Proposal Learning for Semi-Supervised Object Detection

@article{Tang2021ProposalLF,
  title={Proposal Learning for Semi-Supervised Object Detection},
  author={Peng Tang and Chetan Ramaiah and Ran Xu and Caiming Xiong},
  journal={2021 IEEE Winter Conference on Applications of Computer Vision (WACV)},
  year={2021},
  pages={2290-2300}
}
In this paper, we focus on semi-supervised object detection to boost performance of proposal-based object detectors (a.k.a. two-stage object detectors) by training on both labeled and unlabeled data. However, it is non-trivial to train object detectors on unlabeled data due to the un-availability of ground truth labels. To address this problem, we present a proposal learning approach to learn proposal features and predictions from both labeled and unlabeled data. The approach consists of a self… 

Figures and Tables from this paper

Sparsely Annotated Object Detection: A Region-based Semi-supervised Approach
TLDR
This work revisits the formulation of sparsely annotated object detection and proposes a region-based semi-supervised algorithm, that automatically identifies regions containing unlabeled foreground objects and achieves competitive performance on standard semi- supervised setups demonstrating the strength and broad applicability of the approach.
Label Matching Semi-Supervised Object Detection
TLDR
A novel label assignment mech-anism 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 is presented.
Unbiased Teacher for Semi-Supervised Object Detection
TLDR
This work revisits the Semi-Supervised Object Detection (SS-OD) and identifies the pseudo-labeling bias issue in SSOD, and introduces Unbiased Teacher, a simple yet effective approach that jointly trains a student and a gradually progressing teacher in a mutually-beneficial manner.
Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection
TLDR
This paper comprehensively considers divergent types of unlabeled images according to their difficulty levels, utilize them in different phases, and ensemble models from different phases together to generate ultimate results.
End-to-End Semi-Supervised Object Detection with Soft Teacher
TLDR
This paper presents an end-to-end semi-supervised object detection approach, in contrast to previous more complex multi-stage methods, and proposes two simple yet effective techniques within this framework: a soft teacher mechanism where the classification loss of each unlabeled bounding box is weighed by the classification score produced by the teacher network.
Interactive Self-Training with Mean Teachers for Semi-supervised Object Detection
TLDR
This paper proposes an interactive form of self-training using mean teachers for semi-supervised object detection using nonmaximum suppression to fuse the detection results from different iterations, and uses a mean teacher model instead of the original detection model to predict the pseudo labels.
Active Learning Strategies for Weakly-supervised Object Detection
TLDR
Experiments show that BiB outperforms other active learning techniques and significantly improves the base weakly-supervised detector’s performance with only a few fully-annotated images per class, showing a good trade-off between performance and data efficiency.
Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework
TLDR
Instant-Teaching is proposed, a completely end-to-end and effective SSOD framework, which uses instant pseudo labeling with extended weak-strong data augmentations for teaching during each training iteration, which surpasses state-of-the-art methods by 4.2 mAP on MS-COCO when using 2% labeled data.
Temporal Self-Ensembling Teacher for Semi-Supervised Object Detection
TLDR
A novel SSOD model called Temporal Self-Ensembling Teacher (TSET) is proposed, which ensembles its temporal predictions for unlabeled images under stochastic perturbations, and automatically reweights the inconsistent predictions, which preserves the knowledge for difficult objects to detect in the unlabeling images.
Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free and Anchor-based Detectors
TLDR
This paper presents Unbiased Teacher v2, which shows the generalization of SS-OD method to anchor-free detectors and also introduces Listen2Student mechanism for the unsupervised regression loss and develops a novel pseudo-labeling selection mechanism based on the Teacher and Student’s relative uncertainties.
...
...

References

SHOWING 1-10 OF 67 REFERENCES
Semi-supervised Object Detection with Unlabeled Data
TLDR
This work proposes an Expectation-Maximization method for semisupervised object detection with unlabeled images, and estimates the latent labels and optimize the model for both classification part and localization part of object detection.
Consistency-based Semi-supervised Learning for Object detection
TLDR
A Consistency-based Semi-supervised learning method for object Detection (CSD), which is a way of using consistency constraints as a tool for enhancing detection performance by making full use of available unlabeled data.
Large Scale Semi-Supervised Object Detection Using Visual and Semantic Knowledge Transfer
TLDR
Strong evidence is found that visual similarity and semantic relatedness are complementary for the task, and when combined notably improve detection, achieving state-of-the-art detection performance in a semi-supervised setting.
NOTE-RCNN: NOise Tolerant Ensemble RCNN for Semi-Supervised Object Detection
TLDR
A novel NOise Tolerant Ensemble RCNN (NOTE-RCNN) object detector is proposed, in which a few seed box level annotations and a large scale of image level annotations are used to train the detector.
Weakly Supervised Object Localization with Multi-Fold Multiple Instance Learning
TLDR
This work follows a multiple-instance learning approach that iteratively trains the detector and infers the object locations in the positive training images and proposes a window refinement method, which improves the localization accuracy by incorporating an objectness prior.
Unsupervised Feature Learning via Non-parametric Instance Discrimination
TLDR
This work forms this intuition as a non-parametric classification problem at the instance-level, and uses noise-contrastive estimation to tackle the computational challenges imposed by the large number of instance classes.
You Only Look Once: Unified, Real-Time Object Detection
TLDR
Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.
Unsupervised Data Augmentation for Consistency Training
TLDR
A new perspective on how to effectively noise unlabeled examples is presented and it is argued that the quality of noising, specifically those produced by advanced data augmentation methods, plays a crucial role in semi-supervised learning.
LSDA: Large Scale Detection through Adaptation
TLDR
This paper proposes Large Scale Detection through Adaptation (LSDA), an algorithm which learns the difference between the two tasks and transfers this knowledge to classifiers for categories without bounding box annotated data, turning them into detectors.
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TLDR
This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%.
...
...