As marine observation technology develops rapidly, underwater optical image object detection is beginning to occupy an important role in many tasks, such as naval coastal defense tasks, aquaculture, etc. However, in the complex marine environment, the images captured by an optical imaging system are usually severely degraded. Therefore, how to detect objects accurately and quickly under such conditions is a critical problem that needs to be solved. In this manuscript, a novel framework for underwater object detection based on a hybrid transformer network is proposed. First, a lightweight hybrid transformer-based network is presented that can extract global contextual information. Second, a fine-grained feature pyramid network is used to overcome the issues of feeble signal disappearance. Third, the test-time-augmentation method is applied for inference without introducing additional parameters. Extensive experiments have shown that the approach we have proposed is able to detect feeble and small objects in an efficient and effective way. Furthermore, our model significantly outperforms the latest advanced detectors with respect to both the number of parameters and the mAP by a considerable margin. Specifically, our detector outperforms the baseline model by 6.3 points, and the model parameters are reduced by 28.5 M.

Remote sensing image scene classification is an important task of remote sensing image interpretation, which has recently been well addressed by the convolutional neural network owing to its powerful learning ability. However, due to the multiple types of geographical information and redundant background information of the remote sensing images, most of the CNN-based methods, especially those based on a single CNN model and those ignoring the combination of global and local features, exhibit limited performance on accurate classification. To compensate for such insufficiency, we propose a new dual-model deep feature fusion method based on an attention cascade global–local network (ACGLNet). Specifically, we use two popular CNNs as the feature extractors to extract complementary multiscale features from the input image. Considering the characteristics of the global and local features, the proposed ACGLNet filters the redundant background information from the low-level features through the spatial attention mechanism, followed by which the locally attended features are fused with the high-level features. Then, bilinear fusion is employed to produce the fused representation of the dual model, which is finally fed to the classifier. Through extensive experiments on four public remote sensing scene datasets, including UCM, AID, PatternNet, and OPTIMAL-31, we demonstrate the feasibility of the proposed method and its superiority over the state-of-the-art scene classification methods.

Timely and accurate pavement crack detection plays a crucial role in urban transportation and pavement management. Recently, deep learning-based pavement crack detection approaches have witnessed significant advancements. However, high-performance networks heavily rely on complex network structures and massive model parameters, making their application in practical scenarios challenging. To achieve efficient yet accurate pavement crack detection, this paper presents a novel Lightweight Pavement Crack Detection based on Multi-Scale Semantic Map Distillation (LPCD-MSMD). Specifically, we improve the U-Net by designing a novel Cascaded U-Net (C-UNet) structure and incorporating additional branches to capture more subtle features. The proposed C-UNet is optimized by reducing the number of convolutional layers and compressing the channel dimensions, benefiting to a more lightweight model while maintaining comparable performance. Additionally, we utilize the original C-UNet as the teacher network and the simplified network as the student network for a lightweight pavement crack detection. Through the proposed multi-scale semantic map distillation strategy, the student network can acquire multi-scale output knowledge from the cascaded output of the teacher network, benefiting significantly improved performance of the CU-Net(s). Thorough experimental results demonstrate that the elaborately designed student network possesses a remarkably small parameter size of only 0.54 MB. Moreover, the performance evaluated on the Crack500 dataset and the GAPS384 dataset indicate the superiority of proposed method over several typical deep learning-based approaches including SegNet, FCN, BiSeNet, and U-Net. In particular, our method outperforms the second-best method by 0.09 and 0.124 in terms of F1 score evaluated on the Crack500 dataset and the GAPS384 dataset, respectively.

Remote sensing images contain complex backgrounds and multi-scale objects, which pose a challenging task for scene classification. The performance is highly dependent on the capacity of the scene representation as well as the discriminability of the classifier. Although multiple models possess better properties than a single model on these aspects, the fusion strategy for these models is a key component to maximize the final accuracy. In this paper, we construct a novel dual-model architecture with a grouping-attention-fusion strategy to improve the performance of scene classification. Specifically, the model employs two different convolutional neural networks (CNNs) for feature extraction, where the grouping-attention-fusion strategy is used to fuse the features of the CNNs in a fine and multi-scale manner. In this way, the resultant feature representation of the scene is enhanced. Moreover, to address the issue of similar appearances between different scenes, we develop a loss function which encourages small intra-class diversities and large inter-class distances. Extensive experiments are conducted on four scene classification datasets include the UCM land-use dataset, the WHU-RS19 dataset, the AID dataset, and the OPTIMAL-31 dataset. The experimental results demonstrate the superiority of the proposed method in comparison with the state-of-the-arts.

In the letter, we propose a novel yet effective knowledge distillation scheme which mimics an all-round learning process of an excellent student from the teacher, i.e, knowledge review, knowledge preview, and knowledge correction, to acquire more informative and complementary knowledge. In the newly proposed method, to better leverage comprehensive feature knowledge from the teacher model, we propose Knowledge Review and Knowledge Preview Distillation to amalgamate multi-level features from different intermediate layers in both forward and backward pathways and fully distill them through hierarchical context loss, which greatly improves the student's feature learning efficiency. Moreover, we further present a Response Correction Mechanism to reinforce the prediction of student, which can more fully excavate the student's own knowledge, effectively alleviating the negative influence caused by the knowledge gap between the teacher and the student. We verify the effectiveness of our method with various networks on the CIFAR-100 datasets and the proposed method achieves competitive results compared with other state-of-the-art competitors. The code will be available at https://github.com/kbzhang0505/RPC .