Weakly-supervised butterfly detection based on saliency map

Given the actual needs for detecting multiple features of butterflies in natural ecosystems, this paper pro-poses a model of weakly-supervised butterfly detection based on a saliency map (WBD-SM) to enhance the accuracy of butterfly detection in the ecological environment as well as to overcome the difficulty of fine annotation. Our proposed model first extracts the features of different scales using the VGG16 with-out the fully connected layers as the backbone network. Next, the saliency maps of butterfly images are extracted using the deep supervision network with shortcut connections (DSS) used for the butterfly tar-get location. The class activation maps of butterfly images are derived via the adversarial complementary learning (ACoL) network for butterfly target recognition. Then, the saliency and class activation maps are post-processed with conditional random fields, thereby obtaining the refined saliency maps of butterfly objects. Finally, the locations of the butterflies are acquired based on the saliency maps. Experimental re-sults on the 20 categories of butterfly dataset collected in this paper indicate that the WBD-SM achieves a higher recognition accuracy than that of the VGG16 under different division ratios. At the same time, when the training set and test set are 8:2, our WBD-SM attains a 95.67% localization accuracy, which is 9.37% and 11.87% higher than the results of the DSS and ACoL, respectively. Compared with three state-of-the-art fully-supervised object detection networks, RefineDet, YOLOv3 and single-shot detection (SSD), the detection performance of our WBD-SM is better than RefineDet, and YOLOv3, and is almost the same as SSD.(c) 2023 Elsevier Ltd. All rights reserved.

Automated summary

This paper proposes a weakly-supervised butterfly detection model based on a saliency map (WBD-SM) to enhance the accuracy of butterfly detection in the ecological environment. Experimental results show that WBD-SM achieves higher recognition accuracy than VGG16 under different division ratios.