Co-Training for Deep Object Detection: Comparing Single-Modal and Multi-Modal Approaches

Gómez, Jonatan; Villalonga, Gabriel; López, Antonio

doi:10.3390/s21093185

Cited by 4 publications

(3 citation statements)

References 29 publications

(67 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It uses unlabeled samples to improve prediction accuracy. In the cotraining process, random sampling is used to gradually select unlabeled samples to train classifiers [ 39 ]. An algorithm flowchart of cotraining is shown in Figure 2 .…”

Section: Methodsmentioning

confidence: 99%

A Cotraining-Based Semisupervised Approach for Remaining-Useful-Life Prediction of Bearings

Yan

Xia

Wang

et al. 2022

Sensors

View full text Add to dashboard Cite

The failure of bearings can have a significant negative impact on the safe operation of equipment. Recently, deep learning has become one of the focuses of RUL prediction due to its potent scalability and nonlinear fitting ability. The supervised learning process in deep learning requires a significant quantity of labeled data, but data labeling can be expensive and time-consuming. Cotraining is a semisupervised learning method that reduces the quantity of required labeled data through exploiting available unlabeled data in supervised learning to boost accuracy. This paper innovatively proposes a cotraining-based approach for RUL prediction. A CNN and an LSTM were cotrained on large amounts of unlabeled data to obtain a health indicator (HI), then the monitoring data were entered into the HI and the RUL prediction was realized. The effectiveness of the proposed approach was compared and analyzed against individual CNN and LSTM and the stacking networks SAE+LSTM and CNN+LSTM in the existing literature using RMSE and MAPE values on a PHM 2012 dataset. The results demonstrate that the RMSE and MAPE value of the proposed approach are superior to individual CNN and LSTM, and the RMSE value of the proposed approach is 54.72, which is significantly lower than SAE+LSTM (137.12), and close to CNN+LSTM (49.36). The proposed approach has also been tested successfully on a real-world task and thus has strong application value.

show abstract

Section: Methodsmentioning

confidence: 99%

A Cotraining-Based Semisupervised Approach for Remaining-Useful-Life Prediction of Bearings

Yan

Xia

Wang

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Co-learning can be parallel, non-parallel or hybrid depending on the training resourced. In [39], cotraining RGB-D and single modal are placed on a scale. The results show that multi-modal approach is more effective in the task of producing a pseudo-labeled object bounding boxes.…”

Section: B Multi-modal Learningmentioning

confidence: 99%

A Fusion of RGB Features and Local Descriptors for Object Detection in Road Scene

Dinh Nguyen

2024

IEEE Access

View full text Add to dashboard Cite

Many texture descriptors have been introduced in recent years to improve texture analysis and classification outcomes, which are important in many computer vision tasks including object recognition and detection, human detector, and especially in face recognition. Local pattern is a texture descriptor that can successfully extract distinctive texture features that possesses noise and illumination variance robustness. This paper focuses on making use of local pattern features in boosting object detection models in a multimodal fusion paradigm to acquire reliable feature maps in forward propagation throughout the network regardless of variations in photo taking conditions. We propose an adaptive fusion architecture for RGB and Local Ternary Pattern information. This architecture leverage local pattern to enrich information of original feature maps and adapt to many object detection models. Our local pattern fusion network concentrates on backbone and neck modules with an simple and efficient operation. The notable accuracy advancement is 8.03% observed in Cascade R-CNN in KITTI Dataset. In difficult conditions, our fusion models significantly lift the original performance from 4.7% to 66.3% mAP score.INDEX TERMS Multi-modal fusion, object detection, local pattern.

show abstract

“…In previous works, we successfully applied a co-training pattern under the synth-to-real UDA setting for deep object detection [ 31 , 32 ]. This encourages us to address the challenging problem of semantic segmentation under the same setting by proposing a new co-training procedure, which is summarized in Figure 1 .…”

Section: Introductionmentioning

confidence: 99%

Co-Training for Unsupervised Domain Adaptation of Semantic Segmentation Models

Gómez

Villalonga

López

2023

Sensors

Self Cite

View full text Add to dashboard Cite

Semantic image segmentation is a core task for autonomous driving, which is performed by deep models. Since training these models draws to a curse of human-based image labeling, the use of synthetic images with automatically generated labels together with unlabeled real-world images is a promising alternative. This implies addressing an unsupervised domain adaptation (UDA) problem. In this paper, we propose a new co-training procedure for synth-to-real UDA of semantic segmentation models. It performs iterations where the (unlabeled) real-world training images are labeled by intermediate deep models trained with both the (labeled) synthetic images and the real-world ones labeled in previous iterations. More specifically, a self-training stage provides two domain-adapted models and a model collaboration loop allows the mutual improvement of these two models. The final semantic segmentation labels (pseudo-labels) for the real-world images are provided by these two models. The overall procedure treats the deep models as black boxes and drives their collaboration at the level of pseudo-labeled target images, i.e., neither modifying loss functions is required, nor explicit feature alignment. We test our proposal on standard synthetic and real-world datasets for onboard semantic segmentation. Our procedure shows improvements ranging from approximately 13 to 31 mIoU points over baselines.

show abstract

Co-Training for Deep Object Detection: Comparing Single-Modal and Multi-Modal Approaches

Cited by 4 publications

References 29 publications

A Cotraining-Based Semisupervised Approach for Remaining-Useful-Life Prediction of Bearings

A Cotraining-Based Semisupervised Approach for Remaining-Useful-Life Prediction of Bearings

A Fusion of RGB Features and Local Descriptors for Object Detection in Road Scene

Co-Training for Unsupervised Domain Adaptation of Semantic Segmentation Models

Contact Info

Product

Resources

About