In this work, we revisit the weak-to-strong consistency framework, popularized by FixMatch from semi-supervised classification, where the prediction of a weakly perturbed image serves as supervision for its strongly perturbed version. Intriguingly, we observe that such a simple pipeline already achieves competitive results against recent advanced works, when transferred to our segmentation scenario. Its success heavily relies on the manual design of strong data augmentations, however, which may be limited and inadequate to explore a broader perturbation space. Motivated by this, we propose an auxiliary feature perturbation stream as a supplement, leading to an expanded perturbation space. On the other, to sufficiently probe original image-level augmentations, we present a dual-stream perturbation technique, enabling two strong views to be simultaneously guided by a common weak view. Consequently, our overall Unified Dual-Stream Perturbations approach (UniMatch) surpasses all existing methods significantly across all evaluation protocols on the Pascal, Cityscapes, and COCO benchmarks. We also demonstrate the superiority of our method in remote sensing interpretation and medical image analysis. Code is available at https://github.com/LiheYoung/UniMatch.
翻译:在这项工作中,我们重新审视了由半监督分类的FixMatch普及的弱至强一致性框架,通过半监督分类法,预测一个微弱受扰动的图像可以监督其强烈扰动的版本。有趣的是,我们注意到,这种简单的管道在被转移到我们的分解方案时,已经与最近的先进工程取得了竞争性结果,但成功在很大程度上依赖于强大的数据增强的手工设计,而这种手工设计可能有限,也不足以探索更广泛的扰动空间。受此驱动,我们提出一个辅助性特征扰动流作为补充,导致更大的扰动空间。另一方面,为了充分探测原始的图像级增强,我们提出了双流扰动技术,使两种强烈观点能够同时受到共同薄弱观点的引导。因此,我们的总体统一双轨扰动方法(Unimatch)大大超过关于帕斯卡、城市景景区和COCO基准的所有评估协议中的所有现有方法。我们还展示了我们在遥感/YoungM/Mmorgimage分析中所使用的方法的优越性。