MISS: Memory-efficient Instance Segmentation Framework By Visual Inductive Priors Flow Propagation (2403.11576v1)
Abstract: Instance segmentation, a cornerstone task in computer vision, has wide-ranging applications in diverse industries. The advent of deep learning and artificial intelligence has underscored the criticality of training effective models, particularly in data-scarce scenarios - a concern that resonates in both academic and industrial circles. A significant impediment in this domain is the resource-intensive nature of procuring high-quality, annotated data for instance segmentation, a hurdle that amplifies the challenge of developing robust models under resource constraints. In this context, the strategic integration of a visual prior into the training dataset emerges as a potential solution to enhance congruity with the testing data distribution, consequently reducing the dependency on computational resources and the need for highly complex models. However, effectively embedding a visual prior into the learning process remains a complex endeavor. Addressing this challenge, we introduce the MISS (Memory-efficient Instance Segmentation System) framework. MISS leverages visual inductive prior flow propagation, integrating intrinsic prior knowledge from the Synergy-basketball dataset at various stages: data preprocessing, augmentation, training, and inference. Our empirical evaluations underscore the efficacy of MISS, demonstrating commendable performance in scenarios characterized by limited data availability and memory constraints.
- “Instance segmentation challenge track technical report, vipriors workshop at iccv 2021: Task-specific copy-paste data augmentation method for instance segmentation,” arXiv preprint arXiv:2110.00470, 2021.
- “Task-specific data augmentation and inference processing for vipriors instance segmentation challenge,” arXiv preprint arXiv:2211.11282, 2022.
- “Cascade r-cnn: Delving into high quality object detection,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018.
- “Per-pixel classification is not all you need for semantic segmentation,” in Advances in Neural Information Processing Systems, 2021.
- “Instances as queries,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, October 2021, pp. 6910–6919.
- “Cbnet: A composite backbone network architecture for object detection,” Proceedings of the AAAI Conference on Artificial Intelligence, 2022.
- “Simple copy-paste is a strong data augmentation method for instance segmentation,” Proceedings of the IEEE conference on computer vision and pattern recognition, 2021.
- “Vipriors 2: Visual inductive priors for data-efficient deep learning challenges,” arXiv preprint arXiv:2201.08625, 2021.
- “Vipriors 3: Visual inductive priors for data-efficient deep learning challenges,” arXiv preprint arXiv:2305.19688, 2022.
- John Canny, “A computational approach to edge detection,” IEEE Transactions on pattern analysis and machine intelligence, , no. 6, pp. 679–698, 1986.
- “Use of the hough transformation to detect lines and curves in pictures,” Communications of the ACM, vol. 15, no. 1, pp. 11–15, 1972.
- “MMDetection: Open mmlab detection toolbox and benchmark,” arXiv preprint arXiv:1906.07155, 2019.
- “Swa object detection,” arXiv preprint arXiv:2012.12645, 2020.
- “Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time,” International Conference on Machine Learning, 2022.