日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

物体検出arXiv:2302.09779

シンプルなファインチューニングによるインクリメンタル少数ショット物体検出

Incremental Few-Shot Object Detection via Simple Fine-Tuning Approach

シェア:XThreadsFacebookLINEはてブBluesky

ベースクラスを再学習せずに少数の新規クラス例で段階的に学習するiFSDに対し、メタ学習ではなく2段階ファインチューニングで新規クラス分支を適応させる手法を提案し、LVISでメタ学習より30%高いAPを達成した。

著者: Tae-Min Choi, Jong-Hwan Kim

分類: cs.CV, cs.AI, cs.RO

原文アブストラクト

In this paper, we explore incremental few-shot object detection (iFSD), which incrementally learns novel classes using only a few examples without revisiting base classes. Previous iFSD works achieved the desired results by applying meta-learning. However, meta-learning approaches show insufficient performance that is difficult to apply to practical problems. In this light, we propose a simple fine-tuning-based approach, the Incremental Two-stage Fine-tuning Approach (iTFA) for iFSD, which contains three steps: 1) base training using abundant base classes with the class-agnostic box regressor, 2) separation of the RoI feature extractor and classifier into the base and novel class branches for preserving base knowledge, and 3) fine-tuning the novel branch using only a few novel class examples. We evaluate our iTFA on the real-world datasets PASCAL VOC, COCO, and LVIS. iTFA achieves competitive performance in COCO and shows a 30% higher AP accuracy than meta-learning methods in the LVIS dataset. Experimental results show the effectiveness and applicability of our proposed method.

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. 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. 5Google DeepMind、ロボット向けAIを発表新製品・発表

PR・アフィリエイト広告

MINISFORUM(ミニPC)

MINISFORUM(ミニPC)の公式広告バナーMINISFORUM公式ストアを見る ↗
PR本紙発行元 EmplifAI