Semi-Supervised Object Detection
45 papers with code • 7 benchmarks • 1 datasets
Semi-supervised object detection uses both labeled data and unlabeled data for training. It not only reduces the annotation burden for training high-performance object detectors but also further improves the object detector by using a large number of unlabeled data.
Benchmarks
These leaderboards are used to track progress in Semi-Supervised Object Detection
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
Libraries
Use these libraries to find Semi-Supervised Object Detection models and implementations
COCO 10% labeled data
Most implemented papers
End-to-End Semi-Supervised Object Detection with Soft Teacher
microsoft/SoftTeacher
•
•
ICCV 2021
This paper presents an end-to-end semi-supervised object detection approach, in contrast to previous more complex multi-stage methods.
A Simple Semi-Supervised Learning Framework for Object Detection
google-research/ssl_detection
•
•
Semi-supervised learning (SSL) has a potential to improve the predictive performance of machine learning models using unlabeled data.
Unbiased Teacher for Semi-Supervised Object Detection
facebookresearch/unbiased-teacher
•
•
ICLR 2021
To address this, we introduce Unbiased Teacher, a simple yet effective approach that jointly trains a student and a gradually progressing teacher in a mutually-beneficial manner.
Efficient Teacher: Semi-Supervised Object Detection for YOLOv5
AlibabaResearch/efficientteacher
•
•
The Pseudo Label Assigner prevents the occurrence of bias caused by a large number of low-quality pseudo labels that may interfere with the Dense Detector during the student-teacher mutual learning mechanism, and the Epoch Adaptor utilizes domain and distribution adaptation to allow Dense Detector to learn globally distributed consistent features, making the training independent of the proportion of labeled data.
Label Matching Semi-Supervised Object Detection
hikvision-research/SSOD
•
•
CVPR 2022
To remedy this issue, we present a novel label assignment mechanism for self-training framework, namely proposal self-assignment, which injects the proposals from student into teacher and generates accurate pseudo labels to match each proposal in the student model accordingly.
Semi-DETR: Semi-Supervised Object Detection with Detection Transformers
PaddlePaddle/PaddleDetection
•
•
CVPR 2023
Specifically, we propose a Stage-wise Hybrid Matching strategy that combines the one-to-many assignment and one-to-one assignment strategies to improve the training efficiency of the first stage and thus provide high-quality pseudo labels for the training of the second stage.
Consistency-based Semi-supervised Learning for Object detection
soo89/CSD-RFCN
•
•
NeurIPS 2019
Making a precise annotation in a large dataset is crucial to the performance of object detection.
Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection
megvii-basedetection/denseteacher
•
•
To date, the most powerful semi-supervised object detectors (SS-OD) are based on pseudo-boxes, which need a sequence of post-processing with fine-tuned hyper-parameters.
Temporal Self-Ensembling Teacher for Semi-Supervised Object Detection
SYangDong/tse-t
•
•
(1) The teacher model serves a dual role as a teacher and a student, such that the teacher predictions on unlabeled images may be very close to those of student, which limits the upper-bound of the student.
Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework
hattrickcr7/SoftTeacher
•
•
CVPR 2021
To alleviate the confirmation bias problem and improve the quality of pseudo annotations, we further propose a co-rectify scheme based on Instant-Teaching, denoted as Instant-Teaching$^*$.
