ETAD: Training Action Detection End to End on a Laptop

TL;DR

ETAD introduces an efficient end-to-end temporal action detector that significantly reduces GPU memory and computational requirements, enabling training on a laptop while achieving state-of-the-art results.

Contribution

The paper presents a novel training method for TAD that minimizes memory use and computational redundancy, allowing effective training on low-resource devices.

Findings

Achieves 38.25% mAP on ActivityNet-1.3 in 18 hours

Uses only 1.3 GB memory per video during training

Outperforms existing methods in efficiency and accuracy

Abstract

Temporal action detection (TAD) with end-to-end training often suffers from the pain of huge demand for computing resources due to long video duration. In this work, we propose an efficient temporal action detector (ETAD) that can train directly from video frames with extremely low GPU memory consumption. Our main idea is to minimize and balance the heavy computation among features and gradients in each training iteration. We propose to sequentially forward the snippet frame through the video encoder, and backward only a small necessary portion of gradients to update the encoder. To further alleviate the computational redundancy in training, we propose to dynamically sample only a small subset of proposals during training. Moreover, various sampling strategies and ratios are studied for both the encoder and detector. ETAD achieves state-of-the-art performance on TAD benchmarks with remarkable efficiency. On ActivityNet-1.3, training ETAD in 18 hours can reach 38.25% average mAP with only 1.3 GB memory consumption per video under end-to-end training. Our code will be publicly released.