Humans can naturally and effectively find salient regions in complex scenes. Motivated by this observation, attention mechanisms were introduced into computer vision with the aim of imitating this ...aspect of the human visual system. Such an attention mechanism can be regarded as a dynamic weight adjustment process based on features of the input image. Attention mechanisms have achieved great success in many visual tasks, including image classification, object detection, semantic segmentation, video understanding, image generation, 3D vision, multimodal tasks, and self-supervised learning. In this survey, we provide a comprehensive review of various attention mechanisms in computer vision and categorize them according to approach, such as channel attention, spatial attention, temporal attention, and branch attention; a related repository
https://github.com/MenghaoGuo/Awesome-Vision-Attentions
is dedicated to collecting related work. We also suggest future directions for attention mechanism research.
The class activation maps are generated from the final convolutional layer of CNN. They can highlight discriminative object regions for the class of interest. These discovered object regions have ...been widely used for weakly-supervised tasks. However, due to the small spatial resolution of the final convolutional layer, such class activation maps often locate coarse regions of the target objects, limiting the performance of weakly-supervised tasks that need pixel-accurate object locations. Thus, we aim to generate more fine-grained object localization information from the class activation maps to locate the target objects more accurately. In this paper, by rethinking the relationships between the feature maps and their corresponding gradients, we propose a simple yet effective method, called LayerCAM. It can produce reliable class activation maps for different layers of CNN. This property enables us to collect object localization information from coarse (rough spatial localization) to fine (precise fine-grained details) levels. We further integrate them into a high-quality class activation map, where the object-related pixels can be better highlighted. To evaluate the quality of the class activation maps produced by LayerCAM, we apply them to weakly-supervised object localization and semantic segmentation. Experiments demonstrate that the class activation maps generated by our method are more effective and reliable than those by the existing attention methods. The code will be made publicly available.
Delving Deep Into Label Smoothing Zhang, Chang-Bin; Jiang, Peng-Tao; Hou, Qibin ...
IEEE transactions on image processing,
2021, Volume:
30
Journal Article
Peer reviewed
Open access
Label smoothing is an effective regularization tool for deep neural networks (DNNs), which generates soft labels by applying a weighted average between the uniform distribution and the hard label. It ...is often used to reduce the overfitting problem of training DNNs and further improve classification performance. In this paper, we aim to investigate how to generate more reliable soft labels. We present an Online Label Smoothing (OLS) strategy, which generates soft labels based on the statistics of the model prediction for the target category. The proposed OLS constructs a more reasonable probability distribution between the target categories and non-target categories to supervise DNNs. Experiments demonstrate that based on the same classification models, the proposed approach can effectively improve the classification performance on CIFAR-100, ImageNet, and fine-grained datasets. Additionally, the proposed method can significantly improve the robustness of DNN models to noisy labels compared to current label smoothing approaches. The source code is available at our project page: https://mmcheng.net/ols/
Lithium-ion batteries, with high energy density (up to 705 Wh/L) and power density (up to 10,000 W/L), exhibit high capacity and great working performance. As rechargeable batteries, lithium-ion ...batteries serve as power sources in various application systems. Temperature, as a critical factor, significantly impacts on the performance of lithium-ion batteries and also limits the application of lithium-ion batteries. Moreover, different temperature conditions result in different adverse effects. Accurate measurement of temperature inside lithium-ion batteries and understanding the temperature effects are important for the proper battery management. In this review, we discuss the effects of temperature to lithium-ion batteries at both low and high temperature ranges. The current approaches in monitoring the internal temperature of lithium-ion batteries via both contact and contactless processes are also discussed in the review.
Lithium-ion batteries (LIBs), with high energy density and power density, exhibit good performance in many different areas. The performance of LIBs, however, is still limited by the impact of temperature. The acceptable temperature region for LIBs normally is −20 °C ~ 60 °C. Both low temperature and high temperature that are outside of this region will lead to degradation of performance and irreversible damages, such as lithium plating and thermal runaway. Therefore, understanding the temperature effects and accurate measurement of temperature inside lithium-ion batteries are important for the proper battery management. The state-of-art achievements in monitoring the temperature inside the LIBs can be divided into contact measurement and contactless measurement. This review overviews recent development in both the understanding of the temperature effects and the temperature monitoring, and discusses the challenges and possible future directions in achieving optimum battery performance. Display omitted
Allostery plays a crucial role in regulating protein activity, making it a highly sought‐after target in drug development. One of the major challenges in allosteric drug research is the ...identification of allosteric sites. In recent years, many computational models have been developed for accurate allosteric site prediction. Most of these models focus on designing a general rule that can be applied to pockets of proteins from various families. In this study, we present a new approach using the concept of Learning to Rank (LTR). The LTR model ranks pockets based on their relevance to allosteric sites, that is, how well a pocket meets the characteristics of known allosteric sites. After the training and validation on two datasets, the Allosteric Database (ASD) and CASBench, the LTR model was able to rank an allosteric pocket in the top three positions for 83.6% and 80.5% of test proteins, respectively. The model outperforms other common machine learning models with higher F1 scores (0.662 in ASD and 0.608 in CASBench) and Matthews correlation coefficients (0.645 in ASD and 0.589 in CASBench). The trained model is available on the PASSer platform (https://passer.smu.edu) to aid in drug discovery research.
PASSerRank model can rank protein pockets in terms of their relevance to allostery.
Circular RNA (circ-RNA) and exosomes have recently been shown to play important roles in different tumors. However, the functions and regulatory mechanisms of exosomal circ-RNA in pancreatic ductal ...adenocarcinoma (PDAC) tumor progression remain unclear. Here, we identified a circular RNA (circ-PDE8A) from liver-metastatic PDAC cells by microarray analysis, detected its expression levels in clinical tissues and found that high circ-PDE8A expression was correlated with lymphatic invasion, TNM stage and a poor survival rate of PDAC patients. Further study revealed that circ-PDE8A promotes the invasive growth of PDAC cells via upregulating MET. Circ-PDE8A acts as a ceRNA for miR-338 to regulate MACC1 and stimulates invasive growth via the MACC/MET/ERK or AKT pathways. We further imaged the exosome communication between tumor cells and identified the tumor secreted exosomes in blood circulation. Finally, we analyzed the circ-PDE8A expression in plasma exosomes of PDAC patients and found that exosomal circ-PDE8A was associated with progression and prognosis in PDAC patients. Thus, circ-PDE8A may play an important role in tumor invasion, and exosomal circ-PDE8A may be a useful marker of PDAC diagnosis or progression.
•High level of circ-PDE8A is associated with tumor progression and prognosis.•Circ-PDE8A promotes the invasive growth via miR-338/MACC1/MET pathway.•Tumor released exosomes could enter into blood circulation and be detected.•Plasma exosomal circ-PDE8A is correlated to tumor invasion of PDAC patients.
Human skin shows self‐adaptive temperature regulation through both enhanced heat dissipation in high temperature environments and depressed heat dissipation in cold environments. Inspired by such ...thermal regulation processes, an interfacial material system with self‐adaptive temperature regulation in the solar‐driven interfacial evaporation system, which can exhibit automatic temperature oscillation to enable pyroelectricity generation while producing water vapor, is reported. The bioinspired interface system is designed with the combination of a thermochromism‐based temperature regulator consisting of tungsten‐doped vanadium dioxide nanoparticles and a polymeric pyroelectric thin film of polyvinylidene fluoride. Under the simulated solar illumination with power density of 1.1 kW m−2, the bioinspired interfacial evaporation system achieves a self‐adaptive temperature oscillation with the maximum temperature difference of ≈7 °C and this system can simultaneously generate water vapor as well as electricity with an evaporation efficiency of 71.43% and a maximum output electrical power density of 104 µW m−2, respectively. The study demonstrates a design of thermal management at the interface of solar‐driven evaporation system to exhibit a self‐adaptive temperature oscillation and offers an alternative approach for the multifunctional harvesting of solar energy.
Bioinspired temperature regulation at the interface of the interfacial evaporation system is enabled by using thermochromic VO2 nanoparticles as the solar absorption layer, which can modulate the solar thermal process and also the energy distribution within the system. Integrated with a pyroelectric polyvinylidene fluoride film, the system can simultaneously generate water vapor and electricity during the solar‐driven interfacial evaporation process.
Object attention maps generated by image classifiers are usually used as priors for weakly supervised semantic segmentation. However, attention maps usually locate the most discriminative object ...parts. The lack of integral object localization maps heavily limits the performance of weakly supervised segmentation approaches. This paper attempts to investigate a novel way to identify entire object regions in a weakly supervised manner. We observe that image classifiers' attention maps at different training phases may focus on different parts of the target objects. Based on this observation, we propose an online attention accumulation (OAA) strategy that utilizes the attention maps at different training phases to obtain more integral object regions. Specifically, we maintain a cumulative attention map for each target category in each training image and utilize it to record the discovered object regions at different training phases. Albeit OAA can effectively mine more object regions for most images, for some training images, the range of the attention movement is not large, limiting the generation of integral object attention regions. To overcome this problem, we propose incorporating an attention drop layer into the online attention accumulation process to enlarge the range of attention movement during training explicitly. Our method (OAA) can be plugged into any classification network and progressively accumulate the discriminative regions into cumulative attention maps as the training process goes. Additionally, we also explore utilizing the final cumulative attention maps to serve as the pixel-level supervision, which can further assist the network in discovering more integral object regions. When applying the resulting attention maps to the weakly supervised semantic segmentation task, our approach improves the existing state-of-the-art methods on the PASCAL VOC 2012 segmentation benchmark, achieving a mIoU score of 67.2 percent on the test set.
Ensuring precise prediction of the remaining useful life (RUL) for bearings in rolling machinery is crucial for preventing sudden machine failures and optimizing equipment maintenance strategies. ...Since the significant interference encountered in real industrial environments and the high complexity of the machining process, accurate and robust RUL prediction of rolling bearings is of tremendous research importance. Hence, a novel RUL prediction model called CNN-VAE-MBiLSTM is proposed in this paper by integrating advantages of convolutional neural network (CNN), variational autoencoder (VAE), and multiple bi-directional long short-term memory (MBiLSTM). The proposed approach includes a CNN-VAE model and a MBiLSTM model. The CNN-VAE model performs well for automatically extracting low-dimensional features from time-frequency spectrum of multi-axis signals, which simplifies the construction of features and minimizes the subjective bias of designers. Based on these features, the MBiLSTM model achieves a commendable performance in the prediction of RUL for bearings, which independently captures sequential characteristics of features in each axis and further obtains differences among multi-axis features. The performance of the proposed approach is validated through an industrial case, and the result indicates that it exhibits a higher accuracy and a better anti-noise capacity in RUL predictions than comparable methods.