Extended Feature Pyramid Network for Small Object Detection

Deng, Chunfang; Wang, Mengmeng; Liu, Liang; Liu, Yong; Jiang, Yunliang

doi:10.1109/tmm.2021.3074273

Cited by 218 publications

(108 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…mented nonmaximum suppression. We argue that this effect might be due to feature pyramid network scaling inaccuracies [13] that propagate throughout the iterations. Training the model during additional iterations is able to correct some of these inaccuracies.…”

Section: Resultsmentioning

confidence: 95%

Iterative Learning for Instance Segmentation

Sormunen¹,

Lämsä²,

López³

2022

Preprint

View full text Add to dashboard Cite

Instance segmentation is a computer vision task where separate objects in an image are detected and segmented. Stateof-the-art deep neural network models require large amounts of labeled data in order to perform well in this task. Making these annotations is time-consuming. We propose for the first time, an iterative learning and annotation method that is able to detect, segment and annotate instances in datasets composed of multiple similar objects. The approach requires minimal human intervention and needs only a bootstrapping set containing very few annotations. Experiments on two different datasets show the validity of the approach in different applications related to visual inspection.

show abstract

Section: Resultsmentioning

confidence: 95%

Iterative Learning for Instance Segmentation

Sormunen¹,

Lämsä²,

López³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Feature hierarchy ideas can be invested in the field of semantic segmentation by combining the low-level features with high-level features in a top-down module and skip connections. This module upsamples spatially coarser feature maps from higher pyramid levels and then tunes them with features from the bottom-up module [ 29 , 30 ]. Each skip connection merges between two feature maps of the same dimensions so that one comes from the bottom-up path and the other one comes from the top-down path.…”

Section: Preliminaries and Discussionmentioning

confidence: 99%

Intelligent Semantic Segmentation for Self-Driving Vehicles Using Deep Learning

Sellat

Bisoy

Priyadarshini

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Understanding the situation is a critical component of any self-driving system. Accurate real-time visual signal processing to create pixelwise classed pictures, also known as semantic segmentation, is critical for scenario comprehension and subsequent acceptance of this new technology. Due to the intricate interaction between pixels in each frame of the received camera data, such efficiency in terms of processing time and accuracy could not be achieved prior to recent advances in deep learning algorithms. We present an effective approach for semantic segmentation for self-driving automobiles in this study. We combine deep learning architectures like convolutional neural networks and autoencoders, as well as cutting-edge approaches like feature pyramid networks and bottleneck residual blocks, to develop our model. The CamVid dataset, which has undergone considerable data augmentation, is utilised to train and test our model. To validate the suggested model, we compare the acquired findings to various baseline models reported in the literature.

show abstract

“…3D Object Detection. In recent years, with the continuous improvement of the accuracy of object detection of images [16]- [21], [78]- [80], 3D object detection [81]- [84] has received unprecedented attention. The purpose of 3D object detection is to detect object instances in the point cloud using 3D bounding boxes.…”

Section: B Application Directionsmentioning

confidence: 99%

Deep Learning for Weakly-Supervised Object Detection and Object Localization: A Survey

Shao¹,

Chen²,

Shao³

et al. 2021

Preprint

View full text Add to dashboard Cite

Weakly-Supervised Object Detection (WSOD) and Localization (WSOL), i.e., detecting multiple and single instances with bounding boxes in an image using image-level labels, are long-standing and challenging tasks in the CV community. With the success of deep neural networks in object detection, both WSOD and WSOL have received unprecedented attention. Hundreds of WSOD and WSOL methods and numerous techniques have been proposed in the deep learning era. To this end, in this paper, we consider WSOL is a sub-task of WSOD and provide a comprehensive survey of the recent achievements of WSOD. Specifically, we firstly describe the formulation and setting of the WSOD, including the background, challenges, basic framework. Meanwhile, we summarize and analyze all advanced techniques and training tricks for improving detection performance. Then, we introduce the widely-used datasets and evaluation metrics of WSOD. Lastly, we discuss the future directions of WSOD. We believe that these summaries can help pave a way for future research on WSOD and WSOL.

show abstract

Extended Feature Pyramid Network for Small Object Detection

Cited by 218 publications

References 34 publications

Iterative Learning for Instance Segmentation

Iterative Learning for Instance Segmentation

Intelligent Semantic Segmentation for Self-Driving Vehicles Using Deep Learning

Deep Learning for Weakly-Supervised Object Detection and Object Localization: A Survey

Contact Info

Product

Resources

About