Gleo-Det: Deep Convolution Feature-Guided Detector with Local Entropy Optimization for Salient Points

TL;DR

Gleo-Det introduces a novel unsupervised feature detection method combining deep convolution features and local entropy optimization to improve repeatability and detail preservation in salient point detection.

Contribution

The paper proposes a new unsupervised feature detection approach that integrates coarse and fine constraints, uses entropy-based loss functions, and guides detection with deep convolution features.

Findings

Achieves competitive results against state-of-the-art methods

Improves repeatability and detail preservation in salient point detection

Demonstrates effectiveness of entropy-based cost functions in feature detection

Abstract

Feature detection is an important procedure for image matching, where unsupervised feature detection methods are the detection approaches that have been mostly studied recently, including the ones that are based on repeatability requirement to define loss functions, and the ones that attempt to use descriptor matching to drive the optimization of the pipelines. For the former type, mean square error (MSE) is usually used which cannot provide strong constraint for training and can make the model easy to be stuck into the collapsed solution. For the later one, due to the down sampling operation and the expansion of receptive fields, the details can be lost for local descriptors can be lost, making the constraint not fine enough. Considering the issues above, we propose to combine both ideas, which including three aspects. 1) We propose to achieve fine constraint based on the requirement of repeatability while coarse constraint with guidance of deep convolution features. 2) To address the issue that optimization with MSE is limited, entropy-based cost function is utilized, both soft cross-entropy and self-information. 3) With the guidance of convolution features, we define the cost function from both positive and negative sides. Finally, we study the effect of each modification proposed and experiments demonstrate that our method achieves competitive results over the state-of-the-art approaches.