We present the details on each dataset in Table 4 .

We present the details on each dataset in Table 4 .

Catastrophic forgetting, the phenomenon of forgetting previously learned tasks when learning a new one, is a major hurdle in developing continual learning algorithms. A popular method to alleviate forgetting is to use a memory buffer, which stores a subset of previously learned task examples for use during training on new tasks. The de facto method of filling memory is by randomly selecting previous examples. However, this process could introduce outliers or noisy samples that could hurt the generalization of the model. This paper introduces Memory Outlier Elimination (MOE), a method for identifying and eliminating outliers in the memory buffer by choosing samples from label-homogeneous subpopulations. We show that a space with a high homogeneity is related to a feature space that is more representative of the class distribution. In practice, MOE removes a sample if it is surrounded by samples from different labels. We demonstrate the effectiveness of MOE on CIFAR-10, CIFAR-100, and CORe50, outperforming previous well-known memory population methods.

Self-supervised representation learning (SSRL) methods have shown great success in computer vision. In recent studies, augmentation-based contrastive learning methods have been proposed for learning representations that are invariant or equivariant to pre-defined data augmentation operations. However, invariant or equivariant features favor only specific downstream tasks depending on the augmentations chosen. They may result in poor performance when the learned representation does not match task requirements. Here, we consider an active observer that can manipulate views of an object and has knowledge of the action(s) that generated each view. We introduce Contrastive Invariant and Predictive Equivariant Representation learning (CIPER). CIPER comprises both invariant and equivariant learning objectives using one shared encoder and two different output heads on top of the encoder. One output head is a projection head with a state-of-the-art contrastive objective to encourage invariance to augmentations. The other is a prediction head estimating the augmentation parameters, capturing equivariant features. Both heads are discarded after training and only the encoder is used for downstream tasks. We evaluate our method on static image tasks and time-augmented image datasets. Our results show that CIPER outperforms a baseline contrastive method on various tasks. Interestingly, CIPER encourages the formation of hierarchically structured representations where different views of an object become systematically organized in the latent representation space.

Convolutional neural networks show remarkable results in classification but struggle with learning new things on the fly. We present a novel rehearsal-free approach, where a deep neural network is continually learning new unseen object categories without saving any data of prior sequences. Our approach is called RECALL, as the network recalls categories by calculating logits for old categories before training new ones. These are then used during training to avoid changing the old categories. For each new sequence, a new head is added to accommodate the new categories. To mitigate forgetting, we present a regularization strategy where we replace the classification with a regression. Moreover, for the known categories, we propose a Mahalanobis loss that includes the variances to account for the changing densities between known and unknown categories. Finally, we present a novel dataset for continual learning, especially suited for object recognition on a mobile robot (HOWS-CL-25), including 150,795 synthetic images of 25 household object categories. Our approach RECALL outperforms the current state of the art on CORe50 and iCIFAR-100 and reaches the best performance on HOWS-CL-25.

We study how different output layer types of a deep neural network learn and forget in continual learning settings. We describe the three factors affecting catastrophic forgetting in the output layer: (1) weights modifications, (2) interferences, and (3) projection drift. Our goal is to provide more insights into how different types of output layers can address (1) and (2). We also propose potential solutions and evaluate them on several benchmarks. We show that the best-performing output layer type depends on the data distribution drifts or the amount of data available. In particular, in some cases where a standard linear layer would fail, it is sufficient to change the parametrization and get significantly better performance while still training with SGD. Our results and analysis shed light on the dynamics of the output layer in continual learning scenarios and help select the best-suited output layer for a given scenario.

When a robot acquires new information, ideally it would immediately be capable of using that information to understand its environment. While deep neural networks are now widely used by robots for inferring semantic information, conventional neural networks suffer from catastrophic forgetting when they are incrementally updated, with new knowledge overwriting established representations. While a variety of approaches have been developed that attempt to mitigate catastrophic forgetting in the incremental batch learning scenario, in which an agent learns a large collection of labeled samples at once, streaming learning has been much less studied in the robotics and deep learning communities. In streaming learning, an agent learns instances one-by-one and can be tested at any time. Here, we revisit streaming linear discriminant analysis, which has been widely used in the data mining research community. By combining streaming linear discriminant analysis with deep learning, we are able to outperform both incremental batch learning and streaming learning algorithms on both ImageNet-1K and CORe50.

It was recently shown that architectural, regularization and rehearsal strategies can be used to train deep models sequentially on a number of disjoint tasks without forgetting previously acquired knowledge. However, these strategies are still unsatisfactory if the tasks are not disjoint but constitute a single incremental task (e.g., class-incremental learning). In this paper we point out the differences between multi-task and single-incremental-task scenarios and show that well-known approaches such as LWF, EWC and SI are not ideal for incremental task scenarios. A new approach, denoted as AR1, combining architectural and regularization strategies is then specifically proposed. AR1 overhead (in term of memory and computation) is very small thus making it suitable for online learning. When tested on CORe50 and iCIFAR-100, AR1 outperformed existing regularization strategies by a good margin.