{"url":"/method/stac","slug":"stac","name":"STAC","full_name":"STAC","full_name_withheld":false,"description_markdown":"**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 $\\tau$ . The strong augmentations are applied for augmentation consistency during the model training. Target boxes are augmented when global geometric transformations are used.","description_state":"present","introduced_year":null,"introduced_by":{"title":"A Simple Semi-Supervised Learning Framework for Object Detection","paper":"/paper/a-simple-semi-supervised-learning-framework","first_author":"Kihyuk Sohn","n_authors":6,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/a-simple-semi-supervised-learning-framework"},"source":{"url":"https://arxiv.org/abs/2005.04757v2","title":"A Simple Semi-Supervised Learning Framework for Object Detection","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Semi-Supervised Learning Methods","url":"/methods/category/semi-supervised-learning-methods","pwc_aliases":[]}],"n_papers_tagged":8,"archive_num_papers":8,"papers_newest_first":[{"paper":"/paper/shape-transformation-driven-by-active-contour","title":"Shape Transformation Driven by Active Contour for Class-Imbalanced Semi-Supervised Medical Image Segmentation","date":"2024-10-18","arxiv_id":"2410.14210","n_code_links":1,"syntology":null},{"paper":"/paper/stac-leveraging-spatio-temporal-data","title":"STAC: Leveraging Spatio-Temporal Data Associations For Efficient Cross-Camera Streaming and Analytics","date":"2024-01-27","arxiv_id":"2401.15288","n_code_links":1,"syntology":null},{"paper":"/paper/structured-dialogue-discourse-parsing-1","title":"Structured Dialogue Discourse Parsing","date":"2023-06-26","arxiv_id":"2306.15103","n_code_links":1,"syntology":null},{"paper":null,"title":"Systematic Architectural Design of Scale Transformed Attention Condenser DNNs via Multi-Scale Class Representational Response Similarity Analysis","date":"2023-06-16","arxiv_id":"2306.10128","n_code_links":0,"syntology":null},{"paper":null,"title":"Discourse Structure Extraction from Pre-Trained and Fine-Tuned Language Models in Dialogues","date":"2023-02-12","arxiv_id":"2302.05895","n_code_links":0,"syntology":null},{"paper":null,"title":"DNN-Driven Compressive Offloading for Edge-Assisted Semantic Video Segmentation","date":"2022-03-28","arxiv_id":"2203.14481","n_code_links":0,"syntology":null},{"paper":"/paper/humble-teachers-teach-better-students-for","title":"Humble Teachers Teach Better Students for Semi-Supervised Object Detection","date":"2021-06-19","arxiv_id":"2106.10456","n_code_links":0,"syntology":null},{"paper":"/paper/a-simple-semi-supervised-learning-framework","title":"A Simple Semi-Supervised Learning Framework for Object Detection","date":"2020-05-10","arxiv_id":"2005.04757","n_code_links":7,"syntology":{"ran":0,"of":1,"unverified":1,"pointer_only":0}}],"papers_shown":8,"tasks":[{"task":"/task/data-augmentation","name":"Data Augmentation","papers":2},{"task":"/task/object-detection","name":"Object Detection","papers":2},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":2},{"task":"/task/semi-supervised-object-detection","name":"Semi-Supervised Object Detection","papers":2},{"task":"/task/object-detection-1","name":"object-detection","papers":2},{"task":"/task/discourse-parsing","name":"Discourse Parsing","papers":1},{"task":"/task/image-classification","name":"Image Classification","papers":1},{"task":"/task/image-segmentation","name":"Image Segmentation","papers":1},{"task":"/task/medical-image-segmentation","name":"Medical Image Segmentation","papers":1},{"task":"/task/multiple-choice","name":"Multiple-choice","papers":1},{"task":"/task/object","name":"Object","papers":1},{"task":"/task/optical-flow-estimation","name":"Optical Flow Estimation","papers":1},{"task":"/task/segmentation","name":"Segmentation","papers":1},{"task":"/task/semi-supervised-medical-image-segmentation","name":"Semi-supervised Medical Image Segmentation","papers":1},{"task":"/task/sensitivity","name":"Sensitivity","papers":1},{"task":"/task/sentence","name":"Sentence","papers":1},{"task":"/task/sentence-ordering","name":"Sentence Ordering","papers":1},{"task":"/task/video-segmentation","name":"Video Segmentation","papers":1},{"task":"/task/video-semantic-segmentation","name":"Video Semantic Segmentation","papers":1},{"task":"/task/image-classification","name":"image-classification","papers":1}],"tasks_shown":20,"n_tasks":20,"usage_by_year":[{"year":"2020","papers":1},{"year":"2021","papers":1},{"year":"2022","papers":1},{"year":"2023","papers":3},{"year":"2024","papers":2}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/stac"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}