Abstract
Weakly supervised object detection (WSOD) is a challenging task when provided with image category supervision but required to simultaneously learn object locations and object detectors. Many WSOD approaches adopt multiple instance learning (MIL) and have non-convex loss functions which are prone to get stuck into local minima (falsely localize object parts) while missing full object extent during training. In this paper, we introduce a continuation optimization method into MIL and thereby creating continuation multiple instance learning (C-MIL), with the intention of alleviating the non-convexity problem in a systematic way. We partition instances into spatially related and class related subsets, and approximate the original loss function with a series of smoothed loss functions defined within the subsets. Optimizing smoothed loss functions prevents the training procedure falling prematurely into local minima and facilitates the discovery of Stable Semantic Extremal Regions (SSERs) which indicate full object extent. On the PASCAL VOC 2007 and 2012 datasets, C-MIL improves the state-of-the-art of weakly supervised object detection and weakly supervised object localization with large margins.
Abstract (translated)
弱监督目标检测（WSOD）是一项具有挑战性的任务，当提供图像类别监督时，需要同时学习目标位置和目标检测器。许多WSOD方法采用多实例学习（mil），并且具有非凸损失函数，在训练过程中容易陷入局部极小（错误地将对象部分局部化），而缺少完整的对象范围。本文将连续优化方法引入多实例学习（C-mil），以系统地解决非凸性问题。我们将实例划分为空间相关和类相关的子集，并用在这些子集中定义的一系列平滑损失函数来近似原始损失函数。优化平滑损失函数可以防止训练过程过早地陷入局部极小值，并有助于发现稳定的语义极值区域（SSER），这些区域指示了整个对象范围。在PascalVOC 2007和2012数据集上，c-mil提高了弱监督目标检测和大幅度弱监督目标定位的技术水平。
URL
https://arxiv.org/abs/1904.05647
