Fugu-MT 論文翻訳(概要): OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection

論文の概要: OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection

arxiv url: http://arxiv.org/abs/2103.04507v3
Date: Thu, 11 Mar 2021 05:17:08 GMT
ステータス: 処理完了
システム内更新日: 2021-03-12 18:54:22.243493
Title: OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection
Title（参考訳）: OPANAS:オブジェクト検出のためのワンショットパス集約ネットワークアーキテクチャ検索
Authors: Tingting Liang, Yongtao Wang, Zhi Tang, Guosheng Hu, Haibin Ling
Abstract要約: 近年、ニューラルアーキテクチャサーチ (NAS) が特徴ピラミッドネットワーク (FPN) の設計に活用されている。本稿では,探索効率と検出精度を大幅に向上させる,ワンショットパス集約ネットワークアーキテクチャ探索(OPANAS)アルゴリズムを提案する。
参考スコア（独自算出の注目度）: 82.04372532783931
License: http://creativecommons.org/publicdomain/zero/1.0/
Abstract: Recently, neural architecture search (NAS) has been exploited to design feature pyramid networks (FPNs) and achieved promising results for visual object detection. Encouraged by the success, we propose a novel One-Shot Path Aggregation Network Architecture Search (OPANAS) algorithm, which significantly improves both searching efficiency and detection accuracy. Specifically, we first introduce six heterogeneous information paths to build our search space, namely top-down, bottom-up, fusing-splitting, scale-equalizing, skip-connect and none. Second, we propose a novel search space of FPNs, in which each FPN candidate is represented by a densely-connected directed acyclic graph (each node is a feature pyramid and each edge is one of the six heterogeneous information paths). Third, we propose an efficient one-shot search method to find the optimal path aggregation architecture, that is, we first train a super-net and then find the optimal candidate with an evolutionary algorithm. Experimental results demonstrate the efficacy of the proposed OPANAS for object detection: (1) OPANAS is more efficient than state-of-the-art methods (e.g., NAS-FPN and Auto-FPN), at significantly smaller searching cost (e.g., only 4 GPU days on MS-COCO); (2) the optimal architecture found by OPANAS significantly improves main-stream detectors including RetinaNet, Faster R-CNN and Cascade R-CNN, by 2.3-3.2 % mAP comparing to their FPN counterparts; and (3) a new state-of-the-art accuracy-speed trade-off (52.2 % mAP at 7.6 FPS) at smaller training costs than comparable state-of-the-arts. Code will be released at https://github.com/VDIGPKU/OPANAS.
Abstract（参考訳）: 近年、ニューラルアーキテクチャサーチ (NAS) を用いて特徴ピラミッドネットワーク (FPN) を設計し、視覚オブジェクト検出の有望な結果を得た。そこで本研究では,検索効率と検出精度を有意に向上させる,新しいOne-Shot Path Aggregation Network Architecture Search(OPANAS)アルゴリズムを提案する。具体的には、トップダウン、ボトムアップ、融合分割、スケール等化、スキップ接続、およびなしの検索空間を構築するために、6つの異種情報パスを最初に導入します。次に,FPNの候補を高密度に連結した有向非巡回グラフで表現するFPNの新しい探索空間を提案する(各ノードは特徴ピラミッドであり,各エッジは6つの異種情報パスの1つである)。第3に,最適なパスアグリゲーションアーキテクチャ,すなわちスーパーネットをまず学習し,次に進化アルゴリズムを用いて最適な候補を見つけるための効率的なワンショット探索法を提案する。 Experimental results demonstrate the efficacy of the proposed OPANAS for object detection: (1) OPANAS is more efficient than state-of-the-art methods (e.g., NAS-FPN and Auto-FPN), at significantly smaller searching cost (e.g., only 4 GPU days on MS-COCO); (2) the optimal architecture found by OPANAS significantly improves main-stream detectors including RetinaNet, Faster R-CNN and Cascade R-CNN, by 2.3-3.2 % mAP comparing to their FPN counterparts; and (3) a new state-of-the-art accuracy-speed trade-off (52.2 % mAP at 7.6 FPS) at smaller training costs than comparable state-of-the-arts. コードはhttps://github.com/VDIGPKU/OPANASで公開されます。

論文の概要: OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection

関連論文リスト