Improving Low-Light Image Recognition Performance Based on Image-adaptive Learnable Module

2024-01-12

VISIGRAPP : VISAPP

AI Summary

To address the significant degradation in recognition accuracy under low-light conditions, this paper proposes a plug-and-play, image-adaptive, learnable front-end filter that enhances dark-image recognition without fine-tuning or retraining downstream recognition models. The method introduces differentiable, end-to-end optimized image enhancement via a lightweight, model-agnostic module. Its key contributions are: (1) the first image-adaptive hyperparameter prediction mechanism, enabling dynamic, differentiable regression of enhancement parameters; and (2) zero-shot transferability to arbitrary recognition architectures—including CNNs (e.g., ResNet) and vision transformers (ViT)—without architectural modification. Evaluated on multiple low-light benchmark datasets, the approach achieves an average recognition accuracy improvement of 5.2% while incurring less than 3% additional inference latency.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

In recent years, significant progress has been made in image recognition technology based on deep neural networks. However, improving recognition performance under low-light conditions remains a significant challenge. This study addresses the enhancement of recognition model performance in low-light conditions. We propose an image-adaptive learnable module which apply appropriate image processing on input images and a hyperparameter predictor to forecast optimal parameters used in the module. Our proposed approach allows for the enhancement of recognition performance under low-light conditions by easily integrating as a front-end filter without the need to retrain existing recognition models designed for low-light conditions. Through experiments, our proposed method demonstrates its contribution to enhancing image recognition performance under low-light conditions.

Problem

• Low Light Image Recognition
• Accuracy Improvement
• Image Processing

Innovation

• Smart Module
• Automatic Image Adjustment
• Enhanced Recognition in Low Light