基于边缘的可逆重校准网络的快速伪装目标检测
Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration Network
AI总结：
本文提出基于边缘的可逆重校准网络ERRNet，通过选择性边缘聚合和可逆重校准单元建模视觉感知行为，在多数据集上显著超越现有基线，实现高速且稳健的伪装目标检测。
摘要：
伪装目标检测（COD）旨在检测与其周围环境具有相似模式（例如纹理、强度、颜色等）的目标，近期引起了越来越多的研究兴趣。由于伪装目标通常呈现出非常模糊的边界，如何确定目标位置及其弱边界极具挑战性，也是该任务的关键。受人类观察者发现伪装目标时的生物视觉感知过程启发，本文提出了一种新颖的基于边缘的可逆重校准网络，称为ERRNet。该模型具有两个创新设计，即选择性边缘聚合（SEA）和可逆重校准单元（RRU），旨在对视觉感知行为进行建模，并实现有效的边缘先验以及潜在伪装区域与背景之间的交叉比较。更重要的是，与现有的COD模型相比，RRU结合了具有更全面信息的多种先验。实验结果表明，ERRNet在三个COD数据集和五个医学图像分割数据集上均优于现有的前沿基线。特别是，与现有的排名第一的模型SINet相比，ERRNet将性能显著提升了约6%（平均E-measure），同时具有极高的速度（79.3 FPS），这表明ERRNet可以成为COD任务的通用且稳健的解决方案。
英文摘要：
Camouflaged Object Detection (COD) aims to detect objects with similar patterns (e.g., texture, intensity, colour, etc) to their surroundings, and recently has attracted growing research interest. As camouflaged objects often present very ambiguous boundaries, how to determine object locations as well as their weak boundaries is challenging and also the key to this task. Inspired by the biological visual perception process when a human observer discovers camouflaged objects, this paper proposes a novel edge-based reversible re-calibration network called ERRNet. Our model is characterized by two innovative designs, namely Selective Edge Aggregation (SEA) and Reversible Re-calibration Unit (RRU), which aim to model the visual perception behaviour and achieve effective edge prior and cross-comparison between potential camouflaged regions and background. More importantly, RRU incorporates diverse priors with more comprehensive information comparing to existing COD models. Experimental results show that ERRNet outperforms existing cutting-edge baselines on three COD datasets and five medical image segmentation datasets. Especially, compared with the existing top-1 model SINet, ERRNet significantly improves the performance by $\sim$6% (mean E-measure) with notably high speed (79.3 FPS), showing that ERRNet could be a general and robust solution for the COD task.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
