日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

3Dビジョン/敵対的堅牢性arXiv:2409.12379

カリキュラム学習による敵対的相互情報量の最小化で3Dロボットビジョンの堅牢性を向上

Enhancing 3D Robotic Vision Robustness by Minimizing Adversarial Mutual Information through a Curriculum Training Approach

シェア:XThreadsFacebookLINEはてブBluesky

敵対的摂動下での相互情報量を最小化する学習目的とカリキュラム学習を組み合わせ、3Dビジョンモデルの敵対的堅牢性を高める手法を提案。

著者: Nastaran Darabi, Dinithi Jayasuriya, Devashri Naik, Theja Tulabandhula, Amit Ranjan Trivedi

分類: cs.CV, cs.IT, cs.RO, math.IT

原文アブストラクト

Adversarial attacks exploit vulnerabilities in a model's decision boundaries through small, carefully crafted perturbations that lead to significant mispredictions. In 3D vision, the high dimensionality and sparsity of data greatly expand the attack surface, making 3D vision particularly vulnerable for safety-critical robotics. To enhance 3D vision's adversarial robustness, we propose a training objective that simultaneously minimizes prediction loss and mutual information (MI) under adversarial perturbations to contain the upper bound of misprediction errors. This approach simplifies handling adversarial examples compared to conventional methods, which require explicit searching and training on adversarial samples. However, minimizing prediction loss conflicts with minimizing MI, leading to reduced robustness and catastrophic forgetting. To address this, we integrate curriculum advisors in the training setup that gradually introduce adversarial objectives to balance training and prevent models from being overwhelmed by difficult cases early in the process. The advisors also enhance robustness by encouraging training on diverse MI examples through entropy regularizers. We evaluated our method on ModelNet40 and KITTI using PointNet, DGCNN, SECOND, and PointTransformers, achieving 2-5% accuracy gains on ModelNet40 and a 5-10% mAP improvement in object detection. Our code is publicly available at https://github.com/nstrndrbi/Mine-N-Learn.

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2GXO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
  3. 3newmo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
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  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

FRONTIER(GPU搭載BTOパソコン)

FRONTIER(GPU搭載BTOパソコン)の公式広告バナーFRONTIERでGPU搭載PCを見る ↗
PR本紙発行元 EmplifAI