Dark Side Augmentation: Generating Diverse Night Examples For Metric Learning

Abstract

Image retrieval methods based on CNN descriptors rely on metric learning from a large number of diverse examples of positive and negative image pairs. Domains, such as night-time images, with limited availability and variability of training data suffer from poor retrieval performance even with methods performing well on standard benchmarks. We propose to train a GAN-based synthetic-image generator, translating available day-time image examples into night images. Such a generator is used in metric learning as a form of augmentation, supplying training data to the scarce domain. Various types of generators are evaluated and analyzed. We contribute with a novel light-weight GAN architecture that enforces the consistency between the original and translated image through edge consistency. The proposed architecture also allows a simultaneous training of an edge detector that operates on both night and day images. To further increase the variability in the training examples and to maximize th

Stats

• citations6
• S2 citations—
• github stars9
• HF likes0
• heat score8.34
• arxiv keymohwald2023dark

Related papers

• Learning To Generate Novel Classes For Deep Metric Learning (2022)0.00
• Drop The GAN: In Defense Of Patches Nearest Neighbors As Single Image Generative Models (2021)12.87
• No Fear Of The Dark: Image Retrieval Under Varying Illumination Conditions (2019)10.74
• DML-GANR: Deep Metric Learning With Generative Adversarial Network Regularization For High Spatial Resolution Remote Sensing Image Retrieval (2020)10.48
• Embedding Expansion: Augmentation In Embedding Space For Deep Metric Learning (2020)12.02
• Inverting The Generator Of A Generative Adversarial Network (2016)17.61
• Bingan: Learning Compact Binary Descriptors With A Regularized GAN (2018)0.00
• Paired Cross-modal Data Augmentation For Fine-grained Image-to-text Retrieval (2022)8.09