计算机科学
人工智能
目标检测
判别式
机器学习
概率逻辑
模棱两可
对象(语法)
过程(计算)
棱锥(几何)
联营
不确定性(哲学)
基线(sea)
不确定度量化
含糊其词
公制(单位)
模式识别(心理学)
采样(信号处理)
感知
比例(比率)
测量不确定度
代表(政治)
数据挖掘
抽象
特征学习
作者
Xiang Yuan,Gong Cheng,Jiacheng Cheng,Ruixiang Yao,Junwei Han
标识
DOI:10.1109/tip.2026.3654892
摘要
Small object detection (SOD) constitutes a notable yet immensely arduous task, stemming from the restricted informative regions inherent in size-limited instances, which further sparks off heightened uncertainty beyond the capacity of current two-stage detectors. Specifically, the intrinsic ambiguity in small objects undermines the prevailing sampling paradigms and may mislead the model to devote futile effort to those unrecognizable targets, while the inconsistency of features utilized for the detection at two stages further exposes the hierarchical uncertainty. In this paper, we develop an Uncertainty learning framework for Small Object Detection, dubbed as Unc-SOD. By incorporating an auxiliary uncertainty branch to conventional Region Proposal Network (RPN), we model the indeterminacy at instance-level which later on serves as a surrogate criterion for sampling, thereby unearthing adequate candidates dynamically based on the varying degrees of uncertainty and facilitating the learning of proposal networks. In parallel, a Perception-and-Interaction strategy is devised to capture rich and discriminative representations, through optimizing the intrinsic properties from the regional features at the original pyramid and the assigned one, in which the perceptual process unfolds in a mutual paradigm. As the seminal attempt to model uncertainty in SOD task, our Unc-SOD yields state-of-the-art performance on two large-scale small object detection benchmarks, SODA-D and SODA-A, and the results on several SOD-oriented datasets including COCO, VisDrone, and Tsinghua-Tencent 100K also exhibit the promotion to baseline detector. This underscores the efficacy of our approach and its superiority over prevailing detectors when dealing with small instances.
科研通智能强力驱动
Strongly Powered by AbleSci AI