PseudoProp: Robust Pseudo-Label Generation for Semi-Supervised Object Detection in Autonomous Driving Systems

@article{Hu2022PseudoPropRP,
  title={PseudoProp: Robust Pseudo-Label Generation for Semi-Supervised Object Detection in Autonomous Driving Systems},
  author={Shu Hu and Chunfang Liu and Jayanta K. Dutta and Ming-Ching Chang and Siwei Lyu and Naveen Ramakrishnan},
  journal={2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year={2022},
  pages={4389-4397}
}
Semi-supervised object detection methods are widely used in autonomous driving systems, where only a fraction of objects are labeled. To propagate information from the labeled objects to the unlabeled ones, pseudo-labels for unlabeled objects must be generated. Although pseudo-labels have proven to improve the performance of semi-supervised object detection significantly, the applications of image-based methods to video frames result in numerous miss or false detections using such generated… 

Contrastive Class-Specific Encoding for Few-Shot Object Detection

TLDR
A new few-shot object detection framework is proposed that introduces a new contrastive branch to extract the class representation of images, which improves the generalization performance of the detection model for novel classes.

Object Detection for Autonomous Dozers

TLDR
A new type of autonomous vehicle is introduced – an autonomous dozer that is expected to complete construction site tasks in an efficient, robust, and safe manner and two well-known object detection models are trained, and their performances are benchmarked with a wide range of training strategies and hyperparameters.

References

SHOWING 1-10 OF 39 REFERENCES

PseudoSeg: Designing Pseudo Labels for Semantic Segmentation

TLDR
This work presents a simple and novel re-design of pseudo-labeling to generate well-calibrated structured pseudo labels for training with unlabeled or weakly-labeled data and demonstrates the effectiveness of the proposed pseudo- labeling strategy in both low-data and high-data regimes.

A Simple Semi-Supervised Learning Framework for Object Detection

TLDR
STAC is proposed, a simple yet effective SSL framework for visual object detection along with a data augmentation strategy that deploys highly confident pseudo labels of localized objects from an unlabeled image and updates the model by enforcing consistency via strong augmentations.

Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning

TLDR
This work shows that a naive pseudo-labeling overfits to incorrect pseudo-labels due to the so-called confirmation bias and demonstrates that mixup augmentation and setting a minimum number of labeled samples per mini-batch are effective regularization techniques for reducing it.

Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation

TLDR
The Naive-Student model, trained with such simple yet effective iterative semi-supervised learning, attains state-of-the-art results at all three Cityscapes benchmarks, reaching the performance of 67.8% PQ, 42.6% AP, and 85.2% mIOU on the test set.

Semi-Supervised Self-Training of Object Detection Models

TLDR
The key contributions of this empirical study are to demonstrate that a model trained in this manner can achieve results comparable to a modeltrained in the traditional manner using a much larger set of fully labeled data, and that a training data selection metric that is defined independently of the detector greatly outperforms a selection metric based on the detection confidence generated by the detector.

Watch and learn: Semi-supervised learning of object detectors from videos

We present a semi-supervised approach that localizes multiple unknown object instances in long videos. We start with a handful of labeled boxes and iteratively learn and label hundreds of thousands

Humble Teachers Teach Better Students for Semi-Supervised Object Detection

We propose a semi-supervised approach for contemporary object detectors following the teacher-student dual model framework. Our method 1 is featured with 1) the exponential moving averaging strategy

Improving Semantic Segmentation via Video Propagation and Label Relaxation

TLDR
This paper presents a video prediction-based methodology to scale up training sets by synthesizing new training samples in order to improve the accuracy of semantic segmentation networks, and introduces a novel boundary label relaxation technique that makes training robust to annotation noise and propagation artifacts along object boundaries.

R-FCN: Object Detection via Region-based Fully Convolutional Networks

TLDR
This work presents region-based, fully convolutional networks for accurate and efficient object detection, and proposes position-sensitive score maps to address a dilemma between translation-invariance in image classification and translation-variance in object detection.

CAD: Scale Invariant Framework for Real-Time Object Detection

TLDR
A novel CAD framework to improve detection accuracy while preserving the real-time speed is proposed and maxout is introduced to approximate the correlation between image pixels and network predictions to enhance the generalization ability of the proposed framework.