日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

オンライン学習/単眼深度推定arXiv:2410.02980

DecTrain: 単眼深度DNNをオンラインでいつ訓練するかの判断

DecTrain: Deciding When to Train a Monocular Depth DNN Online

シェア:XThreadsFacebookLINEはてブBluesky

単眼深度推定DNNのオンライン自己教師あり学習において、訓練すべきタイミングを精度向上予測と計算コストの比較で判断し、平均44%の時間だけで全時刻訓練と同等の精度を維持する手法を提案。

著者: Zih-Sing Fu, Soumya Sudhakar, Sertac Karaman, Vivienne Sze

分類: cs.LG, cs.RO

原文アブストラクト

Deep neural networks (DNNs) can deteriorate in accuracy when deployment data differs from training data. While performing online training at all timesteps can improve accuracy, it is computationally expensive. We propose DecTrain, a new algorithm that decides when to train a monocular depth DNN online using self-supervision with low overhead. To make the decision at each timestep, DecTrain compares the cost of training with the predicted accuracy gain. We evaluate DecTrain on out-of-distribution data, and find DecTrain maintains accuracy compared to online training at all timesteps, while training only 44% of the time on average. We also compare the recovery of a low inference cost DNN using DecTrain and a more generalizable high inference cost DNN on various sequences. DecTrain recovers the majority (97%) of the accuracy gain of online training at all timesteps while reducing computation compared to the high inference cost DNN which recovers only 66%. With an even smaller DNN, we achieve 89% recovery while reducing computation by 56%. DecTrain enables low-cost online training for a smaller DNN to have competitive accuracy with a larger, more generalizable DNN at a lower overall computational cost.

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  3. 3NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  4. 4GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開
  5. 5UC BerkeleyとNVIDIAの研究者、AIエージェントでロボット制御コードを仮想環境で改善研究・技術

PR・アフィリエイト広告

OZ GAMING(GPU搭載BTOゲーミングPC)

OZ GAMING(GPU搭載BTOゲーミングPC)の公式広告バナーOZ GAMINGで完成品PCを見る ↗
PR本紙発行元 EmplifAI