Detecting test samples drawn sufficiently far away from the training distribution statistically or adversarially is a fundamental requirement for deploying a good classifier in many real-world machine learning applications. However, deep neural networks with the softmax classifier are known to produce highly overconfident posterior distributions even for such abnormal samples. In this paper, we propose a simple yet effective method for detecting any abnormal samples, which is applicable to any pre-trained softmax neural classifier. We obtain the class conditional Gaussian distributions with respect to (low- and upper-level) features of the deep models under Gaussian discriminant analysis, which result in a confidence score based on the Mahalanobis distance. While most prior methods have been evaluated for detecting either out-of-distribution or adversarial samples, but not both, the proposed method achieves the state-of-the-art performances for both cases in our experiments. Moreover, we found that our proposed method is more robust in harsh cases, e.g., when the training dataset has noisy labels or small number of samples. Finally, we show that the proposed method enjoys broader usage by applying it to class-incremental learning: whenever out-of-distribution samples are detected, our classification rule can incorporate new classes well without further training deep models.
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 representations and therefore incompatible with deep learning architectures. We show by experiments on CIFAR-100 and ImageNet ILSVRC 2012 data that iCaRL can learn many classes incrementally over a long period of time where other strategies quickly fail.
Multi-class supervised learning systems require the knowledge of the entire range of labels they predict. Often when learnt incrementally, they suffer from catastrophic forgetting. To avoid this, generous leeways have to be made to the philosophy of incremental learning that either forces a part of the machine to not learn, or to retrain the machine again with a selection of the historic data. While these hacks work to various degrees, they do not adhere to the spirit of incremental learning. In this article, we redefine incremental learning with stringent conditions that do not allow for any undesirable relaxations and assumptions. We design a strategy involving generative models and the distillation of dark knowledge as a means of hallucinating data along with appropriate targets from past distributions. We call this technique, phantom sampling.We show that phantom sampling helps avoid catastrophic forgetting during incremental learning. Using an implementation based on deep neural networks, we demonstrate that phantom sampling dramatically avoids catastrophic forgetting. We apply these strategies to competitive multi-class incremental learning of deep neural networks. Using various benchmark datasets and through our strategy, we demonstrate that strict incremental learning could be achieved. We further put our strategy to test on challenging cases, including cross-domain increments and incrementing on a novel label space. We also propose a trivial extension to unbounded-continual learning and identify potential for future development.
A plain well-trained deep learning model often does not have the ability to learn new knowledge without forgetting the previously learned knowledge, which is known as catastrophic forgetting. Here we propose a novel method, SupportNet, to efficiently and effectively solve the catastrophic forgetting problem in the class incremental learning scenario. SupportNet combines the strength of deep learning and support vector machine (SVM), where SVM is used to identify the support data from the old data, which are fed to the deep learning model together with the new data for further training so that the model can review the essential information of the old data when learning the new information. Two powerful consolidation regularizers are applied to stabilize the learned representation and ensure the robustness of the learned model. We validate our method with comprehensive experiments on various tasks, which show that SupportNet drastically outperforms the state-of-the-art incremental learning methods and even reaches similar performance as the deep learning model trained from scratch on both old and new data. Our program is accessible at: https://github.com/lykaust15/SupportNet
잘 초기화된 복권 티켓 가설(Well-initialized Lottery Ticket Hypothesis, WLTH)에서 영감을 받아, 우리는 Soft-TransFormers(Soft-TF)를 제안한다. 이는 고정된 사전학습 트랜스포머를 선택된 셀프 어텐션(self-attention) 레이어의 query, key, value, output 투영(projection)에 대한 실수값 곱셈 마스크로 구성된 과제별 소프트 서브네트워크를 통해 적응시키는 연속 학습(continual learning) 프레임워크이다. 마스크는 1로 초기화되므로 최적화는 정확히 사전학습 해법에서 시작하며, 마스크 공간 경사하강법은 본질적으로 백본의 지배적 경로를 조절하는 방향으로 편향된다. 우리는 표준 볼록-리ipschitz 가정 하에서, 수렴 속도와 마스크만 사용하는 미세조정의 매개변수 편향(drift) 모두가 사전학습 가중치에서 과제 최적 구성까지의 거리에 의해 제어됨을 증명한다. 이러한 제한된 편향은 두 가지 성질을 만든다. 백본과 과제별 마스크가 덮어쓰이지 않으므로 망각은 구조적으로 제거된다. 또한 모든 과제 서브네트워크가 공유 사전학습 해법 근처에 머물기 때문에, 잘못된 마스크라도 거의 범용적인 함수에 가까운 함수를 평가하므로 과제 추론 오류는 대체로 무해하며, 클래스 증분(class-incremental) 정확도는 과제 추론 신뢰성과 분리된다. 플러그인으로 Soft-TF는 L2P, DualPrompt, HiDe-Prompt, NoRGa와 결합되며, 과제 키 매칭, 엔트로피-그래디언트 기준, 또는 학습된 과제 식별 분류기로 마스크를 선택한다. Split-CIFAR100, Split-ImageNet-R, CUB-200, 5-Datasets 등 클래스 증분 학습 벤치마크에서 Soft-TF는 유사한 학습 가능 매개변수 예산에서 프롬프트 기반, 어댑터 기반, LoRA 스타일 기준선들을 일관되게 능가하면서, 수정되지 않은 백본과 동일한 추론 비용을 유지한다.
Few-shot class-incremental learning (FSCIL) aims to incrementally learn novel classes from limited examples while preserving knowledge of previously learned classes. Existing methods face a critical dilemma: static architectures rely on a constant parameter space to learn from data that arrive sequentially, making them prone to overfitting to the current session, while dynamic architectures continually expand the parameter space, leading to increased complexity. In this study, we explore the potential of Selective State Space Models (SSMs) for FSCIL. Mamba leverages its input-dependent parameters to dynamically adjust its processing patterns and generate content-aware scan patterns without session-wise projector expansion. This enables it to configure distinct processing for base and novel classes, helping preserve existing knowledge while adapting to new ones. To leverage Mamba's potential for FSCIL, we design two key modules: First, we propose a dual selective SSM projector that generates input-conditioned state-space parameters from intermediate features for dynamic adaptation. The dual design structurally decouples base and novel-class processing, employing a frozen base branch to maintain stable base-class features and a dynamic incremental branch that adaptively learns distinctive feature shifts for novel classes. Second, we develop a class-sensitive selective scan mechanism to guide dynamic adaptation of the incremental branch. It reduces the disruption to base-class representations caused by training on novel data, and meanwhile, encourages the selective scan to perform in distinct patterns between base and novel classes. Extensive experiments on miniImageNet, CIFAR-100, and CUB-200 demonstrate that Mamba-FSCIL achieves state-of-the-art performance.