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

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

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Repositories linked to this paper

dlut-dimt/tardal — marked official in Papers with Code; named in the paper
JinyuanLiu-CV/TarDAL
ultralytics/YOLOv5

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Average Runtime (s) 0.05 0.74 0.76 0.78 0.80 0.82 0.84 0.10 0.15 0.20 0.25 M FD Pixel Distribution Figure 1. From the left to right: Detection accuracy and computational comparisons with the state-of-the-art, the scenario and pixel distributions of our benchmark M 3 FD. Ours outperforms all counterparts with higher detection rates, lower average runtime, and fewer training parameters. M 3 FD covers comprehensive scenarios with a wide range of pixel variations especially on both modalities.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.16220")
get_code_for_paper("2203.16220")
have("2203.16220")

Connect an agent — have() is free.