We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We propose a novel method of deep spatial matching (DSM) for image retrieval. Initial ranking is based on image descriptors extracted from convolutional neural network activations by global pooling, as in recent state-of-the-art work. However, the same sparse 3D activation tensor is also approximated by a collection of local features. These local features are then robustly matched to approximate the optimal alignment of the tensors. This happens without any network modification, additional layers or training. No local feature detection happens on the original image. No local feature descriptors and no visual vocabulary are needed throughout the whole process. We experimentally show that the proposed method achieves the state-of-the-art performance on standard benchmarks across different network architectures and different global pooling methods. The highest gain in performance is achieved when diffusion on the nearest-neighbor graph of global descriptors is initiated from spatially verified images.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1905.06358")
get_code_for_paper("1905.06358")
have("1905.06358")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1905.06358.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1905.06358)
Connect an agent — have() is free.