Few-Shot Class-Incremental Learning (FSCIL) introduces a paradigm in which
the problem space expands with limited data. FSCIL methods inherently face the
challenge of catastrophic forgetting as data arrives incrementally, making
models susceptible to overwriting previously acquired knowledge. Moreover,
given the scarcity of labeled samples available at any given time, models may
be prone to overfitting and find it challenging to strike a balance between
extensive pretraining and the limited incremental data. To address these
challenges, we propose the OrCo framework built on two core principles:
features' orthogonality in the representation space, and contrastive learning.
In particular, we improve the generalization of the embedding space by
employing a combination of supervised and self-supervised contrastive losses
during the pretraining phase. Additionally, we introduce OrCo loss to address
challenges arising from data limitations during incremental sessions. Through
feature space perturbations and orthogonality between classes, the OrCo loss
maximizes margins and reserves space for the following incremental data. This,
in turn, ensures the accommodation of incoming classes in the feature space
without compromising previously acquired knowledge. Our experimental results
showcase state-of-the-art performance across three benchmark datasets,
including mini-ImageNet, CIFAR100, and CUB datasets. Code is available at
this https URL

Few-Shot Class-Incremental Learning (FSCIL) introduces the OrCo framework, which addresses challenges of catastrophic forgetting and data limitations during incremental sessions through features' orthogonality and contrastive learning, resulting in state-of-the-art performance across benchmark datasets.

OrCo：通过正交性和对比度实现更好的少样本类增量学习的泛化

OrCo: Towards Better Generalization via Orthogonality and Contrast for  Few-Shot Class-Incremental Learning

While many FSCIL studies have been undertaken, achieving satisfactory
performance, especially during incremental sessions, has remained challenging.
One prominent challenge is that the encoder, trained with an ample base session
training set, often underperforms in incremental sessions. In this study, we
introduce a novel training framework for FSCIL, capitalizing on the
generalizability of the Contrastive Language-Image Pre-training (CLIP) model to
unseen classes. We achieve this by formulating image-object-specific (IOS)
classifiers for the input images. Here, an IOS classifier refers to one that
targets specific attributes (like wings or wheels) of class objects rather than
the image's background. To create these IOS classifiers, we encode a bias
prompt into the classifiers using our specially designed module, which
harnesses key-prompt pairs to pinpoint the IOS features of classes in each
session. From an FSCIL standpoint, our framework is structured to retain
previous knowledge and swiftly adapt to new sessions without forgetting or
overfitting. This considers the updatability of modules in each session and
some tricks empirically found for fast convergence. Our approach consistently
demonstrates superior performance compared to state-of-the-art methods across
the miniImageNet, CIFAR100, and CUB200 datasets. Further, we provide additional
experiments to validate our learned model's ability to achieve IOS classifiers.
We also conduct ablation studies to analyze the impact of each module within
the architecture.

使用 Contrastive Language-Image Pre-training (CLIP) 模型的泛化能力，我们提出了一种创新的 FSCIL 训练框架，通过为输入图像创建针对图像对象特定属性（如翅膀或轮胎）而非背景的 IOS 分类器来解决增量会话中编码器表现不佳的问题。通过特定设计的模块利用关键提示对 IOS 分类器进行编码，以找到每个会话中类别的 IOS 特征，从而始终保留先前的知识并快速适应新的会话，而不会遗忘或过拟合，在 miniImageNet、CIFAR100 和 CUB200 数据集上的实验证明了我们方法相对于最先进方法的优越性能，并通过额外实验验证了我们所学模型实现 IOS 分类器的能力，并进行了消融研究以分析架构中每个模块的影响。