Insect pests are one of the main threats to the commercially important crops. An effective insect pest recognition method can avoid economic losses. In this paper, we proposed a new and simple structure based on the original residual block and named as feature reuse residual block which combines feature from the input signal of a residual block with the residual signal. In each feature reuse residual block, it enhances the capacity of representation by learning half and reuse half feature. By stacking the feature reuse residual block, we obtained the feature reuse residual network (FR-ResNet) and evaluated the performance on IP102 benchmark dataset. The experimental results showed that FR-ResNet can achieve significant performance improvement in terms of insect pest classification. Moreover, to demonstrate the adaptive of our approach, we applied it to various kinds of residual networks, including ResNet, Pre-ResNet, and WRN, and we tested the performance on a series of benchmark datasets: CIFAR-10, CIFAR-100, and SVHN. The experimental results showed that the performance can be improved obviously than original networks. Based on these experiments on CIFAR-10, CIFAR-100, SVHN, and IP102 benchmark datasets, it demonstrates the effectiveness of our approach.

Earlier insect pest recognition is one of the critical factors for agricultural yield. Thus, an effective method to recognize the category of insect pests has become significant issues in the agricultural field. In this paper, we proposed a new residual block to learn multi-scale representation. In each block, it contains three branches: one is parameter-free, and the others contain several successive convolution layers. Moreover, we proposed a module and embedded it into the new residual block to recalibrate the channel-wise feature response and to model the relationship of the three branches. By stacking this kind of block, we constructed the Deep Multi-branch Fusion Residual Network (DMF-ResNet). For evaluating the model performance, we first test our model on CIFAR-10 and CIFAR-100 benchmark datasets. The experimental results show that DMF-ResNet outperforms the baseline models significantly. Then, we construct DMF-ResNet with different depths for high-resolution image classification tasks and apply it to recognize insect pests. We evaluate the model performance on the IP102 dataset, and the experimental results show that DMF-ResNet could achieve the best accuracy performance than the baseline models and other state-of-art methods. Based on these empirical experiments, we demonstrate the effectiveness of our approach.

Crop diseases pose a significant threat to agricultural productivity and global food security. Timely and accurate disease identification is crucial for improving crop yield and quality. While most existing deep learning-based methods focus primarily on image datasets for disease recognition, they often overlook the complementary role of textual features in enhancing visual understanding. To address this problem, we proposed a cross-modal data fusion via a vision-language model for crop disease recognition. Our approach leverages the Zhipu.ai multi-model to generate comprehensive textual descriptions of crop leaf diseases, including global description, local lesion description, and color-texture description. These descriptions are encoded into feature vectors, while an image encoder extracts image features. A cross-attention mechanism then iteratively fuses multimodal features across multiple layers, and a classification prediction module generates classification probabilities. Extensive experiments on the Soybean Disease, AI Challenge 2018, and PlantVillage datasets demonstrate that our method outperforms state-of-the-art image-only approaches with higher accuracy and fewer parameters. Specifically, with only 1.14M model parameters, our model achieves a 98.74%, 87.64% and 99.08% recognition accuracy on the three datasets, respectively. The results highlight the effectiveness of cross-modal learning in leveraging both visual and textual cues for precise and efficient disease recognition, offering a scalable solution for crop disease recognition.

We propose an Inner-Imaging three-dimensional (3D) attentional feature fusion module for a residual network, which is a simple yet effective approach for residual networks. In our attention module, we constructed a 3D soft attention feature map to refine the input feature. The map fuses the attentional features from different dimensions, including channel and spatial axes, to create a 3D attention map. Then, we implemented a feature fusion module to further fuse the attentional features. Lastly, the attention module outputs a 3D soft attention map that is applied to the residual branch. The attention module can also model the relationship between attentional features from different dimensions and achieve the interaction between attentional features. This function allows our attention module to acquire more attentional features. To demonstrate the effectiveness of our method, extensive experiments were conducted on several computer vision benchmark datasets, including ImageNet 2012 and Microsoft COCO (MS COCO) 2017 datasets. The experimental results show that our method performed better than the baseline methods in the tasks of image classification, object detection, and instance segmentation tasks.

Pedestrian detection is an important research topic in the field of visual cognition and autonomous driving systems. The proposal of the YOLO model has significantly improved the speed and accuracy of detection. To achieve full day detection performance, multimodal YOLO models based on RGB-FIR image pairs have become a research hotspot. Existing work has focused on the design of fusion modules after feature extraction of RGB and FIR branch backbone networks, achieving a multimodal backbone network framework based on back-end fusion. However, these methods overlook the complementarity and prior knowledge between modalities and scales in the front-end raw feature extraction of RGB and FIR branch backbone networks. As a result, the performance of the backend fusion framework largely depends on the representation ability of the raw features of each modality in the front-end. This paper proposes a novel RGB-FIR multimodal backbone network framework based on a cross-modality context attentional model (CCAM). Different from the existing works, a multi-level fusion framework is designed. At the front-end of the RGB-FIR parallel backbone network, the CCAM model is constructed for the raw features of each scale. The RGB-FIR feature fusion results of the lower-level features of the RGB and FIR branch backbone networks are fully utilized to optimize the spatial weight of the upper level RGB and FIR features, to achieve cross-modality and cross-scale complementarity between adjacent scale feature extraction modules. At the back-end of the RGB-FIR parallel network, a channel-space joint attention model (CBAM) and self-attention models are combined to obtain the final RGB-FIR fusion features at each scale for those RGB and FIR features optimized by CCAM. Compared with the current RGB-FIR multimodal YOLO model, comparative experiments on different performance evaluation indicators on multiple RGB-FIR public datasets indicate that this method can significantly enhance the accuracy and robustness of pedestrian detection.