تقرير
MAMBA: Multi-level Aggregation via Memory Bank for Video Object Detection
| العنوان: | MAMBA: Multi-level Aggregation via Memory Bank for Video Object Detection |
|---|---|
| المؤلفون: | Sun, Guanxiong, Hua, Yang, Hu, Guosheng, Robertson, Neil |
| المصدر: | In Proceedings of the AAAI Conference on Artificial Intelligence 2021 (Vol. 35, No. 3, pp. 2620-2627) |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition |
| الوصف: | State-of-the-art video object detection methods maintain a memory structure, either a sliding window or a memory queue, to enhance the current frame using attention mechanisms. However, we argue that these memory structures are not efficient or sufficient because of two implied operations: (1) concatenating all features in memory for enhancement, leading to a heavy computational cost; (2) frame-wise memory updating, preventing the memory from capturing more temporal information. In this paper, we propose a multi-level aggregation architecture via memory bank called MAMBA. Specifically, our memory bank employs two novel operations to eliminate the disadvantages of existing methods: (1) light-weight key-set construction which can significantly reduce the computational cost; (2) fine-grained feature-wise updating strategy which enables our method to utilize knowledge from the whole video. To better enhance features from complementary levels, i.e., feature maps and proposals, we further propose a generalized enhancement operation (GEO) to aggregate multi-level features in a unified manner. We conduct extensive evaluations on the challenging ImageNetVID dataset. Compared with existing state-of-the-art methods, our method achieves superior performance in terms of both speed and accuracy. More remarkably, MAMBA achieves mAP of 83.7/84.6% at 12.6/9.1 FPS with ResNet-101. Code is available at https://github.com/guanxiongsun/vfe.pytorch. Comment: update code url https://github.com/guanxiongsun/vfe.pytorch |
| نوع الوثيقة: | Working Paper |
| DOI: | 10.1609/aaai.v35i3.16365 |
| URL الوصول: | http://arxiv.org/abs/2401.09923 |
| رقم الأكسشن: | edsarx.2401.09923 |
| قاعدة البيانات: | arXiv |
| DOI: | 10.1609/aaai.v35i3.16365 |
|---|