Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

CoFiNet: Unveiling Camouflaged Objects with Multi-Scale Finesse

Cunhan Guo, Heyan Huang

TL;DR

CoFiNet tackles camouflaged object detection by transitioning from global to local cues through a coarse-to-fine framework. It introduces the Multi-Scale Feature Integration (MSFI) and the Multi-Activation Selective Kernel Module (MSKM) to fuse and extract multi-scale features, paired with a dual-mask generation scheme via a Spatial Broadcast Decoder to refine fine details. Across CAMO, CHAMELEON, COD10K, and NC4K, CoFiNet achieves state-of-the-art results, supported by ablations that validate the contributions of MSFI, MSKM, and the dual-mask strategy. The work delivers a robust, scalable pipeline with practical potential for diverse applications requiring precise camouflage segmentation.

Abstract

Camouflaged Object Detection (COD) is a critical aspect of computer vision aimed at identifying concealed objects, with applications spanning military, industrial, medical and monitoring domains. To address the problem of poor detail segmentation effect, we introduce a novel method for camouflage object detection, named CoFiNet. Our approach primarily focuses on multi-scale feature fusion and extraction, with special attention to the model's segmentation effectiveness for detailed features, enhancing its ability to effectively detect camouflaged objects. CoFiNet adopts a coarse-to-fine strategy. A multi-scale feature integration module is laveraged to enhance the model's capability of fusing context feature. A multi-activation selective kernel module is leveraged to grant the model the ability to autonomously alter its receptive field, enabling it to selectively choose an appropriate receptive field for camouflaged objects of different sizes. During mask generation, we employ the dual-mask strategy for image segmentation, separating the reconstruction of coarse and fine masks, which significantly enhances the model's learning capacity for details. Comprehensive experiments were conducted on four different datasets, demonstrating that CoFiNet achieves state-of-the-art performance across all datasets. The experiment results of CoFiNet underscore its effectiveness in camouflage object detection and highlight its potential in various practical application scenarios.

CoFiNet: Unveiling Camouflaged Objects with Multi-Scale Finesse

TL;DR

CoFiNet tackles camouflaged object detection by transitioning from global to local cues through a coarse-to-fine framework. It introduces the Multi-Scale Feature Integration (MSFI) and the Multi-Activation Selective Kernel Module (MSKM) to fuse and extract multi-scale features, paired with a dual-mask generation scheme via a Spatial Broadcast Decoder to refine fine details. Across CAMO, CHAMELEON, COD10K, and NC4K, CoFiNet achieves state-of-the-art results, supported by ablations that validate the contributions of MSFI, MSKM, and the dual-mask strategy. The work delivers a robust, scalable pipeline with practical potential for diverse applications requiring precise camouflage segmentation.

Abstract

Camouflaged Object Detection (COD) is a critical aspect of computer vision aimed at identifying concealed objects, with applications spanning military, industrial, medical and monitoring domains. To address the problem of poor detail segmentation effect, we introduce a novel method for camouflage object detection, named CoFiNet. Our approach primarily focuses on multi-scale feature fusion and extraction, with special attention to the model's segmentation effectiveness for detailed features, enhancing its ability to effectively detect camouflaged objects. CoFiNet adopts a coarse-to-fine strategy. A multi-scale feature integration module is laveraged to enhance the model's capability of fusing context feature. A multi-activation selective kernel module is leveraged to grant the model the ability to autonomously alter its receptive field, enabling it to selectively choose an appropriate receptive field for camouflaged objects of different sizes. During mask generation, we employ the dual-mask strategy for image segmentation, separating the reconstruction of coarse and fine masks, which significantly enhances the model's learning capacity for details. Comprehensive experiments were conducted on four different datasets, demonstrating that CoFiNet achieves state-of-the-art performance across all datasets. The experiment results of CoFiNet underscore its effectiveness in camouflage object detection and highlight its potential in various practical application scenarios.
Paper Structure (27 sections, 9 equations, 7 figures, 2 tables, 1 algorithm)

This paper contains 27 sections, 9 equations, 7 figures, 2 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Obeject detection
  4. Generic object detection
  5. Salient object detection
  6. Camouflaged object detection
  7. Multi-scale feature fusion
  8. Methodology
  9. Overview of CoFiNet
  10. Multi-scale feature integration module
  11. Feature extraction through autonomous kernel selection
  12. Multi-activation convolution
  13. Multi-activation selective kernel module
  14. Dual-mask strategy using spatial broadcast decoder
  15. Experiments
  16. ...and 12 more sections

Figures (7)

  • Figure 1: Overview of CoFiNet, where the red arrows stand for the deep supervision.
  • Figure 2: Multi-scale feature integration module
  • Figure 3: Multi-Activation Convolution
  • Figure 4: Multi-activation Selective Kernel Module
  • Figure 5: Visual comparisons.
  • ...and 2 more figures