GreenCOD: A Green Camouflaged Object Detection Method

TL;DR

GreenCOD introduces a novel, efficient camouflaged object detection method that avoids backpropagation, leveraging gradient boosting and deep features to achieve high performance with fewer computational resources.

Contribution

It presents the first backpropagation-free camouflaged object detection approach using gradient boosting and deep features, reducing complexity and computational demands.

Findings

Achieves state-of-the-art performance without backpropagation.

Requires fewer than 20G MACs for training.

Offers a more efficient paradigm for camouflaged object detection.

Abstract

We introduce GreenCOD, a green method for detecting camouflaged objects, distinct in its avoidance of backpropagation techniques. GreenCOD leverages gradient boosting and deep features extracted from pre-trained Deep Neural Networks (DNNs). Traditional camouflaged object detection (COD) approaches often rely on complex deep neural network architectures, seeking performance improvements through backpropagation-based fine-tuning. However, such methods are typically computationally demanding and exhibit only marginal performance variations across different models. This raises the question of whether effective training can be achieved without backpropagation. Addressing this, our work proposes a new paradigm that utilizes gradient boosting for COD. This approach significantly simplifies the model design, resulting in a system that requires fewer parameters and operations and maintains high performance compared to state-of-the-art deep learning models. Remarkably, our models are trained without backpropagation and achieve the best performance with fewer than 20G Multiply-Accumulate Operations (MACs). This new, more efficient paradigm opens avenues for further exploration in green, backpropagation-free model training.