Referring Expression Comprehension (REC) aims to localize an image region of a given object described by a natural-language expression. While promising performance has been demonstrated, existing REC algorithms make a strong assumption that training data feeding into a model are given upfront, which degrades its practicality for real-world scenarios. In this paper, we propose Continual Referring Expression Comprehension (CREC), a new setting for REC, where a model is learning on a stream of incoming tasks. In order to continuously improve the model on sequential tasks without forgetting prior learned knowledge and without repeatedly re-training from a scratch, we propose an effective baseline method named Dual Modular Memorization (DMM), which alleviates the problem of catastrophic forgetting by two memorization modules: Implicit-Memory and Explicit-Memory. Specifically, the former module aims to constrain drastic changes to important parameters learned on old tasks when learning a new task; while the latter module maintains a buffer pool to dynamically select and store representative samples of each seen task for future rehearsal. We create three benchmarks for the new CREC setting, by respectively re-splitting three widely-used REC datasets RefCOCO, RefCOCO+ and RefCOCOg into sequential tasks. Extensive experiments on the constructed benchmarks demonstrate that our DMM method significantly outperforms other alternatives, based on two popular REC backbones.
- Python 2.7
- Pytorch 0.2 (may not work with 1.0 or higher)
- CUDA 8.0
The code is implemented on https://github.com/lichengunc/MAttNet. Follow the instructions in it.
Feel free to ping me ([email protected]) if you encounter trouble getting it to work!
@ARTICLE{9916159,
author={Shen, Heng Tao and Chen, Cheng and Wang, Peng and Gao, Lianli and Wang, Meng and Song, Jingkuan},
journal={IEEE Transactions on Image Processing},
title={Continual Referring Expression Comprehension via Dual Modular Memorization},
year={2022},
volume={31},
number={},
pages={6694-6706},
doi={10.1109/TIP.2022.3212317}
}