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

TS-Net: Combining modality specific and common features for multimodal patch matching

About

Multimodal patch matching addresses the problem of finding the correspondences between image patches from two different modalities, e.g. RGB vs sketch or RGB vs near-infrared. The comparison of patches of different modalities can be done by discovering the information common to both modalities (Siamese like approaches) or the modality-specific information (Pseudo-Siamese like approaches). We observed that none of these two scenarios is optimal. This motivates us to propose a three-stream architecture, dubbed as TS-Net, combining the benefits of the two. In addition, we show that adding extra constraints in the intermediate layers of such networks further boosts the performance. Experimentations on three multimodal datasets show significant performance gains in comparison with Siamese and Pseudo-Siamese networks.

Sovann En, Alexis Lechervy, Fr\'ed\'eric Jurie• 2018

Related benchmarks

TaskDatasetResultRank
Patch MatchingVIS-NIR (test)
Field Match Rate25.45
27
Patch MatchingVIS-NIR
FPR9511.86
11
Patch MatchingCUHK
FPR952.77
11
Patch MatchingVeDAI
FPR@950.45
10
Showing 4 of 4 rows

Other info

Follow for update