Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection

About

This study addresses the issue of fusing infrared and visible images that appear differently for object detection. Aiming at generating an image of high visual quality, previous approaches discover commons underlying the two modalities and fuse upon the common space either by iterative optimization or deep networks. These approaches neglect that modality differences implying the complementary information are extremely important for both fusion and subsequent detection task. This paper proposes a bilevel optimization formulation for the joint problem of fusion and detection, and then unrolls to a target-aware Dual Adversarial Learning (TarDAL) network for fusion and a commonly used detection network. The fusion network with one generator and dual discriminators seeks commons while learning from differences, which preserves structural information of targets from the infrared and textural details from the visible. Furthermore, we build a synchronized imaging system with calibrated infrared and optical sensors, and collect currently the most comprehensive benchmark covering a wide range of scenarios. Extensive experiments on several public datasets and our benchmark demonstrate that our method outputs not only visually appealing fusion but also higher detection mAP than the state-of-the-art approaches.

Jinyuan Liu, Xin Fan, Zhanbo Huang, Guanyao Wu, Risheng Liu, Wei Zhong, Zhongxuan Luo• 2022

Related benchmarks

TaskDatasetResultRank
Semantic segmentationMFNet (test)
mIoU55.73
134
Semantic segmentationFMB (test)
mIoU53.94
59
Object DetectionLLVIP
mAP5093.79
58
Object DetectionM3FD dataset
mAP@0.598.3
48
Visible-Infrared Image FusionMSRS (test)
Average Gradient (AG)1.71
43
Semantic segmentationMSRS
mIoU71.35
42
Infrared-Visible Image FusionRoadScene (test)
Average Gradient (AG)11.84
40
Object DetectionM³FD (test)
mAP@0.5 (Full)82.96
34
Object DetectionMSRS (test)
mAP@0.592.2
34
Multi-Modal Image FusionMRI-CT (test)
EN5.79
30
Showing 10 of 43 rows

Other info

Code

Follow for update