An official website of the United States government
Limited data availability is a challenging problem in the latent fingerprint domain. Synthetically generated fingerprints are vital for training data-hungry neural network-based algorithms. Conventional methods distort clean fingerprints to generate synthetic latent fingerprints. We propose a simple and effective approach using style transfer and image blending to synthesize realistic latent fingerprints. Our evaluation criteria and experiments demonstrate that the generated synthetic latent fingerprints preserve the identity information from the input contact- based fingerprints while possessing similar characteristics as real latent fingerprints. Additionally, we show that the generated fingerprints exhibit several qualities and styles, suggesting that the proposed method can generate multiple samples from a single fingerprint.
more »
« less
Optimizing Representations of Multiple Simultaneous Attributes for Gait Generation Using Deep Learning
Rich variations in gait are generated according to several attributes of the individual and environment, such as age, athleticism, terrain, speed, personal “style”, mood, etc. The effects of these attributes can be hard to quantify explicitly, but relatively straightforward to sample. We seek to generate gait that expresses these attributes, creating synthetic gait samples that exemplify a custom mix of attributes. This is difficult to perform manually, and generally restricted to simple, human-interpretable and handcrafted rules. In this manuscript, we present neural network architectures to learn representations of hard to quantify attributes from data, and generate gait trajectories by composing multiple desirable attributes. We demonstrate this method for the two most commonly desired attribute classes: individual style and walking speed. We show that two methods, cost function design and latent space regularization, can be used individually or combined. We also show two uses of machine learning classifiers that recognize individuals and speeds. Firstly, they can be used as quantitative measures of success; if a synthetic gait fools a classifier, then it is considered to be a good example of that class. Secondly, we show that classifiers can be used in the latent space regularizations and cost functions to improve training beyond a typical squared-error cost.
more »
« less
- Award ID(s):
- 2024446
- PAR ID:
- 10473032
- Publisher / Repository:
- IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Date Published:
- Journal Name:
- IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Volume:
- 31
- ISSN:
- 1534-4320
- Page Range / eLocation ID:
- 2296 to 2305
- Subject(s) / Keyword(s):
- Representation learning, autoencoders, generative models, multi-task learning, style transfer, assistive devices, exoskeletons, personalization.
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The gaits of locomoting systems are typically designed to maximize some sort of efficiency, such as cost of transport or speed. Equally important is the ability to modulate such a gait to effect turning maneuvers. For drag-dominated systems, geometric mechanics provides an elegant and practical framework for both ends—gait design and gait modulation. Within this framework, “constraint curvature” maps can be used to approximate the net displacement of robotic systems over cyclic gaits. Gait optimization is made possible under a previously reported “soap-bubble” algorithm. In this work, we propose both local and global gait morphing algorithms to modify a nominal gait to provide single-parameter steering control. Using a simplified swimmer, we numerically compare the two approaches and show that for modest turns, the local approach, while suboptimal, nevertheless proves effective for steering control. A potential advantage of the local approach is that it can be readily applied to soft robots or other systems where local approximations to the constraint curvature can be garnered from data, but for which obtaining an exact global model is infeasible.more » « less
-
Tortoises are famed for their slow locomotion, which is in part related to their herbivorous diet and the constraints imposed by their protective shells. For most animals, the metabolic cost of transport (CoT) is close to the value predicted for their body mass. Testudines appear to be an exception to this rule, as previous studies indicate that, for their body mass, they are economical walkers. The metabolic efficiency of their terrestrial locomotion is explainable by their walking gait biomechanics and the specialisation of their limb muscle physiology, which embodies a predominance of energy-efficient slow-twitch type I muscle fibres. However, there are only two published experimental reports of the energetics of locomotion in tortoises, and these data show high variability. Here, Mediterranean spur-thighed tortoises (Testudo graeca) were trained to walk on a treadmill. Open-flow respirometry and high-speed filming were simultaneously used to measure the metabolic cost of transport and to quantify limb kinematics, respectively. Our data support the low cost of transport previously reported and demonstrate a novel curvilinear relationship to speed in Testudines, suggesting tortoises have an energetically optimal speed range over which they can move in order to minimise the metabolic cost of transport.more » « less
-
Designing molecules that must satisfy multiple, often conflicting, objectives is a central challenge in molecular discovery. The enormous size of the chemical space and the cost of high-fidelity simulations have driven the development of machine learning-guided strategies for accelerating design with limited data. Among these, Bayesian optimization (BO) offers a principled framework for sample-efficient search, while generative models provide a mechanism to propose novel, diverse candidates beyond fixed libraries. However, existing methods that couple the two often rely on continuous latent spaces, which introduce both architectural entanglement and scalability challenges. This work introduces an alternative, modular “generate-then-optimize” framework for de novo multiobjective molecular design/discovery. At each iteration, a generative model is used to construct a large, diverse pool of candidate molecules, after which a novel acquisition function, qPMHI (multipoint Probability of Maximum Hypervolume Improvement), is used to optimally select a batch of candidates most likely to induce the largest Pareto front expansion. The key insight is that qPMHI decomposes additively, enabling exact, scalable batch selection via only a simple ranking of probabilities that can be easily estimated with Monte Carlo sampling. We benchmark the framework against state-of-the-art latent-space and discrete molecular optimization methods, demonstrating significant improvements across synthetic benchmarks and application-driven tasks. Specifically, in a case study related to sustainable energy storage, we show that our approach quickly uncovers novel, diverse, and high-performing organic (quinone-based) cathode materials for aqueous redox flow battery applications.more » « less
-
Unsupervised domain adaptation for semantic segmentation has been intensively studied due to the low cost of the pixel-level annotation for synthetic data. The most common approaches try to generate images or features mimicking the distribution in the target domain while preserving the semantic contents in the source domain so that a model can be trained with annotations from the latter. However, such methods highly rely on an image translator or feature extractor trained in an elaborated mechanism including adversarial training, which brings in extra complexity and instability in the adaptation process. Furthermore, these methods mainly focus on taking advantage of the labeled source dataset, leaving the unlabeled target dataset not fully utilized. In this paper, we propose a bidirectional style-induced domain adaptation method, called BiSIDA, that employs consistency regularization to efficiently exploit information from the unlabeled target domain dataset, requiring only a simple neural style transfer model. BiSIDA aligns domains by not only transferring source images into the style of target images but also transferring target images into the style of source images to perform high-dimensional perturbation on the unlabeled target images, which is crucial to the success in applying consistency regularization in segmentation tasks. Extensive experiments show that our BiSIDA achieves new state-of-the-art on two commonly-used synthetic-to-real domain adaptation benchmarks: GTA5-to-CityScapes and SYNTHIA-to-CityScapes. Code and pretrained style transfer model are available at: https://github.com/wangkaihong/BiSIDA.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1109/TNSRE.2023.3273599
