<p>Generative Adversarial Networks (GANs) have consistently defined the state-of-the-art in the generative modelling of high-quality images in several applications. The images generated using GANs, however, do not lend themselves to being directly used in supervised learning tasks without first being curated through annotations. This dissertation investigates how to carry out automatic on-the-fly segmentation of GAN-generated images and how this can be applied to the problem of producing high-quality simulated data for X-ray based security screening. The research exploits the hidden layer properties of GAN models in a self-supervised learning framework for the automatic one-shot segmentation of images created by a style-based GAN. The framework consists of a novel contrastive learner that is based on a Sinkhorn distance-based clustering algorithm and that learns a compact feature space for per-pixel classification of the GAN-generated images. This facilitates faster learning of the feature vectors for one-shot segmentation and allows on-the-fly automatic annotation of the GAN images. We have tested our framework on a number of standard benchmarks (CelebA, PASCAL, LSUN) to yield a segmentation performance that not only exceeds the semi-supervised baselines by an average wIoU margin of 1.02 % but also improves the inference speeds by a factor of 4.5. This dissertation also presents BagGAN, an extension of our framework to the problem domain of X-ray based baggage screening. BagGAN produces annotated synthetic baggage X-ray scans to train machine-learning algorithms for the detection of prohibited items during security screening. We have compared the images generated by BagGAN with those created by deterministic ray-tracing models for X-ray simulation and have observed that our GAN-based baggage simulator yields a significantly improved performance in terms of image fidelity and diversity. The BagGAN framework is also tested on the PIDRay and other baggage screening benchmarks to produce segmentation results comparable to their respective baseline segmenters based on manual annotations.</p>
Identifer | oai:union.ndltd.org:purdue.edu/oai:figshare.com:article/23659029 |
Date | 11 July 2023 |
Creators | Ankit V Manerikar (16523988) |
Source Sets | Purdue University |
Detected Language | English |
Type | Text, Thesis |
Rights | CC BY 4.0 |
Relation | https://figshare.com/articles/thesis/SELF-SUPERVISED_ONE-SHOT_LEARNING_FOR_AUTOMATIC_SEGMENTATION_OF_GAN-GENERATED_IMAGES/23659029 |
Page generated in 0.0015 seconds