paper-with-me

Visual Place Recognition 벤치마크

Visual Place Recognition on Baidu Mall

8개 결과 · ⬇ CSV · JSON

Recall@1

41.62 51.31 61.01 70.71 80.4 2015-11 2026-11 NetVLAD — 53.1 (2015-11-23) DINO — 48.3 (2021-04-29) CosPlace — 41.62 (2022-04-05) MixVPR — 64.44 (2023-03-03) DINOv2 — 49.21 (2023-04-14) AnyLoc-VLAD-DINOv2 — 75.22 (2023-08-01) CLIP — 56.02 (2023-08-01) SegVLAD-PreT (M) — 80.4 (2024-09-26) NetVLAD — 53.1 (2015-11-23) MixVPR — 64.44 (2023-03-03) AnyLoc-VLAD-DINOv2 — 75.22 (2023-08-01) SegVLAD-PreT (M) — 80.4 (2024-09-26)
RankModel Recall@1 PaperCodeYear
1 SegVLAD-PreT (M) 80.4 Revisit Anything: Visual Place Recognition via Image Segment Retrieval anyloc/revisit-anything 2024
2 AnyLoc-VLAD-DINOv2 75.22 AnyLoc: Towards Universal Visual Place Recognition AnyLoc/AnyLoc 2023
3 MixVPR 64.44 MixVPR: Feature Mixing for Visual Place Recognition amaralibey/mixvpr 2023
4 CLIP 56.02 AnyLoc: Towards Universal Visual Place Recognition AnyLoc/AnyLoc 2023
5 NetVLAD 53.10 NetVLAD: CNN architecture for weakly supervised place recognition Relja/netvlad · Nanne/pytorch-NetVlad · lyakaap/NetVLAD-pytorch · +11 2015
6 DINOv2 49.21 DINOv2: Learning Robust Visual Features without Supervision huggingface/transformers · facebookresearch/dinov2 · roboflow/rf-detr · +23 2023
7 DINO 48.30 Emerging Properties in Self-Supervised Vision Transformers facebookresearch/dino · lightly-ai/lightly · facebookresearch/vissl · +29 2021
8 CosPlace 41.62 Rethinking Visual Geo-localization for Large-Scale Applications gmberton/cosplace · stschubert/vpr_tutorial 2022
1–8 / 8 페이지당 10 20 50 100