Research Terms
The University of Central Florida invention is a highly effective generalized out-of-distribution (OOD) detection method. Highly scalable, the technology is independent of OOD datasets. Once machine learning models are in real-world applications, they tend to encounter unknown (OOD) data during inference. Detecting OOD is a crucial task in safety-critical applications to ensure the safe deployment of deep learning models. The machine learning model should only be confident about the data type that has already been seen (in-distribution or ID), reinforcing the driving principle of OOD detection.
Current technologies are not generalizable since they need a set of OOD data during training to regularize the model. In contrast, the UCF framework is independent of such regularization and is not based on any particular OOD dataset. Instead, the UCF invention uses an approach that relies on self-supervised feature learning of training samples, where the embeddings lie on a compact low-dimensional space. A fully supervised fine-tuning is then done by mapping the ID class features into 1-dimensional subspace.
Partnering Opportunity: The research team is seeking partners for licensing, research collaboration, or both.
Stage of Development: Prototype available.
RODD: A Self-Supervised Approach for Robust Out-of-Distribution Detection, IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPR'22), June 19, 20, 2022.
The University of Central Florida invention, Spectral Shift Aware Video Editing (SAVE), fine-tunes the spectral shift of the parameter space, significantly reducing the number of trainable parameters and improving computational efficiency. The UCF method includes a novel text-guided video editing framework and a spectral shift regularizer to capture motion information and preserve scene generation capability. It also incorporates frame attention for spatial and temporal consistency.
Text-to-Image (T2I) diffusion models have achieved remarkable success in synthesizing high-quality images conditioned on text prompts. Recent methods have tried to replicate the success by either training text-to-video (T2V) models on a large number of text-video pairs or adapting T2I models on text-video pairs independently. Although the latter is computationally less expensive, it still takes significant time for per-video adaptation. To address this issue, the UCF spectral-shift-aware adaptation framework enables the spectral shift of the parameter space to be fine-tuned instead of the parameters themselves.
Partnering Opportunity
The research team is seeking partners for licensing, research collaboration, or both.
Stage of Development
Prototype available.
SAVE: Spectral-Shift-Aware Adaptation of Image Diffusion Models for Text-driven Video Editing, arXiv:2305.18670 [cs.CV], submitted on 30 May 2023 (v1), last revised 1 Dec 2023 (this version, v2), https://doi.org/10.48550/arXiv.2305.18670