Improving Re-Identification by Estimating and Utilizing Diverse Uncertainty Types for Embeddings

• Published in: Algorithms 2024-10, Vol.17 (10), p.430
• Main Authors: Eisenbach, Markus, Gebhardt, Andreas, Aganian, Dustin, Gross, Horst-Michael
• Format: Article
• Language: English
• Subjects: Computational linguistics; Computer vision; data uncertainty; Datasets; Decision making; distributional uncertainty; Embedding; Hierarchies; Identification; Image processing; Image retrieval; Language processing; Methods; model uncertainty; Natural language interfaces; Neural networks; Normal distribution; out-of-distribution; Query processing; re-identification; Uncertainty; uncertainty estimation for embedding vectors
• ISSN: 1999-4893; 1999-4893
• DOI: 10.3390/a17100430

In most re-identification approaches, embedding vectors are compared to identify the best match for a given query. However, this comparison does not take into account whether the encoded information in the embedding vectors was extracted reliably from the input images. We propose the first attempt that illustrates how all three types of uncertainty, namely model uncertainty (also known as epistemic uncertainty), data uncertainty (also known as aleatoric uncertainty), and distributional uncertainty, can be estimated for embedding vectors. We provide evidence that we do indeed estimate these types of uncertainty, and that each type has its own value for improving re-identification performance. In particular, while the few state-of-the-art approaches that employ uncertainty for re-identification during inference utilize only data uncertainty to improve single-shot re-identification performance, we demonstrate that the estimated model uncertainty vector can be utilized to modify the feature vector. We explore the best method for utilizing the estimated model uncertainty based on the Market-1501 dataset and demonstrate that we are able to further enhance the performance above the already strong baseline UAL. Additionally, we show that the estimated distributional uncertainty resembles the degree to which the current sample is out-of-distribution. To illustrate this, we divide the distractor set of the Market-1501 dataset into four classes, each representing a different degree of out-of-distribution. By computing a score based on the estimated distributional uncertainty vector, we are able to correctly order the four distractor classes and to differentiate them from an in-distribution set to a significant extent.