search

Megvii-BaseDetection / BorderDet

BorderDet: Border Feature for Dense Object Detection(ECCV2020 Oral)
Apache License 2.0
430 stars 63 forks source link

Support of Incremental Object Detection #3

Open rose-jinyang opened 4 years ago

rose-jinyang commented 4 years ago

Hello How are you? Thanks for contributing this project. I have a question. Does this project support class-incremental training for saving training time without catastrophic forgetting? Let's suppose I've trained a model on the dataset with K classes for 7 days. If a new class is added into this dataset, should we train a model with the expanded dataset (K+1 classes) from begin? If so, it is so expensive, especially in case of object detection in retail store. That's because a new class of good is added frequently in retail store. Can we train a new model in short time with the original weight on the expanded dataset? I think that this is a very important function. I send some recommended papers for this project. https://arxiv.org/pdf/1708.06977.pdf https://arxiv.org/pdf/2003.04668.pdf https://arxiv.org/pdf/2003.06957.pdf https://arxiv.org/pdf/2003.07304.pdf Please let me know if you have a willing to implement this. Thanks

Maycbj commented 4 years ago

We don't support these works in detection area now. And I suggest you to modify our code directly, and I believe it is not difficult to implement these works.