Deep Gradient Learning for Efficient Camouflaged Object Detection

Abstract

This paper introduces DGNet, a novel deep framework that exploits object gradient supervision for camouflaged object detection (COD). It decouples the task into two connected branches, i.e., a context and a texture encoder. The essential connection is the gradient-induced transition, representing a soft grouping between context and texture features. Benefiting from the simple but efficient framework, DGNet outperforms existing state-of-the-art COD models by a large margin. Notably, our efficient version, DGNet-S, runs in real-time (80 fps) and achieves comparable results to the cutting-edge model JCSOD-CVPR${}_{21}$ with only 6.82% parameters. Application results also show that the proposed DGNet performs well in polyp segmentation, defect detection, and transparent object segmentation tasks. Codes will be made available at https://github.com/GewelsJI/DGNet.

Accepted by Machine Intelligence Research

References in corpus (7)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Anabranch Network for Camouflaged Object Segmentation
• Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration Network
• Video Polyp Segmentation: A Deep Learning Perspective
• Improving Camouflaged Object Detection with the Uncertainty of Pseudo-edge Labels

Cited by in corpus (9)

• Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applications
• Video Polyp Segmentation: A Deep Learning Perspective
• ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection
• Bilateral Reference for High-Resolution Dichotomous Image Segmentation
• Depth Awakens: A Depth-perceptual Attention Fusion Network for RGB-D Camouflaged Object Detection
• Acquiring Weak Annotations for Tumor Localization in Temporal and Volumetric Data
• Frontiers in Intelligent Colonoscopy
• Weakly Supervised Camouflaged Object Detection Based on the SAM Model and Mask Guidance
• CamoNAS: Neural Architecture Search for Enhanced Camouflaged Object Detection