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 an attention-based approach for multimodal image patch matching using a Transformer encoder attending to the feature maps of a multiscale Siamese CNN. Our encoder is shown to efficiently aggregate multiscale image embeddings while emphasizing task-specific appearance-invariant image cues. We also introduce an attention-residual architecture, using a residual connection bypassing the encoder. This additional learning signal facilitates end-to-end training from scratch. Our approach is experimentally shown to achieve new state-of-the-art accuracy on both multimodal and single modality benchmarks, illustrating its general applicability. To the best of our knowledge, this is the first successful implementation of the Transformer encoder architecture to the multimodal image patch matching task.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2103.11247")
get_code_for_paper("2103.11247")
have("2103.11247")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2103.11247.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2103.11247)
Connect an agent — have() is free.