Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation

By Lihe Yang, Lei Qi, Litong Feng, Wayne Zhang, Yinghuan Shi. Computer Vision and Pattern Recognition, 2022

504 citations recorded by the source corpus.

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. Its superiority is also demonstrated in remote sensing interpretation and medical image analysis. We hope our reproduced FixMatch and our results can inspire more future works.

Subfields: Artificial Intelligence, Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/98cdd14faacf54161f4d73ab65ff2aac85161f89

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation (2024, methodology): “In contrast, OpenVid - 1M adopts a more efficient UniMatch [28] to achieve better optical flows, addressing not only static videos but also those with fast movements.”
Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentation (2022, background): “Some works [207, 208, 206] explicitly divide (a) Atrous convolution [164] to enlarge foreground features (b) Skip-connections [166] to shrink foreground features perturbations into strong and weak perturbations, and use the prediction from a weakly perturbed input to supervise the prediction from…”
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data (2024, background): “This belongs to the research area of semi-supervised learning [31, 55, 89], which is popular with various applications [70, 74].”