A Novel Framework for Trash Classification Using Deep Transfer Learning

Vo, Anh H.; Sơn, Lê Hoàng; Vo, Minh Thanh; Le, Tuong

doi:10.1109/access.2019.2959033

Cited by 155 publications

(70 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For instance, Adede et al [38] fine-tuned a pre-trained model namely ResNet on waste materials images. Vo et al [39] also employed a pre-trained model namely ResNext for classification of waste into organic, inorganic, and medical waste. In [40], a detailed comparison of deep learning and traditional methods have been provided.…”

Section: Waste Classificationmentioning

confidence: 99%

Active Learning Based Federated Learning for Waste and Natural Disaster Image Classification

et al. 2020

View full text Add to dashboard Cite

The feasibility of Federated Learning (FL) is highly dependent on the training and inference capabilities of local models, which are subject to the availability of meaningful and annotated data. The availability of such data is in turn contingent on the tedious and time-consuming annotation job that typically requires the manual analysis of training samples. Active Learning (AL) provides an alternative solution allowing a Machine Learning (ML) model to automatically choose and label the data from which it learns without involving manual inspection of each training sample. In this work, we explore how FL can benefit from unlabelled data available at each participating client using AL. To this aim, we propose an AL-based FL framework by employing and evaluating several AL methods in two different application domains. Through an extensive experimentation setup, we show that AL is equally useful in federated and centralized learning by achieving comparable results with manually labeled data using fewer samples without involving human annotators in collecting training data. We also demonstrated that the proposed method is dataset/application independent by evaluating the proposed method in two interesting applications, namely natural disaster analysis and waste classification, having different properties and challenges. Promising results are obtained on both applications resulting in comparable results against the best-case scenario where each sample is manually analyzed and annotated (Baseline 1), and improvement of 3.1% and 4% with best methods respectively over the training sets with irrelevant images on natural disaster and waste classification datasets (Baseline 2).

show abstract

Section: Waste Classificationmentioning

confidence: 99%

Active Learning Based Federated Learning for Waste and Natural Disaster Image Classification

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Similarly, Chu et al [ 28 ] proposed a hybrid CNN approach for waste classification with a dataset of 5000 waste objects. Vo et al [ 29 ] created another dataset VN-trash with 5904 images for deep transfer learning. Furthermore, Ramalingam et al [ 30 ] presented a debris classification model for floor-cleaning robots with a cascade CNN and an SVM.…”

Section: Related Workmentioning

confidence: 99%

A Multi-Level Approach to Waste Object Segmentation

Wang

Cai

Liang

et al. 2020

Sensors

View full text Add to dashboard Cite

We address the problem of localizing waste objects from a color image and an optional depth image, which is a key perception component for robotic interaction with such objects. Specifically, our method integrates the intensity and depth information at multiple levels of spatial granularity. Firstly, a scene-level deep network produces an initial coarse segmentation, based on which we select a few potential object regions to zoom in and perform fine segmentation. The results of the above steps are further integrated into a densely connected conditional random field that learns to respect the appearance, depth, and spatial affinities with pixel-level accuracy. In addition, we create a new RGBD waste object segmentation dataset, MJU-Waste, that is made public to facilitate future research in this area. The efficacy of our method is validated on both MJU-Waste and the Trash Annotation in Context (TACO) dataset.

show abstract

“…An event might be associated with a time point or not. Studies on sequential or temporal data are usually developed based on Markov model [14]- [17] or Recurrent neural network [18]- [21]. This is an interesting approach; however, sequential data and temporal features can sometimes be unavailable, and models based on these data usually require a high cost in time and computing for training.…”

Section: Related Workmentioning

confidence: 99%

A Variational Autoencoder Mixture Model for Online Behavior Recommendation

Nguyen

Cho

2020

IEEE Access

View full text Add to dashboard Cite

Online behavior recommendation is an attractive research topic related to social media mining. This topic focuses on suggesting suitable behaviors for users in online platforms, including music listening, video watching, e-commerce, to name but a few to improve the user experience, an essential factor for the success of online services. A successful online behavior recommendation system should have the ability to predict behaviors that users used to performs and also suggest behaviors that users never performed before. In this paper, we develop a mixture model that contains two components to address this problem. The first component is the user-specific preference component that represents the habits of users based on their behavior history. The second component is the latent group preference component based on variational autoencoder, a deep generative neural network. This component corresponds to the hidden interests of users and allows us to discover the unseen behavior of users. We conduct experiments on various real-world datasets with different characteristics to show the performance of our model in different situations. The result indicates that our proposed model outperforms the previous mixture models for recommendation problem. INDEX TERMS Online behavior recommendation, Mixture model, Variational autoencoder I. INTRODUCTION Recommending online user behavior is an essential component in many online platforms to improve the user experience. These platforms aim to predict behaviors such as listening to a song, watching a video, purchasing a product, that users are more likely to perform in the future and then suggest that behaviors to users. We can also understand behavior recommendation as suggesting consumed items for users. Thus, in this paper, we may use both term "behavior" and "item" with the same meaning.

show abstract

A Novel Framework for Trash Classification Using Deep Transfer Learning

Cited by 155 publications

References 27 publications

Active Learning Based Federated Learning for Waste and Natural Disaster Image Classification

Active Learning Based Federated Learning for Waste and Natural Disaster Image Classification

A Multi-Level Approach to Waste Object Segmentation

A Variational Autoencoder Mixture Model for Online Behavior Recommendation

Contact Info

Product

Resources

About