Deep Residual Learning for Image Recognition: A Survey
Deep Residual Networks have recently been shown to significantly improve the performance of neural networks trained on ImageNet, with results beating all previous methods on this dataset by large margins in the image classification task. However, the meaning of these impressive numbers and their imp...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/18/8972 |
| _version_ | 1797491587043819520 |
|---|---|
| author | Muhammad Shafiq Zhaoquan Gu |
| author_facet | Muhammad Shafiq Zhaoquan Gu |
| author_sort | Muhammad Shafiq |
| collection | DOAJ |
| description | Deep Residual Networks have recently been shown to significantly improve the performance of neural networks trained on ImageNet, with results beating all previous methods on this dataset by large margins in the image classification task. However, the meaning of these impressive numbers and their implications for future research are not fully understood yet. In this survey, we will try to explain what Deep Residual Networks are, how they achieve their excellent results, and why their successful implementation in practice represents a significant advance over existing techniques. We also discuss some open questions related to residual learning as well as possible applications of Deep Residual Networks beyond ImageNet. Finally, we discuss some issues that still need to be resolved before deep residual learning can be applied on more complex problems. |
| first_indexed | 2024-03-10T00:51:26Z |
| format | Article |
| id | doaj.art-ebb2e4c338dd4079948b6608174aa7fc |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T00:51:26Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-ebb2e4c338dd4079948b6608174aa7fc2023-11-23T14:51:04ZengMDPI AGApplied Sciences2076-34172022-09-011218897210.3390/app12188972Deep Residual Learning for Image Recognition: A SurveyMuhammad Shafiq0Zhaoquan Gu1Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou 510006, ChinaDepartment of New Networks, Peng Cheng Laboratory, Shenzhen 518055, ChinaDeep Residual Networks have recently been shown to significantly improve the performance of neural networks trained on ImageNet, with results beating all previous methods on this dataset by large margins in the image classification task. However, the meaning of these impressive numbers and their implications for future research are not fully understood yet. In this survey, we will try to explain what Deep Residual Networks are, how they achieve their excellent results, and why their successful implementation in practice represents a significant advance over existing techniques. We also discuss some open questions related to residual learning as well as possible applications of Deep Residual Networks beyond ImageNet. Finally, we discuss some issues that still need to be resolved before deep residual learning can be applied on more complex problems.https://www.mdpi.com/2076-3417/12/18/8972deep residual learning for image recognitiondeep residual learningimage processingimage recognition |
| spellingShingle | Muhammad Shafiq Zhaoquan Gu Deep Residual Learning for Image Recognition: A Survey Applied Sciences deep residual learning for image recognition deep residual learning image processing image recognition |
| title | Deep Residual Learning for Image Recognition: A Survey |
| title_full | Deep Residual Learning for Image Recognition: A Survey |
| title_fullStr | Deep Residual Learning for Image Recognition: A Survey |
| title_full_unstemmed | Deep Residual Learning for Image Recognition: A Survey |
| title_short | Deep Residual Learning for Image Recognition: A Survey |
| title_sort | deep residual learning for image recognition a survey |
| topic | deep residual learning for image recognition deep residual learning image processing image recognition |
| url | https://www.mdpi.com/2076-3417/12/18/8972 |
| work_keys_str_mv | AT muhammadshafiq deepresiduallearningforimagerecognitionasurvey AT zhaoquangu deepresiduallearningforimagerecognitionasurvey |