2nd Place Solution for SODA10M Challenge 2021 -- Continual Detection Track
Not on the map. Why?
Abstract (arXiv)
In this technical report, we present our approaches for the continual object detection track of the SODA10M challenge. We adapt ResNet50-FPN as the baseline and try several improvements for the final submission model. We find that task-specific replay scheme, learning rate scheduling, model calibration, and using original image scale helps to improve performance for both large and small objects in images. Our team `hypertune28' secured the second position among 52 participants in the challenge. This work will be presented at the ICCV 2021 Workshop on Self-supervised Learning for Next-Generation Industry-level Autonomous Driving (SSLAD).
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 9 of its 12 references that are in the map. First posted on arXiv 25 Oct 2021.
Builds on
9 of 12 references.
References · 9
- 2016Feature Pyramid Networks for Object Detectioncited by 5,036
- 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,276
- 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 596
- 2017Incremental Learning of Object Detectors without Catastrophic Forgettingcited by 208
- 2021Avalanche: an End-to-End Library for Continual Learningcited by 124
- 2020TIDE: A General Toolbox for Identifying Object Detection Errorscited by 114
- 2019Rethinking Classification and Localization for Object Detectioncited by 98
- 2017Incremental Adversarial Domain Adaptation for Continually Changing Environmentscited by 52
- 2020RODEO: Replay for Online Object Detectioncited by 35
Built on by
Citing papers per year: 2022: 1.
1 paper.