Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Attention-Based Multimodal Image Matching

About

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.

Aviad Moreshet, Yosi Keller• 2021

Related benchmarks

TaskDatasetResultRank
Patch MatchingVIS-NIR (test)
Field Match Rate4.22
27
Patch MatchingUBC Benchmark Liberty, Notre Dame, Yosemite
FPR95 (Train: NOT / Test: LIB)0.35
12
Patch MatchingVIS-NIR
FPR951.76
11
Patch MatchingCUHK
FPR950.05
11
Patch MatchingVeDAI--
10
Patch MatchingGAP-VIR (Ground)
FPR@951.86
9
Patch MatchingGAP-VIR Aerial
FPR@951.13
9
Patch MatchingEn et al. benchmark
VEDAI Score0.00e+0
9
Patch MatchingGAP-VIR Combined
FPR951.5
3
Showing 9 of 9 rows

Other info

Follow for update