End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames
November 28, 2023 ยท Declared Dead ยท ๐ Computer Vision and Pattern Recognition
Repo contents: README.md
Authors
Shuming Liu, Chen-Lin Zhang, Chen Zhao, Bernard Ghanem
arXiv ID
2311.17241
Category
cs.CV: Computer Vision
Citations
54
Venue
Computer Vision and Pattern Recognition
Repository
https://github.com/sming256/AdaTAD
โญ 40
Last Checked
1 month ago
Abstract
Recently, temporal action detection (TAD) has seen significant performance improvement with end-to-end training. However, due to the memory bottleneck, only models with limited scales and limited data volumes can afford end-to-end training, which inevitably restricts TAD performance. In this paper, we reduce the memory consumption for end-to-end training, and manage to scale up the TAD backbone to 1 billion parameters and the input video to 1,536 frames, leading to significant detection performance. The key to our approach lies in our proposed temporal-informative adapter (TIA), which is a novel lightweight module that reduces training memory. Using TIA, we free the humongous backbone from learning to adapt to the TAD task by only updating the parameters in TIA. TIA also leads to better TAD representation by temporally aggregating context from adjacent frames throughout the backbone. We evaluate our model across four representative datasets. Owing to our efficient design, we are able to train end-to-end on VideoMAEv2-giant and achieve 75.4% mAP on THUMOS14, being the first end-to-end model to outperform the best feature-based methods. Code is available at https://github.com/sming256/AdaTAD.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Computer Vision
๐
๐
Old Age
๐
๐
Old Age
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
R.I.P.
๐ป
Ghosted
You Only Look Once: Unified, Real-Time Object Detection
๐
๐
Old Age
SSD: Single Shot MultiBox Detector
๐
๐
Old Age
Squeeze-and-Excitation Networks
R.I.P.
๐ป
Ghosted
Rethinking the Inception Architecture for Computer Vision
Died the same way โ ๐ Death by README
R.I.P.
๐
Death by README
Momentum Contrast for Unsupervised Visual Representation Learning
R.I.P.
๐
Death by README
LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model
R.I.P.
๐
Death by README
Revisiting Graph based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach
R.I.P.
๐
Death by README