Image Retrieval On Roxford Medium

評価指標

mAP

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名	mAP	Paper Title
ResNet101+ArcFace GLDv2-train-clean	74.2	Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval
HesAff–rSIFT–SMK*+SP	59.8	Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking
R – [O] –SPoC	39.8	Aggregating Deep Convolutional Features for Image Retrieval
HOW	79.4	Learning and aggregating deep local descriptors for instance-level recognition
R – [O] –CroW	42.4	Cross-dimensional Weighting for Aggregated Deep Convolutional Features
FIRe	81.8	Learning Super-Features for Image Retrieval
DELF–ASMK*+SP	67.8	Large-Scale Image Retrieval with Attentive Deep Local Features
Dino	51.5	Emerging Properties in Self-Supervised Vision Transformers
DELF–HQE+SP	73.4	Large-Scale Image Retrieval with Attentive Deep Local Features
R–R-MAC	60.9	End-to-end Learning of Deep Visual Representations for Image Retrieval
HesAff–rSIFT–HQE+SP	71.3	Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking
DELG+ α QE reranking + RRT reranking	80.4	Instance-level Image Retrieval using Reranking Transformers
HesAff–rSIFT–ASMK*	60.4	Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking
HesAff–rSIFT–SMK*	59.4	Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking
Token	82.28	Learning Token-based Representation for Image Retrieval
AMES	90.7	AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-level Retrieval
HED-N-GAN	66.3	Dark Side Augmentation: Generating Diverse Night Examples for Metric Learning
HesAff–rSIFT–ASMK*+SP	60.6	Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking
HesAff–rSIFT–VLAD	33.9	Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking
R–GeM	64.7	Fine-tuning CNN Image Retrieval with No Human Annotation

0 of 23 row(s) selected.