Description
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 . The strong augmentations are applied for augmentation consistency during the model training. Target boxes are augmented when global geometric transformations are used.
Papers Using This Method
Shape Transformation Driven by Active Contour for Class-Imbalanced Semi-Supervised Medical Image Segmentation2024-10-18STAC: Leveraging Spatio-Temporal Data Associations For Efficient Cross-Camera Streaming and Analytics2024-01-27Structured Dialogue Discourse Parsing2023-06-26Systematic Architectural Design of Scale Transformed Attention Condenser DNNs via Multi-Scale Class Representational Response Similarity Analysis2023-06-16Discourse Structure Extraction from Pre-Trained and Fine-Tuned Language Models in Dialogues2023-02-12DNN-Driven Compressive Offloading for Edge-Assisted Semantic Video Segmentation2022-03-28Humble Teachers Teach Better Students for Semi-Supervised Object Detection2021-06-19A Simple Semi-Supervised Learning Framework for Object Detection2020-05-10