Data Augmented Dual-Attention Interactive Image Classification Network

Zhu, Qiangxi; Li, Zhixin

doi:10.1007/978-3-031-15934-3_7

Cited by 2 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…TransFG [71] reports 94.8% accuracy and some regularization techniques can be employed to overcome the overfitting issue brought by PSM. Data Augmented Dual-Attention Interactive Network (DADAINet) [78] utilizes dual attention which comprises LSTM and MHSA to recalibrate the feature responses based on their importance. The resultant feature maps then undergo Channel Interaction and Local Feature Fusion module for the generation of more discriminative features.…”

Section: ) Quantitative Analysismentioning

confidence: 99%

Coarse-to-Fine Context Aggregation Network for Vehicle Make and Model Recognition

Tan,

Chuah,

Chow

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Vehicle Make and Model Recognition (VMMR) is one of the fundamental elements in Intelligent Transportation System (ITS) that becomes the enabler for plenty of downstream tasks. Most of the past studies advance the recognition performance by focusing on the top-level feature maps but this practice hinders the ability of the network to learn features. Although the top-level feature maps are rich in global context information, they do not incorporate the fine-scale details that are embedded within the low-level feature maps. In this work, we bridge the gap by proposing a Coarse-to-Fine Context Aggregation (CFCA) module which effectively integrates information from feature maps of various scales. In particular, the crossscale features are generated by first refining the scale-specific components independently and then fusing them in a nonlinear manner through convolution. The resultant multi-scale feature maps are highly discriminative, as they contain both local subtle details and global abstract information. This is proven when the proposed framework achieves astounding classification performance on five publicly available datasets i.e. web-nature Comprehensive Cars (CompCars), Stanford Cars, Car-FG3K, surveillance-nature CompCars and Mohsin-VMMR. Moreover, the neurons exhibit high feature responses on the discriminative vehicle parts, corresponding to the superior feature extraction ability of the CFCA module. The CFCA module is also highly generalizable to other networks as it elevates the performance of VGG16, Inceptionv3, ResNet50 and DenseNet169.

show abstract

Section: ) Quantitative Analysismentioning

confidence: 99%