.png){kind=icon}
返回
Tail-Calibrated Transformer Autoencoding with Prototype- Guided Mining for Open-World Object Detection
.png){kind=icon}
OA
AI
DOI：10.3390/app152010918.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Open-world object detection (OWOD) aims to build detectors that can recognize known categories while simultaneously identifying unknown objects and incrementally learning novel classes. Despite recent advances, existing OWOD approaches still struggle with two critical challenges: the severe bias toward head classes in long-tailed data distributions and the misclassification of unknown objects as background. To address these issues, we introduce TAPM (Tail-Calibrated Transformer Autoencoding with Prototype-Guided Mining), a novel framework that explicitly enhances tail-class representation and robustly reveals unknown objects. TAPM integrates three core innovations: (1) a transformer-based autoencoder that reconstructs region features to calibrate embeddings for rare categories, mitigating the dominance of frequent classes; (2) a prototype-guided mining strategy that leverages class prototypes to localize both overlooked tail instances and candidate unknowns; and (3) an uncertainty-aware soft-labeling mechanism that assigns probabilistic supervision to pseudo-unknowns, reducing noise in incremental learning. Extensive experiments on the MS-COCO and LVIS benchmarks demonstrate that TAPM significantly improves unknown-object recall while maintaining strong known-class accuracy, achieving state-of-the-art performance across both the superclass-separated (S-OWODB) and superclass-mixed (M-OWODB) benchmarks. In particular, TAPM achieves a +20.4-point gain in U-Recall over the strong PROB baseline, underscoring its effectiveness in detecting novel objects without sacrificing mean Average Precision (mAP). Furthermore, TAPM achieves better generalization on cross-dataset evaluations, highlighting its robustness in diverse open-world scenarios.
Keyword:
open-world object detection (OWOD)
incremental learning
unknown-object discovery
uncertainty-aware labeling
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
A
IF:
2.5
论文数:
7.6K
被引数:
4
机构
引用论文
Redefining Object Detection for Open-World Settings: A Framework for Simultaneous Identification of Known and Unknown Classes重新定义开放世界设置的对象检测: 同时识别已知和未知课程的框架.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks更快的r-cnn: 基于区域建议网络的实时目标检测OAAI
OAAI分享收藏分享收藏分享收藏
查看更多内容