Methods › General › Semi-Supervised Learning Methods › STAC

STAC

8 papers tagged archive 2025-07-28

Introduced by Kihyuk Sohn et al. in A Simple Semi-Supervised Learning Framework for Object Detection

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

STAC is a semi-supervised framework for visual object detection along with a data augmentation strategy. STAC deploys highly confident pseudo labels of localized objects from an unlabeled image and updates the model by enforcing consistency via strong augmentations. We generate pseudo labels (i.e., bounding boxes and their class labels) for unlabeled data using test-time inference, including NMS , of the teacher model trained with labeled data. We then compute unsupervised loss with respect to pseudo labels whose confidence scores are above a threshold τ . The strong augmentations are applied for augmentation consistency during the model training. Target boxes are augmented when global geometric transformations are used.

PaperSource

Papers archive 2025-07-28

8 shown of 8, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Data Augmentation2
Object Detection2
Semantic Segmentation2
Semi-Supervised Object Detection2
object-detection2
Discourse Parsing1
Image Classification1
Image Segmentation1
Medical Image Segmentation1
Multiple-choice1
Object1
Optical Flow Estimation1
Segmentation1
Semi-supervised Medical Image Segmentation1
Sensitivity1
Sentence1
Sentence Ordering1
Video Segmentation1
Video Semantic Segmentation1
image-classification1

Usage over time archive 2025-07-28

Papers per year tagged with STAC: 2020 to 2024, peak 3 3 0 2020: 1 paper 2020 2021: 1 paper 2021 2022: 1 paper 2022 2023: 3 papers 2023 2024: 2 papers 2024
Papers per year the archive tags with this method, by the paper's archive date (8 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Semi-Supervised Learning Methods

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections