Abstract
Both few-shot learning and domain adaptation sub-fields in Computer Vision have seen significant recent progress in terms of the availability of state-of-the-art algorithms and datasets. Frameworks have been developed for each sub-field; however, building a common system or framework that combines both is something that has not been explored. As part of our research, we present the first unified framework that combines domain adaptation for the few-shot learning setting across 3 different tasks - image classification, object detection and video classification. Our framework is highly modular with the capability to support few-shot learning with/without the inclusion of domain adaptation depending on the algorithm. Furthermore, the most important configurable feature of our framework is the on-the-fly setup for incremental $n$-shot tasks with the optional capability to configure the system to scale to a traditional many-shot task. With more focus on Self-Supervised Learning (SSL) for current few-shot learning approaches, our system also supports multiple SSL pre-training configurations. To test our framework's capabilities, we provide benchmarks on a wide range of algorithms and datasets across different task and problem settings. The code is open source has been made publicly available here: this https URL
Abstract (translated)
在计算机视觉领域，少量样本学习和域适应这两个子领域的研究都取得了显著进展，尤其是在先进算法和数据集的可用性方面。为每个子领域开发了框架；然而，构建一个能够将两者结合起来的通用系统或框架还未曾被探索过。作为我们研究的一部分，我们提出了首个结合少量样本学习场景下的域适应的统一框架，涵盖了三种不同的任务：图像分类、目标检测和视频分类。我们的框架高度模块化，支持根据算法需要选择是否包含域适应的少量样本学习。此外，我们框架最重要的可配置特性是能够实时设置增量$n$-样本任务，并且可以选择将系统扩展到传统的多样本任务中去。鉴于目前少量样本学习方法对自监督学习（SSL）的关注越来越多，我们的系统还支持多种SSL预训练配置。为了测试我们框架的能力，我们在广泛的算法和数据集上提供了基准，在不同的任务和问题设置下进行验证。代码是开源的，并在这里公开：此 https 链接
URL
https://arxiv.org/abs/2412.16275
