paper-with-me

Object Counting 벤치마크

Object Counting on CARPK

17개 결과 · ⬇ CSV · JSON

MAE 낮을수록 좋음

2.12 40.59 79.06 117.5 156 2015-06 2026-09 Faster R-CNN (2015) — 39.88 (2015-06-04) YOLO (2016) — 156.0 (2015-06-08) One-Look Regression (2016) — 21.88 (2016-09-14) YOLO9000opt (2017) — 130.4 (2016-12-25) RetinaNet (2018) — 16.62 (2017-07-19) LPN Counting (2017) — 22.76 (2017-07-19) RetinaNet (2018) — 24.58 (2017-08-07) Soft-IoU + EM-Merger unit — 6.77 (2019-04-01) HLCNN — 2.12 (2021-07-13) SAFECount — 5.33 (2022-01-22) BMNet+ — 5.76 (2022-03-16) CounTR — 5.75 (2022-08-29) CounTX (uses arbitrary text input to specify object to count, used "the cars" for CARPK) — 8.13 (2023-06-02) VLCounter — 6.46 (2023-12-27) CLIP-LOCAR — 4.01 (2025-07-11) CountOCC — 49.89 (2025-11-16) Spatially-Aware Class-Agnostic Object Co — 6.27 (2026-07-18) Faster R-CNN (2015) — 39.88 (2015-06-04) One-Look Regression (2016) — 21.88 (2016-09-14) RetinaNet (2018) — 16.62 (2017-07-19) Soft-IoU + EM-Merger unit — 6.77 (2019-04-01) HLCNN — 2.12 (2021-07-13)
RankModel MAERMSE PaperCodeYear
1 HLCNN 2.123.02 An Accurate Car Counting in Aerial Images Based on Convolutional Neural Networks ekilic/Heatmap-Learner-CNN-for-Object-Counting 2021
2 CLIP-LOCAR 4.016.02 Car Object Counting and Position Estimation via Extension of the CLIP-EBC Framework jungseoik/CLIP-LOCAR 2025
3 SAFECount 5.337.04 Few-shot Object Counting with Similarity-Aware Feature Enhancement zhiyuanyou/SAFECount 2022
4 CounTR 5.757.45 CounTR: Transformer-based Generalised Visual Counting Verg-Avesta/CounTR 2022
5 BMNet+ 5.767.83 Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting flyinglynx/Bilinear-Matching-Network 2022
6 Spatially-Aware Class-Agnostic Object Co 자동 추출 6.27 Spatially-Aware Class-Agnostic Object Counting 2026
7 VLCounter 6.468.68 VLCounter: Text-aware Visual Representation for Zero-Shot Object Counting seunggu0305/vlcounter 2023
8 Soft-IoU + EM-Merger unit 6.778.52 Precise Detection in Densely Packed Scenes eg4000/SKU110K_CVPR19 · Media-Smart/SKU110K-DenseDet · tyomj/product_detection · +2 2019
9 CounTX (uses arbitrary text input to specify object to count, used "the cars" for CARPK) 8.1310.87 Open-world Text-specified Object Counting niki-amini-naieni/countx 2023
10 RetinaNet (2018) 16.6222.30 Drone-based Object Counting by Spatially Regularized Regional Proposal Network 2017
11 One-Look Regression (2016) 21.8836.73 A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning 2016
12 LPN Counting (2017) 22.7634.46 Drone-based Object Counting by Spatially Regularized Regional Proposal Network 2017
13 RetinaNet (2018) 24.58 Focal Loss for Dense Object Detection tensorflow/models · facebookresearch/detectron2 · open-mmlab/mmdetection · +231 2017
14 Faster R-CNN (2015) 39.8847.67 Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks facebookresearch/detectron2 · open-mmlab/mmdetection · facebookresearch/detectron · +193 2015
15 CountOCC 자동 추출 49.89 Counting Through Occlusion: Framework for Open World Amodal Counting 2025
16 YOLO9000opt (2017) 130.40172.46 YOLO9000: Better, Faster, Stronger AlexeyAB/darknet · PaddlePaddle/PaddleDetection · thtrieu/darkflow · +228 2016
17 YOLO (2016) 156.0057.55 You Only Look Once: Unified, Real-Time Object Detection AlexeyAB/darknet · PaddlePaddle/PaddleDetection · thtrieu/darkflow · +141 2015
1–17 / 17 페이지당 10 20 50 100