Realize your surroundings: Exploiting context information for small object detection

Leng, Jiaxu; Ren, Yihui; Jiang, Wen; Sun, Xiaoding; Wang, Ye

doi:10.1016/j.neucom.2020.12.093

Cited by 59 publications

(17 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The specific process includes several steps: the collection of English text data, the preprocessing of English text data, the vectorization of the obtained data, and the establishment of the optimal DNN model and test. The collected English text semantic data are divided into two parts: a test set and a training set [ 16 , 17 ].…”

Section: Model Establishment and Scheme Designmentioning

confidence: 99%

Application of Dual‐Channel Convolutional Neural Network Algorithm in Semantic Feature Analysis of English Text Big Data

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The current Internet data explosion is expecting an ever-higher demand for text emotion analysis that greatly facilitates public opinion analysis and trend prediction, among others. Therefore, this paper proposes to use a dual-channel convolutional neural network (DCNN) algorithm to analyze the semantic features of English text big data. Following the analysis of the effect of CNN, artificial neural network (ANN), and recurrent neural network (RNN) on English text data analysis, the more effective long short-term memory (LSTM) and the gated recurrent unit (GRU) neural network (NN) are introduced, and each network is combined with the dual-channel CNN, respectively, and comprehensively analyzed under comparative experiments. Second, the semantic features of English text big data are analyzed through the improved SO-pointwise mutual information (SO-PMI) algorithm. Finally, the ensemble dual-channel CNN model is established. Under the comparative experiment, GRU NN has a better feature detection effect than LSTM NN, but the performance increase from dual-channel CNN to GRU NN + dual-channel CNN is not obvious. Under the comparative analysis of GRU NN + dual-channel CNN model and LSTM NN + dual-channel CNN model, GRU NN + dual-channel CNN model ensures the high accuracy of semantic feature analysis and improves the analysis speed of the model. Further, after the attention mechanism is added to the GRU NN + dual-channel CNN model, the accuracy of semantic feature analysis of the model is improved by nearly 1.3%. Therefore, the ensemble model of GRU NN + dual-channel CNN + attention mechanism is more suitable for semantic feature analysis of English text big data. The results will help the e-commerce platform to analyze the evaluation language and semantic features for the current network English short texts.

show abstract

Section: Model Establishment and Scheme Designmentioning

confidence: 99%

Application of Dual‐Channel Convolutional Neural Network Algorithm in Semantic Feature Analysis of English Text Big Data

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…These models are used as backbone network in EfficientDet and Scaled-Yolov4 respectively. Feature pyramid network in object detection enhances feature extraction that improves overall mAP [21]. And, performing scaling on the feature pyramid network and final image classification and bounding box regression modules in the model improves mAP in object detection even further [13].…”

Section: Related Workmentioning

confidence: 99%

“…In object detection, objects that fall in the 32x32 pixel or lower category are categorized as small objects [21]. Plastic waste can be of varied sizes such as small medium or large sizes.…”

Section: Related Workmentioning

confidence: 99%

“…Plastic waste can be of varied sizes such as small medium or large sizes. Traditional object detection models show poor performance on small objects [21,22]. Whereas, current state-of-the-art object detection models, Scaled-Yolov4 and Efficient-Det, confirm an increase in the performance of small, medium as well as large objects with their backbone neural network architecture and feature pyramid network [13,14].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

An Object Detection and Scaling Model for Plastic Waste Sorting

Padalkar¹,

Pathak²,

Stynes³

2021

Proceedings of the 1st International Conference on AI for People: Towards Sustainable AI, CAIP 2021, 20-24 November 2021, Bolog

View full text Add to dashboard Cite

Plastic waste sorting involves the separation of plastic into its individual plastic types. This research proposes an Object Detection and Scaling Model for plastic waste sorting to detect four types of plastics using the WaDaBa dataset. This research compares the Object Detection and Scaling Models Scaled-Yolov4 and EfficientDet. Results demonstrate that Scaled-Yolov4-CSP outperforms the state of the art, Colour-Histogram based Canny-Edge-Gaussian Filter, by 21% accuracy.

show abstract

“…the door) where it is located. Related works [21,22] also show that context information from the surroundings of small objects could provide important cues for successful detection. In this work, in the labeling stage, instead of performing relabeling by humans, we first apply an automatic approach to enhance the tight bounding box for each small object to include some local context information before the training stage.…”

Section: Introductionmentioning

confidence: 98%

MultiCLU: Multi-stage Context Learning and Utilization for Storefront Accessibility Detection and Evaluation

Wang

Chen

Tang

et al. 2022

Proceedings of the 2022 International Conference on Multimedia Retrieval

View full text Add to dashboard Cite

In this work, a storefront accessibility image dataset is collected from Google street view and is labeled with three main objects for storefront accessibility: doors (for store entrances), doorknobs (for accessing the entrances) and stairs (for leading to the entrances). Then MultiCLU, a new multi-stage context learning and utilization approach, is proposed with the following four stages: Context in Labeling (CIL), Context in Training (CIT), Context in Detection (CID) and Context in Evaluation (CIE). The CIL stage automatically extends the label for each knob to include more local contextual information. In the CIT stage, a deep learning method is used to project the visual information extracted by a Faster R-CNN based object detector to semantic space generated by a Graph Convolutional Network. The CID stage uses the spatial relation reasoning between categories to refine the confidence score. Finally in the CIE stage, a new loose evaluation metric for storefront accessibility, especially for knob category, is proposed to efficiently help BLV users to find estimated knob locations. Our experiment results show that the proposed MultiCLU framework can achieve significantly better performance than the baseline detector using Faster R-CNN, with +13.4% on mAP and +15.8% on recall, respectively. Our new evaluation metric also introduces a new way to evaluate storefront accessibility objects, which could benefit BLV group in real life. CCS CONCEPTS• Computing methodologies → Computer vision; Deep Learning.

show abstract

Realize your surroundings: Exploiting context information for small object detection

Cited by 59 publications

References 34 publications

Application of Dual‐Channel Convolutional Neural Network Algorithm in Semantic Feature Analysis of English Text Big Data

Application of Dual‐Channel Convolutional Neural Network Algorithm in Semantic Feature Analysis of English Text Big Data

An Object Detection and Scaling Model for Plastic Waste Sorting

MultiCLU: Multi-stage Context Learning and Utilization for Storefront Accessibility Detection and Evaluation

Contact Info

Product

Resources

About