Class-incremental Learning via Deep Model Consolidation (original) (raw)

End-to-End Incremental Learning

Computer Vision – ECCV 2018, 2018

Although deep learning approaches have stood out in recent years due to their state-of-the-art results, they continue to suffer from catastrophic forgetting, a dramatic decrease in overall performance when training with new classes added incrementally. This is due to current neural network architectures requiring the entire dataset, consisting of all the samples from the old as well as the new classes, to update the model-a requirement that becomes easily unsustainable as the number of classes grows. We address this issue with our approach to learn deep neural networks incrementally, using new data and only a small exemplar set corresponding to samples from the old classes. This is based on a loss composed of a distillation measure to retain the knowledge acquired from the old classes, and a cross-entropy loss to learn the new classes. Our incremental training is achieved while keeping the entire framework end-to-end, i.e., learning the data representation and the classifier jointly, unlike recent methods with no such guarantees. We evaluate our method extensively on the CIFAR-100 and Im-ageNet (ILSVRC 2012) image classification datasets, and show state-of-the-art performance.

Class-Incremental Learning with Strong Pre-trained Models

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Class-incremental learning (CIL) has been widely studied under the setting of starting from a small number of classes (base classes). Instead, we explore an understudied real-world setting of CIL that starts with a strong model pre-trained on a large number of base classes. We hypothesize that a strong base model can provide a good representation for novel classes and incremental learning can be done with small adaptations. We propose a 2-stage training scheme, i) feature augmentation-cloning part of the backbone and fine-tuning it on the novel data, and ii) fusion-combining the base and novel classifiers into a unified classifier. Experiments show that the proposed method significantly outperforms state-of-the-art CIL methods on the large-scale ImageNet dataset (e.g. +10% overall accuracy than the best). We also propose and analyze understudied practical CIL scenarios, such as base-novel overlap with distribution shift. Our proposed method is robust and generalizes to all analyzed CIL settings.

Class-Incremental Learning: Survey and Performance Evaluation on Image Classification

IEEE Transactions on Pattern Analysis and Machine Intelligence

For future learning systems incremental learning is desirable, because it allows for: efficient resource usage by eliminating the need to retrain from scratch at the arrival of new data; reduced memory usage by preventing or limiting the amount of data required to be stored-also important when privacy limitations are imposed; and learning that more closely resembles human learning. The main challenge for incremental learning is catastrophic forgetting, which refers to the precipitous drop in performance on previously learned tasks after learning a new one. Incremental learning of deep neural networks has seen explosive growth in recent years. Initial work focused on taskincremental learning, where a task-ID is provided at inference time. Recently, we have seen a shift towards class-incremental learning where the learner must discriminate at inference time between all classes seen in previous tasks without recourse to a task-ID. In this paper, we provide a complete survey of existing class-incremental learning methods for image classification, and in particular we perform an extensive experimental evaluation on thirteen class-incremental methods. We consider several new experimental scenarios, including a comparison of classincremental methods on multiple large-scale image classification datasets, investigation into small and large domain shifts, and comparison of various network architectures.

Class-incremental learning: survey and performance evaluation

arXiv (Cornell University), 2020

For future learning systems incremental learning is desirable, because it allows for: efficient resource usage by eliminating the need to retrain from scratch at the arrival of new data; reduced memory usage by preventing or limiting the amount of data required to be stored -- also important when privacy limitations are imposed; and learning that more closely resembles human learning. The main challenge for incremental learning is catastrophic forgetting, which refers to the precipitous drop in performance on previously learned tasks after learning a new one. Incremental learning of deep neural networks has seen explosive growth in recent years. Initial work focused on task incremental learning, where a task-ID is provided at inference time. Recently we have seen a shift towards class-incremental learning where the learner must classify at inference time between all classes seen in previous tasks without recourse to a task-ID. In this paper, we provide a complete survey of existing methods for incremental learning, and in particular we perform an extensive experimental evaluation on twelve class-incremental methods. We consider several new experimental scenarios, including a comparison of class-incremental methods on multiple large-scale datasets, investigation into small and large domain shifts, and comparison on various network architectures.

ClaRe: Practical Class Incremental Learning By Remembering Previous Class Representations

2021

This paper presents a practical and simple yet efficient method to effectively deal with the catastrophic forgetting for Class Incremental Learning (CIL) tasks. CIL tends to learn new concepts perfectly, but not at the expense of performance and accuracy for old data. Learning new knowledge in the absence of data instances from previous classes or even imbalance samples of both old and new classes makes CIL an ongoing challenging problem. These issues can be tackled by storing exemplars belonging to the previous tasks or by utilizing the rehearsal strategy. Inspired by the rehearsal strategy with the approach of using generative models, we propose ClaRe, an efficient solution for CIL by remembering the representations of learned classes in each increment. Taking this approach leads to generating instances with the same distribution of the learned classes. Hence, our model is somehow retrained from the scratch using a new training set including both new and the generated samples. Sub...

Semantic Drift Compensation for Class-Incremental Learning

2020

Class-incremental learning of deep networks sequentially increases the number of classes to be classified. During training, the network has only access to data of one task at a time, where each task contains several classes. In this setting, networks suffer from catastrophic forgetting which refers to the drastic drop in performance on previous tasks. The vast majority of methods have studied this scenario for classification networks, where for each new task the classification layer of the network must be augmented with additional weights to make room for the newly added classes. Embedding networks have the advantage that new classes can be naturally included into the network without adding new weights. Therefore, we study incremental learning for embedding networks. In addition, we propose a new method to estimate the drift, called semantic drift, of features and compensate for it without the need of any exemplars. We approximate the drift of previous tasks based on the drift that is experienced by current task data. We perform experiments on fine-grained datasets, CIFAR100 and ImageNet-Subset. We demonstrate that embedding networks suffer significantly less from catastrophic forgetting. We outperform existing methods which do not require exemplars and obtain competitive results compared to methods which store exemplars. Furthermore, we show that our proposed SDC when combined with existing methods to prevent forgetting consistently improves results. 1

DILF-EN framework for Class-Incremental Learning

arXiv (Cornell University), 2021

A class-incremental learning problem is characterized by training data becoming available in a phase-by-phase manner. Deep learning models suffer from catastrophic forgetting of the classes in the older phases as they get trained on the classes introduced in the new phase. In this work, we show that the effect of catastrophic forgetting on the model prediction varies with the change in orientation of the same image, which is a novel finding. Based on this, we propose a novel data-ensemble approach that combines the predictions for the different orientations of the image to help the model retain further information regarding the previously seen classes and thereby reduce the effect of forgetting on the model predictions. However, we cannot directly use the data-ensemble approach if the model is trained using traditional techniques. Therefore, we also propose a novel dual-incremental learning framework that involves jointly training the network with two incremental learning objectives, i.e., the class-incremental learning objective and our proposed data-incremental learning objective. In the dualincremental learning framework, each image belongs to two classes, i.e., the image class (for class-incremental learning) and the orientation class (for data-incremental learning). In class-incremental learning, each new phase introduces a new set of classes, and the model cannot access the complete training data from the older phases. In our proposed data-incremental learning, the orientation classes remain the same across all the phases, and the data introduced by the new phase in class-incremental learning acts as new training data for these orientation classes. We empirically demonstrate that the dual-incremental learning framework is vital to the data-ensemble approach. We apply our proposed approach to state-of-the-art class-incremental learning methods and empirically show that our framework significantly improves the performance of these methods. Our proposed method significantly improves the performance of the stateof-the-art method (AANets) on the CIFAR-100 dataset by absolute margins of 3.30%, 4.28%, 3.55%, 4.03%, for the number of phases P=50, 25, 10, and 5, respectively, which establishes the efficacy of the proposed work.

M2KD: Multi-model and Multi-level Knowledge Distillation for Incremental Learning

arXiv (Cornell University), 2019

Incremental learning targets at achieving good performance on new categories without forgetting old ones. Knowledge distillation has been shown critical in preserving the performance on old classes. Conventional methods, however, sequentially distill knowledge only from the penultimate model, leading to performance degradation on the old classes in later incremental learning steps. In this paper, we propose a multi-model and multi-level knowledge distillation strategy. Instead of sequentially distilling knowledge only from the penultimate model, we directly leverage all previous model snapshots. In addition, we incorporate an auxiliary distillation to further preserve knowledge encoded at the intermediate feature levels. To make the model more memory efficient, we adapt mask based pruning to reconstruct all previous models with a small memory footprint. Experiments on standard incremental learning benchmarks show that our method improves the overall performance over standard distillation techniques. ZHOU et al.: INCREMENTAL LEARNING VIA M 2 KD Incremental step S1 S2 S3 Knowledge distillation Knowledge distillation Incremental step S1 S2 S3 Knowledge distillation Knowledge distillation

Tree-CNN: A hierarchical Deep Convolutional Neural Network for incremental learning

Neural Networks, 2019

Over the past decade, Deep Convolutional Neural Networks (DCNNs) have shown remarkable performance in most computer vision tasks. These tasks traditionally use a fixed dataset, and the model, once trained, is deployed as is. Adding new information to such a model presents a challenge due to complex training issues, such as "catastrophic forgetting", and sensitivity to hyperparameter tuning. However, in this modern world, data is constantly evolving, and our deep learning models are required to adapt to these changes. In this paper, we propose an adaptive hierarchical network structure composed of DCNNs that can grow and learn as new data becomes available. The network grows in a tree-like fashion to accommodate new classes of data, while preserving the ability to distinguish the previously trained classes. The network organizes the incrementally available data into feature-driven superclasses and improves upon existing hierarchical CNN models by adding the capability of self-growth. The proposed hierarchical model, when compared against fine-tuning a deep network, achieves significant reduction of training effort, while maintaining competitive accuracy on CIFAR-10 and CIFAR-100.

Self-Training for Class-Incremental Semantic Segmentation

IEEE Transactions on Neural Networks and Learning Systems, 2022

We study incremental learning for semantic segmentation where when learning new classes we have no access to the labeled data of previous tasks. When incrementally learning new classes, deep neural networks suffer from catastrophic forgetting of previous learned knowledge. To address this problem, we propose to apply a self-training approach that leverages unlabeled data, which is used for rehearsal of previous knowledge. Additionally, conflict reduction is proposed to resolve the conflicts of pseudo labels generated from both the old and new models. We show that maximizing self-entropy can further improve results by smoothing the overconfident predictions. The experiments demonstrate state-of-the-art results: obtaining a relative gain of up to 114% on Pascal-VOC 2012 and 8.5% on the more challenging ADE20K compared to previous state-of-the-art methods.