The Surprising Positive Knowledge Transfer in Continual 3D Object Shape Reconstruction

Abstract

Continual learning is known for suffering from catastrophic forgetting, a phenomenon where earlier learned concepts are forgotten at the expense of more recent samples. In this work, we challenge the assumption that continual learning is inevitably associated with catastrophic forgetting by presenting a set of tasks that surprisingly do not suffer from catastrophic forgetting when learned continually. We attempt to provide an insight into the property of these tasks that make them robust to catastrophic forgetting and the potential of having a proxy representation learning task for continual classification. We further introduce a novel yet simple algorithm, YASS that outperforms state-of-the-art methods in the class-incremental categorization learning task. Finally, we present DyRT, a novel tool for tracking the dynamics of representation learning in continual models. The codebase, dataset and pretrained models released with this article can be found at https://github.com/ngailapdi/CLRec.

Latent-Insensitive autoencoders for Anomaly Detection

“…The spectrum of approaches between the aforementioned two extremes is best captured by the so-called "stability-plasticity" dilemma [29]. The decision to use autoencoders as part of the proposed model is dictated by firstly, its unsupervised nature, and secondly it has been shown that autoencoders are comparatively resilient to catastrophic forgetting [45]. For CL, since the bottleneck layer is the most sensitive part of our model for a given task, we create a separate latent layer for each class and the aforementioned process is repeated.…”