Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Towards Fine-grained Large Object Segmentation 1st Place Solution to 3D AI Challenge 2020 -- Instance Segmentation Track (2009.04650v2)

Published 10 Sep 2020 in cs.CV

Abstract: This technical report introduces our solutions of Team 'FineGrainedSeg' for Instance Segmentation track in 3D AI Challenge 2020. In order to handle extremely large objects in 3D-FUTURE, we adopt PointRend as our basic framework, which outputs more fine-grained masks compared to HTC and SOLOv2. Our final submission is an ensemble of 5 PointRend models, which achieves the 1st place on both validation and test leaderboards. The code is available at https://github.com/zehuichen123/3DFuture_ins_seg.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (20)
  1. Hybrid task cascade for instance segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 4974–4983, 2019.
  2. Mmdetection: Open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155, 2019.
  3. Tensormask: A foundation for dense object segmentation. In Proceedings of the IEEE International Conference on Computer Vision, pages 2061–2069, 2019.
  4. BlendMask: Top-down meets bottom-up for instance segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8573–8581, 2020.
  5. Disentangle your dense object detector. In Proceedings of the 29th ACM international conference on multimedia, pages 4939–4948, 2021.
  6. Deformable convolutional networks. In Proceedings of the IEEE International Conference on Computer Vision, pages 764–773, 2017.
  7. Covscode: a novel real-time collaborative programming environment for lightweight ide. Applied Sciences, 9(21):4642, 2019.
  8. Res2net: A new multi-scale backbone architecture. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019.
  9. Mask R-CNN. arXiv preprint arXiv:1703.06870, 2017.
  10. Mask Scoring R-CNN. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 6409–6418, 2019.
  11. 1st place solutions of waymo open dataset challenge 2020–2d object detection track. arXiv preprint arXiv:2008.01365, 2020.
  12. Pointrend: Image segmentation as rendering. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9799–9808, 2020.
  13. Rebalancing expanding ev sharing systems with deep reinforcement learning. In Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, pages 1338–1344, 2021.
  14. Fleet rebalancing for expanding shared e-mobility systems: A multi-agent deep reinforcement learning approach. IEEE Transactions on Intelligent Transportation Systems, 24(4):3868–3881, 2023.
  15. Libra R-CNN: Towards balanced learning for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 821–830, 2019.
  16. Conditional convolutions for instance segmentation. arXiv preprint arXiv:2003.05664, 2020.
  17. SOLOv2: Dynamic, Faster and Stronger. arXiv preprint arXiv:2003.10152, 2020.
  18. Rethinking classification and localization for object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10186–10195, 2020.
  19. Aggregated residual transformations for deep neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1492–1500, 2017.
  20. Multistep flow prediction on car-sharing systems: A multi-graph convolutional neural network with attention mechanism. International Journal of Software Engineering and Knowledge Engineering, 29(11n12):1727–1740, 2019.
Citations (1)

Summary

We haven't generated a summary for this paper yet.