.0 (2015-04-30) Fast R-CNN — 70.0 (2015-04-30) Fast R-CNN — 70.0 (2015-04-30) YOLO — 63.4 (2015-06-08) YOLO — 63.4 (2015-06-08) YOLO — 63.4 (2015-06-08) YOLO — 63.4 (2015-06-08) YOLO — 63.4 (2015-06-08) SSD512 (07+12+COCO) — 81.6 (2015-12-08) SSD512 (07+12+COCO) — 81.6 (2015-12-08) SSD512 (07+12+COCO) — 81.6 (2015-12-08) SSD512 (07+12+COCO) — 81.6 (2015-12-08) SSD512 (07+12+COCO) — 81.6 (2015-12-08) OHEM — 78.9 (2016-04-12) OHEM — 78.9 (2016-04-12) OHEM — 78.9 (2016-04-12) OHEM — 78.9 (2016-04-12) OHEM — 78.9 (2016-04-12) subCNN — 68.5 (2016-04-16) subCNN — 68.5 (2016-04-16) subCNN — 68.5 (2016-04-16) subCNN — 68.5 (2016-04-16) subCNN — 68.5 (2016-04-16) YOLO v2 — 78.6 (2016-12-25) YOLO v2 — 78.6 (2016-12-25) YOLO v2 — 78.6 (2016-12-25) YOLO v2 — 78.6 (2016-12-25) YOLO v2 — 78.6 (2016-12-25) DeNet-101 (skip) — 77.1 (2017-03-30) DeNet-101 (skip) — 77.1 (2017-03-30) DeNet-101 (skip) — 77.1 (2017-03-30) DeNet-101 (skip) — 77.1 (2017-03-30) DeNet-101 (skip) — 77.1 (2017-03-30) FRCN — 74.2 (2017-04-11) FRCN — 74.2 (2017-04-11) FRCN — 74.2 (2017-04-11) FRCN — 74.2 (2017-04-11) FRCN — 74.2 (2017-04-11) CoupleNet — 82.7 (2017-08-09) BlitzNet512 + seg (s8) — 81.5 (2017-08-09) CoupleNet — 82.7 (2017-08-09) BlitzNet512 + seg (s8) — 81.5 (2017-08-09) CoupleNet — 82.7 (2017-08-09) BlitzNet512 + seg (s8) — 81.5 (2017-08-09) CoupleNet — 82.7 (2017-08-09) BlitzNet512 + seg (s8) — 81.5 (2017-08-09) CoupleNet — 82.7 (2017-08-09) BlitzNet512 + seg (s8) — 81.5 (2017-08-09) I+ORE — 76.2 (2017-08-16) I+ORE — 76.2 (2017-08-16) I+ORE — 76.2 (2017-08-16) I+ORE — 76.2 (2017-08-16) I+ORE — 76.2 (2017-08-16) VGG-16 + KL Loss + var voting + soft-NMS — 71.6 (2018-09-23) VGG-16 + KL Loss + var voting + soft-NMS — 71.6 (2018-09-23) VGG-16 + KL Loss + var voting + soft-NMS — 71.6 (2018-09-23) VGG-16 + KL Loss + var voting + soft-NMS — 71.6 (2018-09-23) VGG-16 + KL Loss + var voting + soft-NMS — 71.6 (2018-09-23) ThunderNet SNet535 Backbone — 78.6 (2019-03-28) ThunderNet SNet535 Backbone — 78.6 (2019-03-28) ThunderNet SNet535 Backbone — 78.6 (2019-03-28) ThunderNet SNet535 Backbone — 78.6 (2019-03-28) ThunderNet SNet535 Backbone — 78.6 (2019-03-28) CenterNet(DLA34, Flip, 512x512) — 80.7 (2019-04-16) CenterNet(DLA34, Flip, 512x512) — 80.7 (2019-04-16) CenterNet(DLA34, Flip, 512x512) — 80.7 (2019-04-16) CenterNet(DLA34, Flip, 512x512) — 80.7 (2019-04-16) CenterNet(DLA34, Flip, 512x512) — 80.7 (2019-04-16) HSD (VGG16, 512x512, single-scale test) — 83.0 (2019-10-01) HSD (VGG16, 320x320, single-scale test) — 81.7 (2019-10-01) HSD (VGG16, 512x512, single-scale test) — 83.0 (2019-10-01) HSD (VGG16, 320x320, single-scale test) — 81.7 (2019-10-01) HSD (VGG16, 512x512, single-scale test) — 83.0 (2019-10-01) HSD (VGG16, 320x320, single-scale test) — 81.7 (2019-10-01) HSD (VGG16, 512x512, single-scale test) — 83.0 (2019-10-01) HSD (VGG16, 320x320, single-scale test) — 81.7 (2019-10-01) HSD (VGG16, 512x512, single-scale test) — 83.0 (2019-10-01) HSD (VGG16, 320x320, single-scale test) — 81.7 (2019-10-01) PS-KD (ResNet-152, CutMix) — 79.7 (2020-06-22) PS-KD (ResNet-152, CutMix) — 79.7 (2020-06-22) PS-KD (ResNet-152, CutMix) — 79.7 (2020-06-22) PS-KD (ResNet-152, CutMix) — 79.7 (2020-06-22) PS-KD (ResNet-152, CutMix) — 79.7 (2020-06-22) Localize — 81.5 (2020-09-29) Localize — 81.5 (2020-09-29) Localize — 81.5 (2020-09-29) Localize — 81.5 (2020-09-29) Localize — 81.5 (2020-09-29) Perona Malik (Perona and Malik, 1990) — 74.37 (2020-11-03) Perona Malik (Perona and Malik, 1990) — 74.37 (2020-11-03) Perona Malik (Perona and Malik, 1990) — 74.37 (2020-11-03) Perona Malik (Perona and Malik, 1990) — 74.37 (2020-11-03) Perona Malik (Perona and Malik, 1990) — 74.37 (2020-11-03) Cascade Eff-B7 NAS-FPN (Copy Paste pre-training, single-scale) — 89.3 (2020-12-13) Cascade Eff-B7 NAS-FPN (Copy Paste pre-training, single-scale) — 89.3 (2020-12-13) Cascade Eff-B7 NAS-FPN (Copy Paste pre-training, single-scale) — 89.3 (2020-12-13) Cascade Eff-B7 NAS-FPN (Copy Paste pre-training, single-scale) — 89.3 (2020-12-13) Cascade Eff-B7 NAS-FPN (Copy Paste pre-training, single-scale) — 89.3 (2020-12-13) EEEA-Net-C2 (YOLOv4) — 81.8 (2021-08-13) EEEA-Net-C2 (YOLOv4) — 81.8 (2021-08-13) EEEA-Net-C2 (YOLOv4) — 81.8 (2021-08-13) EEEA-Net-C2 (YOLOv4) — 81.8 (2021-08-13) EEEA-Net-C2 (YOLOv4) — 81.8 (2021-08-13) DETReg (MDef-DETR) — 84.16 (2021-11-22) DETReg (MDef-DETR) — 84.16 (2021-11-22) DETReg (MDef-DETR) — 84.16 (2021-11-22) DETReg (MDef-DETR) — 84.16 (2021-11-22) DETReg (MDef-DETR) — 84.16 (2021-11-22) DPNet — 79.2 (2022-09-28) DPNet — 79.2 (2022-09-28) DPNet — 79.2 (2022-09-28) DPNet — 79.2 (2022-09-28) DPNet — 79.2 (2022-09-28) FemotoDet — 22.9 (2023-01-17) FemotoDet — 22.9 (2023-01-17) FemotoDet — 22.9 (2023-01-17) FemotoDet — 22.9 (2023-01-17) FemotoDet — 22.9 (2023-01-17) TinyissimoYOLO-v8 — 42.3 (2023-11-02) TinyissimoYOLO-v8 — 42.3 (2023-11-02) TinyissimoYOLO-v8 — 42.3 (2023-11-02) TinyissimoYOLO-v8 — 42.3 (2023-11-02) TinyissimoYOLO-v8 — 42.3 (2023-11-02) YOLO-Former — 86.01 (2024-01-11) YOLO-Former — 86.01 (2024-01-11) YOLO-Former — 86.01 (2024-01-11) YOLO-Former — 86.01 (2024-01-11) YOLO-Former — 86.01 (2024-01-11) Cascade — 0.5 (2025-11-11) R-CNN — 58.5 (2013-11-11) SPP(combination) — 60.9 (2014-06-18) Fast R-CNN — 70.0 (2015-04-30) SSD512 (07+12+COCO) — 81.6 (2015-12-08) CoupleNet — 82.7 (2017-08-09) HSD (VGG16, 512x512, single-scale test) — 83.0 (2019-10-01) Cascade Eff-B7 NAS-FPN (Copy Paste pre-training, single-scale) — 89.3 (2020-12-13)
RankModel MAPAP50mAP@50mAP@50-95 Extra Training Data PaperCodeYear
1 Cascade Eff-B7 NAS-FPN (Copy Paste pre-training, single-scale) 89.3% Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation PaddlePaddle/PaddleOCR · open-mmlab/mmdetection · tensorflow/tpu · +2 2020
2 YOLO-Former 86.01% YOLO-Former: YOLO Shakes Hand With ViT 2024
3 DETReg (MDef-DETR) 84.16%84.16 Class-agnostic Object Detection with Multi-modal Transformer mmaaz60/mvits_for_class_agnostic_od 2021
4 HSD (VGG16, 512x512, single-scale test) 83.0% Hierarchical Shot Detector JialeCao001/HSD 2019
5 CoupleNet 82.7% CoupleNet: Coupling Global Structure with Local Parts for Object Detection princewang1994/R-FCN.pytorch · tshizys/CoupleNet · princewang1994/RFCN_CoupleNet.pytorch 2017
6 EEEA-Net-C2 (YOLOv4) 81.8% EEEA-Net: An Early Exit Evolutionary Neural Architecture Search chakkritte/eeea-net 2021
7 HSD (VGG16, 320x320, single-scale test) 81.7% Hierarchical Shot Detector JialeCao001/HSD 2019
8 SSD512 (07+12+COCO) 81.6% SSD: Single Shot MultiBox Detector open-mmlab/mmdetection · serengil/deepface · pytorch/vision · +218 2015
9 BlitzNet512 + seg (s8) 81.5% BlitzNet: A Real-Time Deep Network for Scene Understanding dvornikita/blitznet · ShunyuYao/blitznet_instance_segment 2017
9 Localize 81.5% Localize to Classify and Classify to Localize: Mutual Guidance in Object Detection ZHANGHeng19931123/MutualGuide 2020
11 CenterNet(DLA34, Flip, 512x512) 80.7% Objects as Points tensorflow/models · open-mmlab/mmdetection · PaddlePaddle/PaddleDetection · +73 2019
12 PS-KD (ResNet-152, CutMix) 79.7% Self-Knowledge Distillation with Progressive Refinement of Targets lgcnsai/ps-kd-pytorch 2020
13 DPNet 79.2% DPNet: Dual-Path Network for Real-time Object Detection with Lightweight Attention huiminshii/dpnet · MS-Mind/MS-Code-02 2022
14 OHEM 78.9% Training Region-based Object Detectors with Online Hard Example Mining abhi2610/ohem · tkuanlun350/Kaggle_Ship_Detection_2018 · Bennie-Han/Image-augementation-pytorch · +2 2016
15 YOLO v2 78.6% YOLO9000: Better, Faster, Stronger AlexeyAB/darknet · PaddlePaddle/PaddleDetection · thtrieu/darkflow · +228 2016
15 ThunderNet SNet535 Backbone 78.6% ThunderNet: Towards Real-time Generic Object Detection ouyanghuiyu/Thundernet_Pytorch · qinzheng93/thundernet · saswat0/Thundernet-Object-Detection 2019
17 DeNet-101 (skip) 77.1% DeNet: Scalable Real-time Object Detection with Directed Sparse Sampling lachlants/denet 2017
18 I+ORE 76.2% Random Erasing Data Augmentation rwightman/pytorch-image-models · pytorch/vision · albumentations-team/albumentations · +15 2017
19 Perona Malik (Perona and Malik, 1990) 74.37% Learning Visual Representations for Transfer Learning by Suppressing Texture HaohanWang/ImageNet-Sketch 2020
20 FRCN 74.2% A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection xiaolonw/adversarial-frcnn · HusterRC/adversarial-frcnn-master · busyboxs/Some-resources-useful-for-me · +1 2017
1–20 / 151 다음 → 페이지당 10 20 50 100