Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration Network
作者：
Highlights：
• We propose a novel architecture called Edge-based Reversible Re-calibration Network (ERRNet) for camouflaged object detection. It advances the state-of-the-art performance with real-time inference speed on eight challenging datasets.
• We design an aggregation strategy, Selective Edge Aggregation (SEA), to obtain initial edge prior, which can well alleviate the “ambiguous” problem of weak boundaries.
• To model the cross-comparison stage of visual perception, we further design a multivariate calibration strategy, termed Reversible Re-calibration Unit (RRU), which re-calibrates the coarse inference map by considering diverse priors.
摘要
•We propose a novel architecture called Edge-based Reversible Re-calibration Network (ERRNet) for camouflaged object detection. It advances the state-of-the-art performance with real-time inference speed on eight challenging datasets.•We design an aggregation strategy, Selective Edge Aggregation (SEA), to obtain initial edge prior, which can well alleviate the “ambiguous” problem of weak boundaries.•To model the cross-comparison stage of visual perception, we further design a multivariate calibration strategy, termed Reversible Re-calibration Unit (RRU), which re-calibrates the coarse inference map by considering diverse priors.
论文关键词：Camouflaged Object Detection,Reversible Re-calibration Unit,Selective Edge Aggregation,NGES Priors
论文评审过程：Received 31 July 2020, Revised 25 October 2021, Accepted 31 October 2021, Available online 2 November 2021, Version of Record 14 November 2021.
论文官网地址：https://doi.org/10.1016/j.patcog.2021.108414
