Memory Based Online Learning of Deep Representations from Video Streams

By Federico Pernici, Federico Bartoli, Matteo Bruni, A. del Bimbo. 2017

31 citations recorded by the source corpus.

We present a novel online unsupervised method for face identity learning from video streams. The method exploits deep face descriptors together with a memory based learning mechanism that takes advantage of the temporal coherence of visual data. Specifically, we introduce a discriminative descriptor matching solution based on Reverse Nearest Neighbour and a forgetting strategy that detect redundant descriptors and discard them appropriately while time progresses. It is shown that the proposed learning procedure is asymptotically stable and can be effectively used in relevant applications like multiple face identification and tracking from unconstrained video streams. Experimental results show that the proposed method achieves comparable results in the task of multiple face tracking and better performance in face identification with offline approaches exploiting future information. Code will be publicly available.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Towards Open World Object Detection (2021, background): “[47] studies open world face identity learning while [64] proposed to use an exemplar set of seen classes to match them against a new sample, and rejects it in case of a low match with all previously known classes.”
Task-Free Continual Learning (2018, neutral): “In terms of applications, the work of Pernici et al. [26, 25] is similar to our ﬁrst application scenario.”
Continual Learning in Neural Networks (2019, result): “[115, 114] is similar to our first application scenario.”
Class-incremental Learning with Pre-allocated Fixed Classifiers (2020, background): “incremental learning of features in more realistic scenarios in which classes can be revisited [43], [44], [45], [46].”
Deep learning in video multi-object tracking: A survey (2019, methodology): “In [70], the authors reused the visual features extracted by the CNN-based detector, and the association was performed using a Reverse Nearest Neighbor technique [102].”
Regular Polytope Networks (2021, methodology): “At a high level, all these approaches can be framed as a nonparametric estimation method (like nearest neighbors) sitting on top of a high-powered parametric function (Faster R-CNN in the case of object detection [63], a face feature extractor in [60] and [61], and a SiamFC feature extractor [70] fo”