Contrastive Learning for Image Complexity Representation

TL;DR

This paper introduces CLIC, a contrastive learning framework using MoCo v2 and RCM for representing image complexity, achieving performance comparable to supervised methods without manual annotations.

Contribution

The paper proposes a novel contrastive learning approach with RCM for image complexity representation, reducing annotation costs and improving task performance.

Findings

CLIC performs comparably to supervised methods.

RCM increases data diversity without extra data.

CLIC enhances computer vision task performance.

Abstract

Quantifying and evaluating image complexity can be instrumental in enhancing the performance of various computer vision tasks. Supervised learning can effectively learn image complexity features from well-annotated datasets. However, creating such datasets requires expensive manual annotation costs. The models may learn human subjective biases from it. In this work, we introduce the MoCo v2 framework. We utilize contrastive learning to represent image complexity, named CLIC (Contrastive Learning for Image Complexity). We find that there are complexity differences between different local regions of an image, and propose Random Crop and Mix (RCM), which can produce positive samples consisting of multi-scale local crops. RCM can also expand the train set and increase data diversity without introducing additional data. We conduct extensive experiments with CLIC, comparing it with both unsupervised and supervised methods. The results demonstrate that the performance of CLIC is comparable to that of state-of-the-art supervised methods. In addition, we establish the pipelines that can apply CLIC to computer vision tasks to effectively improve their performance.