日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

セグメンテーションarXiv:1807.07284

ピクセルを信じて:ピクセルラベリングから物体位置推定とシーン分類へ

In pixels we trust: From Pixel Labeling to Object Localization and Scene Categorization

シェア:XThreadsFacebookLINEはてブBluesky

セマンティックセグメンテーションを入力として物体検出とシーン分類を統合的に行うボトムアップ手法を提案し、NYU Depth V2で3タスクの最先端性能を達成した。

著者: Carlos Herranz-Perdiguero, Carolina Redondo-Cabrera, Roberto J. López-Sastre

分類: cs.CV, cs.RO

原文アブストラクト

While there has been significant progress in solving the problems of image pixel labeling, object detection and scene classification, existing approaches normally address them separately. In this paper, we propose to tackle these problems from a bottom-up perspective, where we simply need a semantic segmentation of the scene as input. We employ the DeepLab architecture, based on the ResNet deep network, which leverages multi-scale inputs to later fuse their responses to perform a precise pixel labeling of the scene. This semantic segmentation mask is used to localize the objects and to recognize the scene, following two simple yet effective strategies. We evaluate the benefits of our solutions, performing a thorough experimental evaluation on the NYU Depth V2 dataset. Our approach achieves a performance that beats the leading results by a significant margin, defining the new state of the art in this benchmark for the three tasks comprising the scene understanding: semantic segmentation, object detection and scene categorization.

関連論文

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2Google DeepMind、ロボット向けAIを発表新製品・発表
  3. 3GXO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
  4. 4パナソニックHDなど、触覚に即応する両手作業AI「T-Rex」を共同開発研究・技術
  5. 5SoftBank主導、Agile Robotsが5億ドル調達 NVIDIAと日立も参加資金調達

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