Instance segmentation is a fundamental task in computer vision with broad applications across various industries. In recent years, with the proliferation of deep learning and artificial intelligence applications, how to train effective models with limited data has become a pressing issue for both academia and industry. In the Visual Inductive Priors challenge (VIPriors2023), participants must train a model capable of precisely locating individuals on a basketball court, all while working with limited data and without the use of transfer learning or pre-trained models. We propose Memory effIciency inStance Segmentation framework based on visual inductive prior flow propagation that effectively incorporates inherent prior information from the dataset into both the data preprocessing and data augmentation stages, as well as the inference phase. Our team (ACVLAB) experiments demonstrate that our model achieves promising performance (0.509 [email protected]:0.95) even under limited data and memory constraints.

翻译：实例分割是计算机视觉中的一项基础任务，具有广泛的行业应用。近年来，随着深度学习与人工智能应用的普及，如何在有限数据条件下训练有效模型已成为学术界和工业界亟待解决的问题。在视觉归纳先验挑战赛（VIPriors2023）中，参赛者需在不使用迁移学习或预训练模型且数据受限的情况下，训练能精确定位篮球场上个体的模型。我们提出基于视觉归纳先验流传播的内存高效实例分割框架，该框架在数据预处理、数据增强阶段以及推理阶段均有效整合数据集的固有先验信息。我们团队（ACVLAB）的实验表明，即便在数据与内存受限条件下，该模型仍取得了优越性能（0.509 [email protected]:0.95）。