Saved in:
Bibliographic Details
Main Authors: Sun, Guanxiong, Hua, Yang, Hu, Guosheng, Robertson, Neil
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.09923
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909090239741952
author Sun, Guanxiong
Hua, Yang
Hu, Guosheng
Robertson, Neil
author_facet Sun, Guanxiong
Hua, Yang
Hu, Guosheng
Robertson, Neil
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2401_09923
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MAMBA: Multi-level Aggregation via Memory Bank for Video Object Detection
Sun, Guanxiong
Hua, Yang
Hu, Guosheng
Robertson, Neil
Computer Vision and Pattern Recognition
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.
title MAMBA: Multi-level Aggregation via Memory Bank for Video Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.09923