Few-shot class-incremental learning (FSCIL) struggles to incrementally recognize novel classes from few examples without catastrophic forgetting of old classes or overfitting to new classes. We propose TLCE, which ensembles multiple pre-trained models to improve separation of novel and old classes. TLCE minimizes interference between old and new classes by mapping old class images to quasi-orthogonal prototypes using episodic training. It then ensembles diverse pre-trained models to better adapt to novel classes despite data imbalance. Extensive experiments on various datasets demonstrate that our transfer learning ensemble approach outperforms state-of-the-art FSCIL methods.
Incremental learning is useful if an AI agent needs to integrate data from a stream. The problem is non trivial if the agent runs on a limited computational budget and has a bounded memory of past data. In a deep learning approach, the constant computational budget requires the use of a fixed architecture for all incremental states. The bounded memory generates data imbalance in favor of new classes and a prediction bias toward them appears. This bias is commonly countered by introducing a data balancing step in addition to the basic network training. We depart from this approach and propose s…
Incremental Learning (IL) is useful when artificial systems need to deal with streams of data and do not have access to all data at all times. The most challenging setting requires a constant complexity of the deep model and an incremental model update without access to a bounded memory of past data. Then, the representations of past classes are strongly affected by catastrophic forgetting. To mitigate its negative effect, an adapted fine tuning which includes knowledge distillation is usually deployed. We propose a different approach based on a vanilla fine tuning backbone. It leverages initi…
DFKI - German Research Center for Artificial Intelligence（德国人工智能研究中心）；Birla Institute of Technology and Science, Pilani（皮拉尼·博拉理工学院）；Computer Vision Center, Barcelona（巴塞罗那计算机视觉中心）
In class-incremental semantic segmentation (CISS), deep learning architectures suffer from the critical problems of catastrophic forgetting and semantic background shift. Although recent works focused on these issues, existing classifier initialization methods do not address the background shift problem and assign the same initialization weights to both background and new foreground class classifiers. We propose to address the background shift with a novel classifier initialization method which employs gradient-based attribution to identify the most relevant weights for new classes from the cl…
Instituto de Ciências Matemáticas e de Computação, Universidade de São Paulo（圣保罗大学数学与计算机科学研究所）
We present a classification method with incremental capabilities based on the Optimum-Path Forest classifier (OPF). The OPF considers instances as nodes of a fully-connected training graph, arc weights represent distances between two feature vectors. Our algorithm includes new instances in an OPF in linear-time, while keeping similar accuracies when compared with the original quadratic-time model.
Sculpting Margin Penalty: Intra-Task Adapter Merging and Classifier Calibration for Few-Shot Class-Incremental Learning
School of Computer Science and Technology, Beijing Institute of Technology（计算机科学与技术学院，北京理工大学）；School of Optics and Photonics, Beijing Institute of Technology（光学与 photonics 学院，北京理工大学）；School of Medical Technology, Beijing Institute of Technology（医学技术学院，北京理工大学）
Embedding Space Allocation with Angle-Norm Joint Classifiers for Few-Shot Class-Incremental Learning
National Key Laboratory for Novel Software Technology（新型软件技术国家重点实验室）；School of Artificial Intelligence（人工智能学院）；School of Electronic Science and Engineering（电子科学与工程学院）
Xi’an Jiaotong University（西安交通大学）；Singapore Management University（新加坡管理大学）；Peng Cheng Laboratory（鹏城实验室）；Harbin Institute of Technology（哈尔滨工业大学）；Shenzhen Institute of Advanced Technology, Chinese Academy of Science（中国科学院深圳先进技术研究院）
This paper focuses on the prevalent performance imbalance in the stages of incremental learning. To avoid obvious stage learning bottlenecks, we propose a brand-new stage-isolation based incremental learning framework, which leverages a series of stage-isolated classifiers to perform the learning task of each stage without the interference of others. To be concrete, to aggregate multiple stage classifiers as a uniform one impartially, we first introduce a temperature-controlled energy metric for indicating the confidence score levels of the stage classifiers. We then propose an anchor-based en…
Peking University（北京大学）；University of Oxford（牛津大学）；JD Explore Academy（京东探索研究院）；Wuhan University（武汉大学）；Peng Cheng Laboratory（鹏城实验室）
Few-shot class-incremental learning (FSCIL) has been a challenging problem as only a few training samples are accessible for each novel class in the new sessions. Finetuning the backbone or adjusting the classifier prototypes trained in the prior sessions would inevitably cause a misalignment between the feature and classifier of old classes, which explains the well-known catastrophic forgetting problem. In this paper, we deal with this misalignment dilemma in FSCIL inspired by the recently discovered phenomenon named neural collapse, which reveals that the last-layer features of the same clas…
Current deep learning classifiers, carry out supervised learning and store class discriminatory information in a set of shared network weights. These weights cannot be easily altered to incrementally learn additional classes, since the classification weights all require retraining to prevent old class information from being lost and also require the previous training data to be present. We present a novel two stage architecture which couples visual feature learning with probabilistic models to represent each class in the form of a Gaussian Mixture Model. By using these independent class repres…
Few-shot class-incremental learning (FSCIL) aims to design machine learning algorithms that can continually learn new concepts from a few data points, without forgetting knowledge of old classes. The difficulty lies in that limited data from new classes not only lead to significant overfitting issues but also exacerbate the notorious catastrophic forgetting problems. Moreover, as training data come in sequence in FSCIL, the learned classifier can only provide discriminative information in individual sessions, while FSCIL requires all classes to be involved for evaluation. In this paper, we add…
University of Oxford（牛津大学）；IST Austria（奥地利科学技术研究所）
A major open problem on the road to artificial intelligence is the development of incrementally learning systems that learn about more and more concepts over time from a stream of data. In this work, we introduce a new training strategy, iCaRL, that allows learning in such a class-incremental way: only the training data for a small number of classes has to be present at the same time and new classes can be added progressively. iCaRL learns strong classifiers and a data representation simultaneously. This distinguishes it from earlier works that were fundamentally limited to fixed data represen…
Northeastern University（东北大学）；Microsoft Research（微软研究院）；City University of New York（纽约城市大学）
In this paper, we address the incremental classifier learning problem, which suffers from catastrophic forgetting. The main reason for catastrophic forgetting is that the past data are not available during learning. Typical approaches keep some exemplars for the past classes and use distillation regularization to retain the classification capability on the past classes and balance the past and new classes. However, there are four main problems with these approaches. First, the loss function is not efficient for classification. Second, there is unbalance problem between the past and new classes…
MPI for Informatics（马克斯·普朗克信息学研究所）；Goethe University Frankfurt（法兰克福大学）；MIT-IBM Watson AI Lab（MIT-IBM沃森人工智能实验室）
Both generalized and incremental few-shot learning have to deal with three major challenges: learning novel classes from only few samples per class, preventing catastrophic forgetting of base classes, and classifier calibration across novel and base classes. In this work we propose a three-stage framework that allows to explicitly and effectively address these challenges. While the first phase learns base classes with many samples, the second phase learns a calibrated classifier for novel classes from few samples while also preventing catastrophic forgetting. In the final phase, calibration is…
National University of Science and Technology（国立科技大学）
The ability to learn from incrementally arriving data is essential for any life-long learning system. However, standard deep neural networks forget the knowledge about the old tasks, a phenomenon called catastrophic forgetting, when trained on incrementally arriving data. We discuss the biases in current Generative Adversarial Networks (GAN) based approaches that learn the classifier by knowledge distillation from previously trained classifiers. These biases cause the trained classifier to perform poorly. We propose an approach to remove these biases by distilling knowledge from the classifier…
Exemplar-Free Class Incremental Learning via Incremental Representation
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；School of Mathematics and Statistics, Beijing Technology and Business University（北京工商大学数学与统计学院）
Yonsei University（延世大学）；Korea Institute of Science and Technology (KIST)（韩国科学技术研究院）
Class-incremental semantic segmentation (CISS) labels each pixel of an image with a corresponding object/stuff class continually. To this end, it is crucial to learn novel classes incrementally without forgetting previously learned knowledge. Current CISS methods typically use a knowledge distillation (KD) technique for preserving classifier logits, or freeze a feature extractor, to avoid the forgetting problem. The strong constraints, however, prevent learning discriminative features for novel classes. We introduce a CISS framework that alleviates the forgetting problem and facilitates learni…
A method based on one class support vector machine (OCSVM) is proposed for class incremental learning. Several OCSVM models divide the input space into several parts. Then, the 1VS1 classifiers are constructed for the confuse part by using the support vectors. During the class incremental learning process, the OCSVM of the new class is trained at first. Then the support vectors of the old classes and the support vectors of the new class are reused to train 1VS1 classifiers for the confuse part. In order to bring more information to the certain support vectors, the support vectors are at the bo…
Regularization-based methods are beneficial to alleviate the catastrophic forgetting problem in class-incremental learning. With the absence of old task images, they often assume that old knowledge is well preserved if the classifier produces similar output on new images. In this paper, we find that their effectiveness largely depends on the nature of old classes: they work well on classes that are easily distinguishable between each other but may fail on more fine-grained ones, e.g., boy and girl. In spirit, such methods project new data onto the feature space spanned by the weight vectors in…
Dynamic Feature Learning and Matching for Class-Incremental Learning
Macau University of Science and Technology（澳门科技大学）；State Key Laboratory of Multimodal Artificial Intelligence Systems（多模态人工智能系统国家重点实验室）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
National University of Sciences and Technology（国家科技大学）；School of Electrical Engineering and Computer Science（电子工程与计算机科学学院）；National Center of Artificial Intelligence（国家人工智能中心）
One of the key differences between the learning mechanism of humans and Artificial Neural Networks (ANNs) is the ability of humans to learn one task at a time. ANNs, on the other hand, can only learn multiple tasks simultaneously. Any attempts at learning new tasks incrementally cause them to completely forget about previous tasks. This lack of ability to learn incrementally, called Catastrophic Forgetting, is considered a major hurdle in building a true AI system. In this paper, our goal is to isolate the truly effective existing ideas for incremental learning from those that only work under …
Dynamic Residual Classifier for Class Incremental Learning
Sun Yat-sen University（中山大学）；Guangdong Key Laboratory of Big Data Analysis and Processing（广东省大数据分析与处理重点实验室）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education（教育部机器智能与先进计算重点实验室）
Dual Consolidation for Pre-Trained Model-Based Domain-Incremental Learning
School of Artificial Intelligence, Nanjing University（南京大学人工智能学院）；National Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）
Automatic Construction of Pattern Classifiers Capable of Continuous Incremental Learning and Unlearning Tasks Based on Compact-Sized Probabilistic Neural Network
Department of Computer Engineering, College of Science & Technology（计算机工程系，科学与技术学院）
University of Toronto（多伦多大学）；LG AI Research（LG人工智能研究院）
Online class-incremental continual learning (CL) studies the problem of learning new classes continually from an online non-stationary data stream, intending to adapt to new data while mitigating catastrophic forgetting. While memory replay has shown promising results, the recency bias in online learning caused by the commonly used Softmax classifier remains an unsolved challenge. Although the Nearest-Class-Mean (NCM) classifier is significantly undervalued in the CL community, we demonstrate that it is a simple yet effective substitute for the Softmax classifier. It addresses the recency bias…
The influence of class orderings in the evaluation of incremental learning has received very little attention. In this paper, we investigate the impact of class orderings for incrementally learned classifiers. We propose a method to compute various orderings for a dataset. The orderings are derived by simulated annealing optimization from the confusion matrix and reflect different incremental learning scenarios, including maximally and minimally confusing tasks. We evaluate a wide range of state-of-the-art incremental learning methods on the proposed orderings. Results show that orderings can …
PILoRA: Prototype Guided Incremental LoRA for Federated Class-Incremental Learning
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science and Innovation, Chinese Academy of Sciences（中国科学院香港创新研究院人工智能与机器人中心）
Few-shot Class-Incremental Learning via Generative Co-Memory Regularization
Institute of Information Engineering（信息工程研究所）；Chinese Academy of Sciences（中国科学院）；School of Cyber Security（网络安全学院）；University of Chinese Academy of Sciences（中国科学院大学）；Department of Communication Engineering（通信工程系）
Scalable Analytic Classifiers with Associative Drift Compensation for Class-Incremental Learning of Vision Transformers
School of Systems Science, Beijing Normal University, Beijing 100875, China（北京师范大学系统科学学院）；School of Artificial Intelligence, Anhui University, Hefei 230601, China（安徽大学人工智能学院）；Faculty of Informatics, Universita' Della Svizzera Italiana, Lugano, Switzerland（瑞士意大利大学信息学院）
This paper proposes a working recipe of using Vision Transformer (ViT) in class incremental learning. Although this recipe only combines existing techniques, developing the combination is not trivial. Firstly, naive application of ViT to replace convolutional neural networks (CNNs) in incremental learning results in serious performance degradation. Secondly, we nail down three issues of naively using ViT: (a) ViT has very slow convergence when the number of classes is small, (b) more bias towards new classes is observed in ViT than CNN-based architectures, and (c) the conventional learning rat…
Traditional learning systems are trained in closed-world for a fixed number of classes, and need pre-collected datasets in advance. However, new classes often emerge in real-world applications and should be learned incrementally. For example, in electronic commerce, new types of products appear daily, and in a social media community, new topics emerge frequently. Under such circumstances, incremental models should learn several new classes at a time without forgetting. We find a strong correlation between old and new classes in incremental learning, which can be applied to relate and facilitat…
University of Chinese Academy of Science（中国科学院大学）；Institute of Automation, Chinese Academy of Sciences (CAS)（中国科学院自动化研究所）
Class incremental learning(CIL) has attracted much attention, but most existing related works focus on fine-tuning the entire representation model, which inevitably results in much catastrophic forgetting. In the contrast, with a semantic-rich pre-trained representation model, parameter-additional-tuning (PAT) only changes very few parameters to learn new visual concepts. Recent studies have proved that PAT-based CIL can naturally avoid fighting against forgetting by replaying or distilling like most of the existing methods. However, we find that PAT-based CIL still faces serious semantic drif…
IPEC: Test-Time Incremental Prototype Enhancement Classifier for Few-Shot Learning
College of Intelligent Robotics and Advanced Manufacturing, Fudan University（智能机器人与先进制造学院，复旦大学）；School of Microelectronics, Fudan University（微电子学院，复旦大学）；Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education, East China University of Science and Technology（教育部先进化工过程控制与优化重点实验室，东华大学）
South China University of Technology（华南理工大学）；City University of Hongkong（香港城市大学）
Most of the proposed person re-identification algorithms conduct supervised training and testing on single labeled datasets with small size, so directly deploying these trained models to a large-scale real-world camera network may lead to poor performance due to underfitting. It is challenging to incrementally optimize the models by using the abundant unlabeled data collected from the target domain. To address this challenge, we propose an unsupervised incremental learning algorithm, TFusion, which is aided by the transfer learning of the pedestrians' spatio-temporal patterns in the target dom…
UIFormer: A Unified Transformer-based Framework for Incremental Few-Shot Object Detection and Instance Segmentation
Hunan University（湖南大学）；Hunan Agricultural University（湖南农业大学）；Anhui University（安徽大学）；Swansea University（斯旺西大学）；Northwestern Polytechnical University（西北工业大学）；Guangxi Normal University（广西师范大学）；University of Western Australia（西澳大学）
University of Windsor（温莎大学）；Higher School of Communication of Tunis（突尼斯高等通信学院）
In this paper we outline a PhD research plan. This research contributes to the field of one-class incremental learning and classification in case of non-stationary environments. The goal of this PhD is to define a new classification framework able to deal with very small learning dataset at the beginning of the process and with abilities to adjust itself according to the variability of the incoming data which create large scale datasets. As a preliminary work, incremental Covariance-guided One-Class Support Vector Machine is proposed to deal with sequentially obtained data. It is inspired from…
University of Trento（特伦托大学）；Fondazione Bruno Kessler（布鲁诺·凯塞勒基金会）
We study the new task of class-incremental Novel Class Discovery (class-iNCD), which refers to the problem of discovering novel categories in an unlabelled data set by leveraging a pre-trained model that has been trained on a labelled data set containing disjoint yet related categories. Apart from discovering novel classes, we also aim at preserving the ability of the model to recognize previously seen base categories. Inspired by rehearsal-based incremental learning methods, in this paper we propose a novel approach for class-iNCD which prevents forgetting of past information about the base c…
