We propose MonoBox, an innovative box-supervised segmentation method constrained by monotonicity to liberate its training from the user-unfriendly box-tightness assumption. In contrast to conventional box-supervised segmentation, where the box edges must precisely touch the target boundaries, MonoBox leverages imprecisely-annotated boxes to achieve robust pixel-wise segmentation. The 'linchpin' is that, within the noisy zones around box edges, MonoBox discards the traditional misguiding multiple-instance learning loss, and instead optimizes a carefully-designed objective, termed monotonicity constraint. Along directions transitioning from the foreground to background, this new constraint steers responses to adhere to a trend of monotonically decreasing values. Consequently, the originally unreliable learning within the noisy zones is transformed into a correct and effective monotonicity optimization. Moreover, an adaptive label correction is introduced, enabling MonoBox to enhance the tightness of box annotations using predicted masks from the previous epoch and dynamically shrink the noisy zones as training progresses. We verify MonoBox in the box-supervised segmentation task of polyps, where satisfying box-tightness is challenging due to the vague boundaries between the polyp and normal tissues. Experiments on both public synthetic and in-house real noisy datasets demonstrate that MonoBox exceeds other anti-noise state-of-the-arts by improving Dice by at least 5.5% and 3.3%, respectively. Codes are at https://github.com/Huster-Hq/MonoBox.

翻译：我们提出MonoBox，一种受单调性约束的创新性框监督分割方法，旨在将其训练过程从用户不友好的框紧密度假设中解放出来。与传统的框监督分割方法（其框边缘必须精确触及目标边界）不同，MonoBox利用不精确标注的框来实现稳健的像素级分割。其关键在于，在框边缘周围的噪声区域内，MonoBox摒弃了传统易误导的多示例学习损失，转而优化一个精心设计的目标，称为单调性约束。在从前景过渡到背景的方向上，这一新约束引导响应值遵循单调递减的趋势。因此，原本在噪声区域内不可靠的学习过程被转化为正确且有效的单调性优化。此外，我们引入了自适应标签校正机制，使MonoBox能够利用前一训练周期预测的掩码来增强框标注的紧密度，并随着训练进程动态缩小噪声区域。我们在息肉分割的框监督任务中验证了MonoBox，由于息肉与正常组织之间边界模糊，满足框紧密度在该任务中颇具挑战。在公开合成数据集和内部真实噪声数据集上的实验表明，MonoBox超越了其他抗噪声的先进方法，分别将Dice系数至少提高了5.5%和3.3%。代码位于 https://github.com/Huster-Hq/MonoBox。