CamoNAS: Neural Architecture Search for Enhanced Camouflaged Object Detection

arXiv cs.AI Papers

Summary

Introduces CamoNAS, a frequency-aware multi-resolution Neural Architecture Search framework for camouflaged object detection, achieving state-of-the-art results on four benchmarks.

arXiv:2607.01870v1 Announce Type: new Abstract: Camouflaged Object Detection (COD) aims to locate and segment objects that blend into their surroundings, presenting challenges due to weak edge cues and ill-defined boundaries. Traditional COD models rely on hand-designed architectures and multi-scale feature fusion, which are often guided by intuition rather than systematic search. This paper introduces CamoNAS, a frequency-aware multi-resolution Neural Architecture Search (NAS) framework for COD. CamoNAS automatically searches both cell-level operations and network-level downsampling paths, forming a hierarchical search space tailored to detect camouflaged objects. Additionally, it adopts an RGB frequency dual-stream architecture, where a learnable wavelet transform complements the RGB spatial stream. CamoNAS achieves state-of-the-art performance on four COD benchmarks (CAMO, COD10K, NC4K, CHAMELEON), highlighting the effectiveness of NAS for COD. Our code is available at https://github.com/rendaweiSIMIT/CamoNAS.
Original Article
View Cached Full Text

Cached at: 07/03/26, 05:46 AM

# CamoNAS: Neural Architecture Search for Enhanced Camouflaged Object Detection
Source: [https://arxiv.org/abs/2607.01870](https://arxiv.org/abs/2607.01870)
[View PDF](https://arxiv.org/pdf/2607.01870)

> Abstract:Camouflaged Object Detection \(COD\) aims to locate and segment objects that blend into their surroundings, presenting challenges due to weak edge cues and ill\-defined boundaries\. Traditional COD models rely on hand\-designed architectures and multi\-scale feature fusion, which are often guided by intuition rather than systematic search\. This paper introduces CamoNAS, a frequency\-aware multi\-resolution Neural Architecture Search \(NAS\) framework for COD\. CamoNAS automatically searches both cell\-level operations and network\-level downsampling paths, forming a hierarchical search space tailored to detect camouflaged objects\. Additionally, it adopts an RGB frequency dual\-stream architecture, where a learnable wavelet transform complements the RGB spatial stream\. CamoNAS achieves state\-of\-the\-art performance on four COD benchmarks \(CAMO, COD10K, NC4K, CHAMELEON\), highlighting the effectiveness of NAS for COD\. Our code is available at[this https URL](https://github.com/rendaweiSIMIT/CamoNAS)\.

## Submission history

From: Dawei Ren \[[view email](https://arxiv.org/show-email/c4d619d8/2607.01870)\] **\[v1\]**Thu, 2 Jul 2026 08:25:51 UTC \(3,715 KB\)

Similar Articles

On-Device Neural Architecture Search

arXiv cs.LG

Proposes a lightweight neural architecture search performed directly on the deployment device for near-sensor computing, validated on sEMG sign language and fault diagnosis datasets, achieving improved accuracy and reduced RAM occupancy.