HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Image Retrieval On Rparis Hard

Metrics

mAP

Results

Performance results of various models on this benchmark

Paper Title
AMES89.7AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-level Retrieval
SuperGlobal86.7Global Features are All You Need for Image Retrieval and Reranking
Hypergraph propagation83.3Hypergraph Propagation and Community Selection for Objects Retrieval
Token78.56Learning Token-based Representation for Image Retrieval
DELG+ α QE reranking + RRT reranking77.7Instance-level Image Retrieval using Reranking Transformers
ResNet101+ArcFace GLDv2-train-clean70.3Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval
FIRe70.0Learning Super-Features for Image Retrieval
DELF–HQE+SP69.3Large-Scale Image Retrieval with Attentive Deep Local Features
HOW62.4Learning and aggregating deep local descriptors for instance-level recognition
R–R-MAC59.4 Particular object retrieval with integral max-pooling of CNN activations
R–GeM56.3 Fine-tuning CNN Image Retrieval with No Human Annotation
DELF–ASMK*+SP55.4 Large-Scale Image Retrieval with Attentive Deep Local Features
Dino51.6Emerging Properties in Self-Supervised Vision Transformers
R – [O] –CroW 47.2Cross-dimensional Weighting for Aggregated Deep Convolutional Features
HesAff–rSIFT–HQE+SP45.1Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking
HesAff–rSIFT–HQE44.7Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking
R – [O] –SPoC44.7Aggregating Local Deep Features for Image Retrieval
R – [O] –MAC44.1Particular object retrieval with integral max-pooling of CNN activations
HesAff–rSIFT–ASMK*+SP35.0Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking
HesAff–rSIFT–ASMK*34.5Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking
0 of 23 row(s) selected.
Image Retrieval On Rparis Hard | SOTA | HyperAI