mlsanityData to 14 Oct 2026

Augment Before Copy-Paste: Data and Memory Efficiency-Oriented Instance Segmentation Framework for Sport-scenes

arXiv 2403.11572 ↗First posted 18 Mar 2024cs.CV cs.MMcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 19 references that are in the map. First posted on arXiv 18 Mar 2024.

Builds on

17 of 19 references.

References · 17

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  2. 2018Group Normalizationcited by 1,524
  3. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,396
  4. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,385
  5. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,276
  6. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,152
  7. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 596
  8. 2019Hybrid Task Cascade for Instance Segmentationcited by 481
  9. 2019Mask Scoring R-CNNcited by 266
  10. 2021Instances as Queriescited by 158
  11. 2020GridMask Data Augmentationcited by 123
  12. 2021CBNet: A Composite Backbone Network Architecture for Object Detectioncited by 77
5 more
  1. 2020SWA Object Detectioncited by 22
  2. 2022VIPriors 2: Visual Inductive Priors for Data-Efficient Deep Learning Challengescited by 8
  3. 2021Instance Segmentation Challenge Track Technical Report, VIPriors Workshop at ICCV 2021: Task-Specific Copy-Paste Data Augmentation Method for Instance Segmentationcited by 5
  4. 2022Task-Specific Data Augmentation and Inference Processing for VIPriors Instance Segmentation Challengecited by 5
  5. 2023VIPriors 3: Visual Inductive Priors for Data-Efficient Deep Learning Challengescited by 4

Built on by

Not cited yet.