ML-CapsNet meets VB-DI-D: A novel distortion-tolerant baseline for perturbed object recognition

Lin, Zhongqi; Zheng, Zengwei; Jia, Jingdun; Gao, Wanlin; Huang, Feng

doi:10.1016/j.engappai.2023.105937

Cited by 4 publications

(2 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, most of the available databases do not consider real-world scenarios, especially images and videos captured in uncontrolled environments, which are affected by various types of distortions. In fact, many studies have shown that OD performance is strongly influenced by the quality of the images [5], [6], [12], [13], [7]. It is worth noticing that the number and types of distortions considered in these studies and the existing dedicated dataset are limited.…”

Section: Related Workmentioning

confidence: 99%

“…OD is still a hot topic and many methods have been proposed during these last two decades [3], [4]. However, the impact of the distortions on the performance of the proposed OD solutions was often neglected apart a few studies limited to object recognition and image classification under specific distortions (noise and blur) [5] and OD under photometric and geometric distortions [6]. A previous study [7] highlighted the distortion impact on the OD performance through global and local distortions without any scene context consideration have been achieved, which proved the usefulness of data augmentation by using a distorted database to improve OD models robustness.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

CD-COCO: A Versatile Complex Distorted COCO Database for Scene-Context-Aware Computer Vision

Beghdadi,

Mallem

et al. 2023

2023 11th European Workshop on Visual Information Processing (EUVIP)

View full text Add to dashboard Cite

The recent development of deep learning methods applied to vision has enabled their increasing integration into real-world applications to perform complex Computer Vision (CV) tasks. However, image acquisition conditions have a major impact on the performance of high-level image processing. A possible solution to overcome these limitations is to artificially augment the training databases or to design deep learning models that are robust to signal distortions. We opt here for the first solution by enriching the database with complex and realistic distortions which were ignored until now in the existing databases. To this end, we built a new versatile database derived from the well-known MS-COCO database to which we applied local and global photo-realistic distortions. These new local distortions are generated by considering the scene context of the images that guarantees a high level of photo-realism. Distortions are generated by exploiting the depth information of the objects in the scene as well as their semantics. This guarantees a high level of photo-realism and allows to explore real scenarios ignored in conventional databases dedicated to various CV applications. Our versatile database offers an efficient solution to improve the robustness of various CV tasks such as Object Detection (OD), scene segmentation, and distortion-type classification methods. The image database, scene classification index, and distortion generation codes are publicly available 1 .

show abstract