Image Retrieval On Rparis Hard

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	Repository
R–GeM	56.3	Fine-tuning CNN Image Retrieval with No Human Annotation
FIRe	70.0	Learning Super-Features for Image Retrieval
HOW	62.4	Learning and aggregating deep local descriptors for instance-level recognition
HesAff–rSIFT–VLAD	17.5	Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking
Token	78.56	Learning Token-based Representation for Image Retrieval
DELG+ α QE reranking + RRT reranking	77.7	Instance-level Image Retrieval using Reranking Transformers
HesAff–rSIFT–HQE	44.7	Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking
Hypergraph propagation	83.3	Hypergraph Propagation and Community Selection for Objects Retrieval
Dino	51.6	Emerging Properties in Self-Supervised Vision Transformers
DELF–ASMK*+SP	55.4	Large-Scale Image Retrieval with Attentive Deep Local Features
HesAff–rSIFT–SMK*+SP	31.3	Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking
R – [O] –SPoC	44.7	Aggregating Local Deep Features for Image Retrieval	-
HesAff–rSIFT–SMK*	31.2	Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking
SuperGlobal	86.7	Global Features are All You Need for Image Retrieval and Reranking
R – [O] –CroW	47.2	Cross-dimensional Weighting for Aggregated Deep Convolutional Features
R–R-MAC	59.4	Particular object retrieval with integral max-pooling of CNN activations
DELF–HQE+SP	69.3	Large-Scale Image Retrieval with Attentive Deep Local Features
HesAff–rSIFT–ASMK*	34.5	Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking
HesAff–rSIFT–ASMK*+SP	35.0	Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking
R – [O] –MAC	44.1	Particular object retrieval with integral max-pooling of CNN activations

0 of 23 row(s) selected.