Search

The task of multi-label image recognition is to predict a set of object labels that present in an image. As objects normally co-occur in an image, it is desirable to model label dependencies to improve recognition performance. To capture and explore such important information, we propose Graph Convolutional Networks based models for multi-label recognition, where directed graphs are constructed over classes and information is propagated between classes to learn inter-dependent class-level representations. Following this idea, we design two particular models that approach multi-label classification from different views. In our first model, the prior knowledge about the class dependencies is integrated into classifier learning. Specifically, we propose Classifier-Learning-GCN to map class-level semantic representations (\eg, word embedding) into classifiers that maintain the inter-class topology. In our second model, we decompose the visual representation of an image into a set of label-aware features and propose Prediction-Learning-GCN to encode such features into inter-dependent image-level prediction scores. Furthermore, we also present an effective correlation matrix construction approach to capture inter-class relationships and consequently guide information propagation among classes. Empirical results on generic multi-label recognition demonstrate that the effectiveness of both two proposed models. Moreover, the proposed methods also show advantages in other multi-label related applications.

The SnakeCLEF2023 competition aims to the development of advanced algorithms for snake species identification through the analysis of images and accompanying metadata. This paper presents a method leveraging utilization of both images and metadata. Modern CNN models and strong data augmentation are utilized to learn better representation of images. To relieve the challenge of long-tailed distribution, seesaw loss is utilized in our method. We also design a light model to calculate prior probabilities using metadata features extracted from CLIP in post processing stage. Besides, we attach more importance to venomous species by assigning venomous species labels to some examples that model is uncertain about. Our method achieves 91.31% score of the final metric combined of F1 and other metrics on private leaderboard, which is the 1st place among the participators. The code is available at https://github.com/xiaoxsparraw/CLEF2023., This work was the winner solution of the SnakeCLEF2023 challenge

Semantic change detection (SCD) and land cover mapping (LCM) are always treated as a dual task in the field of remote sensing. However, due to diverse real-world scenarios, many SCD categories are not easy to be clearly recognized, such as “water-vegetation” and “water-tree”, which can be regarded as fine-grained differences. In addition, even a single LCM category is usually difficult to define. For instance, some “vegetation” categories with litter vegetation coverage are easily confused with the general “ground” category. SCD/LCM becomes challenging under both challenges of its fine-grained nature and label ambiguity. In this paper, we tackle the SCD and LCM tasks simultaneously by proposing a coarse-to-fine attention tree (CAT) model. Specifically, it consists of an encoder, a decoder and a coarse-to-fine attention tree module. The encoder-decoder structure extracts the high-level features from input multi-temporal images first and then reconstructs them to return SCD and LCM predictions. Our coarse-to-fine attention tree, on the one hand, utilizes the tree structure to better model a hierarchy of categories by predicting the coarse-grained labels first and then predicting the fine-grained labels later. On the other hand, it applies the attention mechanism to capture discriminative pixel regions. Furthermore, to address label ambiguity in SCD/LCM, we also equip a label distribution learning loss upon our model. Experiments on the large-scale SECOND dataset justify that the proposed CAT model outperforms state-of-the-art models. Moreover, various ablation studies have demonstrated the effectiveness of tailored designs in the CAT model for solving semantic change detection problems.

The task of few-shot fine-grained recognition is to classify images belonging to subordinate categories merely depending on few examples. Due to the fine-grained nature, it is desirable to capture subtle but discriminative part-level patterns from limited training data, which makes it a challenging problem. In this paper, to generate fine-grained tailored representations for few-shot recognition, we propose a Dual Attention Network (Dual Att-Net) consisting of two dual branches of both hard- and soft-attentions. Specifically, by producing attention guidance from deep activations of input images, our hard-attention is realized by keeping a few useful deep descriptors and forming them as a bag of multi-instance learning. Since these deep descriptors could correspond to objects' parts, the advantage of modeling as a multi-instance bag is able to exploit inherent correlation of these fine-grained parts. On the other side, a soft attended activation representation can be obtained by applying attention guidance upon original activations, which brings comprehensive attention information as the counterpart of hard-attention. After that, both outputs of dual branches are aggregated as a holistic image embedding w.r.t. input images. By performing meta-learning, we can learn a powerful image embedding in such a metric space to generalize to novel classes. Experiments on three popular fine-grained benchmark datasets show that our Dual Att-Net obviously outperforms other existing state-of-the-art methods.

Simplicity Bias (SB) is a phenomenon that deep neural networks tend to rely favorably on simpler predictive patterns but ignore some complex features when applied to supervised discriminative tasks. In this work, we investigate SB in long-tailed image recognition and find the tail classes suffer more severely from SB, which harms the generalization performance of such underrepresented classes. We empirically report that self-supervised learning (SSL) can mitigate SB and perform in complementary to the supervised counterpart by enriching the features extracted from tail samples and consequently taking better advantage of such rare samples. However, standard SSL methods are designed without explicitly considering the inherent data distribution in terms of classes and may not be optimal for long-tailed distributed data. To address this limitation, we propose a novel SSL method tailored to imbalanced data. It leverages SSL by triple diverse levels, i.e., holistic-, partial-, and augmented-level, to enhance the learning of predictive complex patterns, which provides the potential to overcome the severe SB on tail data. Both quantitative and qualitative experimental results on five long-tailed benchmark datasets show our method can effectively mitigate SB and significantly outperform the competing state-of-the-arts.

Labeling objects at a subordinate level typically requires expert knowledge, which is not always available when using random annotators. As such, learning directly from web images for fine-grained recognition has attracted broad attention. However, the presence of label noise and hard examples in web images are two obstacles for training robust fine-grained recognition models. To this end, in this paper, we propose a novel approach to remove irrelevant samples from real-world web images during training, while employing useful hard examples to update the network. Thus, our approach can alleviate the harmful effects of irrelevant noisy web images and hard examples to achieve better performance. Extensive experiments on three commonly used fine-grained datasets demonstrate that our approach is far superior to current state-of-the-art web-supervised methods.

The practical task of Automatic Check-Out (ACO) is to accurately predict the presence and count of each product in an arbitrary product combination. Beyond the large-scale and the fine-grained nature of product categories as its main challenges, products are always continuously updated in realistic check-out scenarios, which is also required to be solved in an ACO system. Previous work in this research line almost depends on the supervisions of labor-intensive bounding boxes of products by performing a detection paradigm. While, in this paper, we propose a Self-Supervised Multi-Category Counting (S2MC2) network to leverage the point-level supervisions of products in check-out images to both lower the labeling cost and be able to return ACO predictions in a class incremental setting. Specifically, as a backbone, our S2MC2 is built upon a counting module in a class-agnostic counting fashion. Also, it consists of several crucial components including an attention module for capturing fine-grained patterns and a domain adaptation module for reducing the domain gap between single product images as training and check-out images as test. Furthermore, a self-supervised approach is utilized in S2MC2 to initialize the parameters of its backbone for better performance. By conducting comprehensive experiments on the large-scale automatic check-out dataset RPC, we demonstrate that our proposed S2MC2 achieves superior accuracy in both traditional and incremental settings of ACO tasks over the competing baselines.

Unsupervised learning technology has caught up with or even surpassed supervised learning technology in general object classification (GOC) and person re-identification (re-ID). However, it is found that the unsupervised learning of fine-grained visual classification (FGVC) is more challenging than GOC and person re-ID. In order to bridge the gap between unsupervised and supervised learning for FGVC, we investigate the essential factors (including feature extraction, clustering, and contrastive learning) for the performance gap between supervised and unsupervised FGVC. Furthermore, we propose a simple, effective, and practical method, termed as UFCL, to alleviate the gap. Three key issues are concerned and improved: First, we introduce a robust and powerful backbone, ResNet50-IBN, which has an ability of domain adaptation when we transfer ImageNet pre-trained models to FGVC tasks. Next, we propose to introduce HDBSCAN instead of DBSCAN to do clustering, which can generate better clusters for adjacent categories with fewer hyper-parameters. Finally, we propose a weighted feature agent and its updating mechanism to do contrastive learning by using the pseudo labels with inevitable noise, which can improve the optimization process of learning the parameters of the network. The effectiveness of our UFCL is verified on CUB-200-2011, Oxford-Flowers, Oxford-Pets, Stanford-Dogs, Stanford-Cars and FGVC-Aircraft datasets. Under the unsupervised FGVC setting, we achieve state-of-the-art results, and analyze the key factors and the important parameters to provide a practical guidance., 12 pages, 7 figures

We propose Equiangular Basis Vectors (EBVs) for classification tasks. In deep neural networks, models usually end with a k-way fully connected layer with softmax to handle different classification tasks. The learning objective of these methods can be summarized as mapping the learned feature representations to the samples' label space. While in metric learning approaches, the main objective is to learn a transformation function that maps training data points from the original space to a new space where similar points are closer while dissimilar points become farther apart. Different from previous methods, our EBVs generate normalized vector embeddings as "predefined classifiers" which are required to not only be with the equal status between each other, but also be as orthogonal as possible. By minimizing the spherical distance of the embedding of an input between its categorical EBV in training, the predictions can be obtained by identifying the categorical EBV with the smallest distance during inference. Various experiments on the ImageNet-1K dataset and other downstream tasks demonstrate that our method outperforms the general fully connected classifier while it does not introduce huge additional computation compared with classical metric learning methods. Our EBVs won the first place in the 2022 DIGIX Global AI Challenge, and our code is open-source and available at https://github.com/NJUST-VIPGroup/Equiangular-Basis-Vectors., Comment: CVPR 2023

Polyethylene oxide (PEO) was one of the most classic and widely used solid polymer electrolyte matrixes. In this work, we added the previously synthesized titanium dioxide (B-P25) fillers with oxygen vacancies to the PEO-LiClO4 solid electrolyte system. It is found that compared with the pristine P25 fillers, the oxygen vacancies lead to the decrease of ionic conductivity and the Li+ transference number. Infrared and Raman spectroscopy shows that the introduction of oxygen vacancies lead to the formation of Li+-ClO4− ion pairs and the decrease of carrier concentration resulted in the decrease of Li+ conductivity. Further theoretical calculations verified that this is due to the preferential combination of oxygen vacancies and ether oxygen atoms of PEO. This finding effectively supplements the effect of oxide oxygen vacancies on the conduction of Li+ in the PEO matrix, and not all oxygen vacancies are beneficial to the conduction of Li+ ions in the PEO matrix.

High interfacial energy Li

Semi-supervised few-shot learning consists in training a classifier to adapt to new tasks with limited labeled data and a fixed quantity of unlabeled data. Many sophisticated methods have been developed to address the challenges this problem comprises. In this paper, we propose a simple but quite effective approach to predict accurate negative pseudo-labels of unlabeled data from an indirect learning perspective, and then augment the extremely label-constrained support set in few-shot classification tasks. Our approach can be implemented in just few lines of code by only using off-the-shelf operations, yet it is able to outperform state-of-the-art methods on four benchmark datasets., Accepted by NeurIPS 2022

The aggregation of inorganic particles with high mass ratio will form a heterogeneous electric field in the solid polymer electrolytes (SPEs), which is difficult to be compatible with lithium anode, leading to inadequate ionic conductivity. Herein, a facile spray drying method is adopted to increase the mass ratio of inorganic particles and solve the aggregation problems of fillers simultaneously. The polyvinylidene fluoride (PVDF) with lithium bis(trifluoromethanesulfonyl)imide (LiTFSI) covers the surface of each Li6.4La3Zr1.4Ta0.6O12 (LLZTO) granules during the nebulization process, then forming flat solid electrolytes via layer-by-layer deposition. Characterized by the atomic force microscope, the obtained solid electrolytes achieve a homogenous dispersion of Young’s modulus and surface electric field. As a result, the as-prepared SPEs present high tensile strength of 7.1 MPa, high ionic conductivity of 1.86 × 10−4 S·cm−1 at room temperature, and wide electrochemical window up to 5.0 V, demonstrating increased mechanical strength and uniform lithium-ion migration channels for SPEs. Thanks to the as-prepared SPEs, the lithium-symmetrical cells show a highly stable Li plating/stripping cycling for over 1,000 h at 0.1 mA·cm−2. The corresponding Li/LCoO2 batteries also present good rate capability and excellent cyclic performance with capacity retention of 80% after 100 cycles at room temperature.

In recent years, visual recognition on challenging long-tailed distributions, where classes often exhibit extremely imbalanced frequencies, has made great progress mostly based on various complex paradigms (e.g., meta learning). Apart from these complex methods, simple refinements on training procedures also make contributions. These refinements, also called tricks, are minor but effective, such as adjustments in the data distribution or loss functions. However, different tricks might conflict with each other. If users apply these long-tail related tricks inappropriately, it could cause worse recognition accuracy than expected. Unfortunately, there has not been a scientific guideline of these tricks in the literature. In this paper, we first collect existing tricks in long-tailed visual recognition and then perform extensive and systematic experiments, in order to give a detailed experimental guideline and obtain an effective combination of these tricks. Furthermore, we also propose a novel data augmentation approach based on class activation maps for long-tailed recognition, which can be friendly combined with re-sampling methods and shows excellent results. By assembling these tricks scientifically, we can outperform state-of-the-art methods on four long-tailed benchmark datasets, including ImageNet-LT and iNaturalist 2018. Our code is open-source and available at https://github.com/zhangyongshun/BagofTricks-LT.

Although aqueous zinc metal batteries (AZMBs) have attractive advantages such as high safety, low cost and eco-friendliness, severe dendrites formation and side reactions of zinc metal anodes cause a serious challenge for commercial applications. Herein, a polyanionic hydrogel electrolyte, poly 2-acrylamido-2-methyl-1-propane sulfonate zinc (PAMPSZn) is firstly designed and synthesized by ion exchange and free-radical polymerization. The PAMPSZn hydrogel electrolyte owns fixed polyanionic chain and restricted Zn2+ transport channels, which can effectively alleviate the side reactions and prevent the formation of Zn dendrites simultaneously. Consequently, the anode-friendly electrolyte not only enables ultra-stable Zn plating/stripping over 4500 h at 1.0 mA cm−2, but also achieves high preferred orientation deposition during the procedure of repeated plating/stripping. It delivers high reversibility with high initial coulombic efficiency (87.5%) and average coulombic efficiency (99.3%) in Zn/Cu cells at 0.5 mA cm−2. Zn/V2O5 cells with the developed electrolyte also possess outstanding cycle stability with capacity retention of 80.2% after 400 cycles at 0.5 A g−1. The PAMPSZn hydrogel electrolyte with unique fixed polyanionic chain and restricted Zn2+ transport channels demonstrates an effective strategy to solve both dendrites formation and side reactions in AZMBs, providing a new opportunity for high performance AZMBs.

ObjectiveTrends in the incidence, disability-adjusted life-years (DALYs), and mortality rate of cervical cancer remain unknown.MethodsThe average annual percent changes (AAPCs) and relative risks (RR) in the incidence, DALYs, and mortality rate were determined using a joinpoint regression analysis; the net age, period, and cohort effects on above rates were evaluated.ResultsA significant increase in age-standardized incidence (AAPC, 0.9%; 95CI: 0.8, 1.1) but significant decreases in age-standardized DALYs (AAPC, -0.4%; 95%CI: -0.60, -0.20) and the mortality rate (AAPC, -0.4%; 95CI: -0.6, –0.3) were observed. As for age-specific rates, the incidence was higher in younger age groups, and the DALYs and mortality rate were lower in older age groups. The effects of age included a slight but significant increase in the RR with advancing age from 35 to 94 years; the period effect included a significant increase in the incidence over the 2005–2019 periods; and the cohort effect included a substantial increase in the incidence from earlier to later birth cohorts.ConclusionsThe incidence of cervical cancer increased from 1990 to 2019, particularly in younger age groups, and the DALYs and mortality rate decreased in the older age groups. Furthermore, the incidence increased with age, period, and cohort.

The task of webly-supervised fine-grained recognition is to boost recognition accuracy of classifying subordinate categories (e.g., different bird species) by utilizing freely available but noisy web data. As the label noises significantly hurt the network training, it is desirable to distinguish and eliminate noisy images. In this paper, we propose two strategies, i.e., open-set noise removal and closed-set noise correction, to both remove such two kinds of web noises w.r.t. fine-grained recognition. Specifically, for open-set noise removal, we utilize a pre-trained deep model to perform deep descriptor transformation to estimate the positive correlation between these web images, and detect the open-set noises based on the correlation values. Regarding closed-set noise correction, we develop a top-k recall optimization loss for firstly assigning a label set towards each web image to reduce the impact of hard label assignment for closed-set noises. Then, we further propose to correct the sample with its label set as the true single label from a partial label learning perspective. Experiments on several webly-supervised fine-grained benchmark datasets show that our method obviously outperforms other existing state-of-the-art methods.

Multi-label image recognition is a fundamental but challenging computer vision and multimedia task. Great progress has been achieved by exploiting label correlations among these multiple labels associated with a single image, which is the most crucial issue for multi-label image recognition. In this paper, to explicitly model label correlations, we propose a unified deep learning framework to Disentangle, Embed and Rank (DER) the corresponding label cues. Specifically, we first obtain class-aware disentangled maps (CADMs) by reforming deep activations in accordance with the class-specific recognition weights. Then, after transforming CADMs into the corresponding label vectors, we propose an embedding operation from a metric learning perspective to pull the relevant label vectors together and push irrelevant label vectors away. Furthermore, a ranking operation is employed, which aims to accurately and robustly measure the similarity/dissimilarity of these label vectors. Our model can be trained in an end-to-end manner with only image-level supervision, during which the proposed embedding and ranking operations can contribute to the CADMs learning through back-propagation. In addition, the obtained CADMs are aggregated and further used as an essential feature stream for the final multi-label classification. We conduct extensive experiments on three commonly used multi-label benchmark datasets. Quantitative results show that our model can significantly and consistently outperform previous competitive methods. Moreover, qualitative analysis of our DER proposal also reveals the effectiveness of our proposed model.

The safety of lithium-ion batteries (LIBs) is a serious and challenging problem that threatens the applications of large-scale energy storage as well as the daily usage of mobile devices. In this work, we developed a rational design of reinforced ceramic-coated separator by modifying the ceramic-coated separator with an overall-covered layer of electron-insulated polypyrrole throughout the entire separator. As a result, the modified separator shows an improved thermal stability without visible shrinkage at 200 °C, has a better electrolyte wettability and a higher Li+ transference number of 0.56. With these advantages, cells assembled with the modified separators show better safety performance and an improved rate capability.

DOI：10.3969/j.issn.1672⁃6731.2020.12.014

Landmark/pose estimation in single monocular images have received much effort in computer vision due to its important applications. It remains a challenging task when input images severe occlusions caused by, e.g., adverse camera views. Under such circumstances, biologically implausible pose predictions may be produced. In contrast, human vision is able to predict poses by exploiting geometric constraints of landmark point inter-connectivity. To address the problem, by incorporating priors about the structure of pose components, we propose a novel structure-aware fully convolutional network to implicitly take such priors into account during training of the deep network. Explicit learning of such constraints is typically challenging. Instead, inspired by how human identifies implausible poses, we design discriminators to distinguish the real poses from the fake ones (such as biologically implausible ones). If the pose generator G generates results that the discriminator fails to distinguish from real ones, the network successfully learns the priors. Training of the network follows the strategy of conditional Generative Adversarial Networks (GANs). The effectiveness of the proposed network is evaluated on three pose-related tasks: 2D single human pose estimation, 2D facial landmark estimation and 3D single human pose estimation. The proposed approach significantly outperforms the state-of-the-art methods and almost always generates plausible pose predictions, demonstrating the usefulness of implicit learning of structures using GANs., 18 pages. Extended version of arXiv:1705.00389. Accepted to IEEE Trans. Pattern Analysis and Machine Intelligence

In this paper, we propose Suppression-Enhancing Mask based attention and Interactive Channel transformatiON (SEMICON) to learn binary hash codes for dealing with large-scale fine-grained image retrieval tasks. In SEMICON, we first develop a suppression-enhancing mask (SEM) based attention to dynamically localize discriminative image regions. More importantly, different from existing attention mechanism simply erasing previous discriminative regions, our SEM is developed to restrain such regions and then discover other complementary regions by considering the relation between activated regions in a stage-by-stage fashion. In each stage, the interactive channel transformation (ICON) module is afterwards designed to exploit correlations across channels of attended activation tensors. Since channels could generally correspond to the parts of fine-grained objects, the part correlation can be also modeled accordingly, which further improves fine-grained retrieval accuracy. Moreover, to be computational economy, ICON is realized by an efficient two-step process. Finally, the hash learning of our SEMICON consists of both global- and local-level branches for better representing fine-grained objects and then generating binary hash codes explicitly corresponding to multiple levels. Experiments on five benchmark fine-grained datasets show our superiority over competing methods., Comment: ECCV 2022

Long-tailed instance segmentation is a challenging task due to the extreme imbalance of training samples among classes. It causes severe biases of the head classes (with majority samples) against the tailed ones. This renders "how to appropriately define and alleviate the bias" one of the most important issues. Prior works mainly use label distribution or mean score information to indicate a coarse-grained bias. In this paper, we explore to excavate the confusion matrix, which carries the fine-grained misclassification details, to relieve the pairwise biases, generalizing the coarse one. To this end, we propose a novel Pairwise Class Balance (PCB) method, built upon a confusion matrix which is updated during training to accumulate the ongoing prediction preferences. PCB generates fightback soft labels for regularization during training. Besides, an iterative learning paradigm is developed to support a progressive and smooth regularization in such debiasing. PCB can be plugged and played to any existing method as a complement. Experimental results on LVIS demonstrate that our method achieves state-of-the-art performance without bells and whistles. Superior results across various architectures show the generalization ability. The code and trained models are available at https://github.com/megvii-research/PCB., Comment: Accepted to CVPR 2022

Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer vision and pattern recognition, and underpins a diverse set of real-world applications. The task of FGIA targets analyzing visual objects from subordinate categories, e.g., species of birds or models of cars. The small inter-class and large intra-class variation inherent to fine-grained image analysis makes it a challenging problem. Capitalizing on advances in deep learning, in recent years we have witnessed remarkable progress in deep learning powered FGIA. In this paper we present a systematic survey of these advances, where we attempt to re-define and broaden the field of FGIA by consolidating two fundamental fine-grained research areas -- fine-grained image recognition and fine-grained image retrieval. In addition, we also review other key issues of FGIA, such as publicly available benchmark datasets and related domain-specific applications. We conclude by highlighting several research directions and open problems which need further exploration from the community., Accepted by IEEE TPAMI

With the advent of deep neural networks, quite a lot of multimedia tasks have been significantly improved. While, however, deep neural networks still lack the ability of learning from less labeling, e.g., with limited exemplars or fast generalizing to new tasks. In order to address the current inefficiency of multimedia, there is pressing need to research methods to drastically reduce requirements for labeled training data. This workshop aims to provide a platform for discussing the challenges and corresponding innovative approaches in multimedia with less labeling. We hope more advanced technologies can be proposed or inspired, and also we invite several domain-specific experts for sharing their insights and research progress on the topic of MULL.

Learning from the web can ease the extreme dependence of deep learning on large-scale manually labeled datasets. Especially for fine-grained recognition, which targets at distinguishing subordinate categories, it will significantly reduce the labeling costs by leveraging free web data. Despite its significant practical and research value, the webly supervised fine-grained recognition problem is not extensively studied in the computer vision community, largely due to the lack of high-quality datasets. To fill this gap, in this paper we construct two new benchmark webly supervised fine-grained datasets, termed WebFG-496 and WebiNat-5089, respectively. In concretely, WebFG-496 consists of three sub-datasets containing a total of 53,339 web training images with 200 species of birds (Web-bird), 100 types of aircrafts (Web-aircraft), and 196 models of cars (Web-car). For WebiNat-5089, it contains 5089 sub-categories and more than 1.1 million web training images, which is the largest webly supervised fine-grained dataset ever. As a minor contribution, we also propose a novel webly supervised method (termed "{Peer-learning}") for benchmarking these datasets.~Comprehensive experimental results and analyses on two new benchmark datasets demonstrate that the proposed method achieves superior performance over the competing baseline models and states-of-the-art. Our benchmark datasets and the source codes of Peer-learning have been made available at {\url{https://github.com/NUST-Machine-Intelligence-Laboratory/weblyFG-dataset}}., accepted by ICCV 2021

Chlorogenic acid (CA) has been discovered to regulate macrophage polarization in pneumonia. This study aims to analyze the functional mechanism of CA in alveolar macrophage (AM) polarization and provide a theoretical basis for treatment of Klebsiella pneumoniae (Kp)-induced pneumonia. Mice were infected with Kp, and treated with CA and silent information regulator 1 (SIRT1) inhibitor (Selisistat). Mouse survival rate was recorded and bacterial burden was detected. AM polarization and pathologic change of lung tissues were evaluated. Expressions of SIRT1 and HMGB1 and cytokine levels were detected. MH-S cells were infected with Kp to establish the pneumonia cell model, followed by transfection of si-SIRT1 and HMGB1 overexpression vector. The HMGB1 expression in the nucleus and cytoplasm was detected. HMGB1 subcellular localization and HMGB1 acetylation level were detected. Kp led to high death rates, SIRT down-regulation and increases in inflammatory factor level and bacterial burden, and promoted M1 polarization. CA treatment improved mouse survival rate and promoted M2 polarization and SIRT1 expression. SIRT1 decreased HMGB1 acetylation level to inhibit nuclear to the cytoplasm translocation. Silencing SIRT1 or HMGB1 overexpression reversed the effect of CA on Kp-induced pneumonia. Overall, CA activated SIRT1 to inhibit HMGB1 acetylation level and nuclear translocation, thereby promoting M2 polarization in AMs and alleviating Kp-induced pneumonia.

Object detection requires plentiful data annotated with bounding boxes for model training. However, in many applications, it is difficult or even impossible to acquire a large set of labeled examples for the target task due to the privacy concern or lack of reliable annotators. On the other hand, due to the high-quality image search engines, such as Flickr and Google, it is relatively easy to obtain resource-rich unlabeled datasets, whose categories are a superset of those of target data. In this article, to improve the target model with cost-effective supervision from source data, we propose a partial transfer learning approach QBox to actively query labels for bounding boxes of source images. Specifically, we design two criteria, i.e., informativeness and transferability, to measure the potential utility of a bounding box for improving the target model. Based on these criteria, QBox actively queries the labels of the most useful boxes from the source domain and, thus, requires fewer training examples to save the labeling cost. Furthermore, the proposed query strategy allows annotators to simply labeling a specific region, instead of the whole image, and, thus, significantly reduces the labeling difficulty. Extensive experiments are performed on various partial transfer benchmarks and a real COVID-19 detection task. The results validate that QBox improves the detection accuracy with lower labeling cost compared to state-of-the-art query strategies for object detection.

The fluorescent properties of conjugated microporous polyphenylene (CMPs) were tuned through a wide range by inclusion of small amount of comonomer as chromophore in the network. The multi-color CMPs were used for explosives sensing and demonstrated broad sensitivity (ranging from -0.01888 μM

Traditional fine-grained image recognition is required to distinguish different subordinate categories ( e.g. , birds species) based on the visual cues beneath raw images. Due to both small inter-class variations and large intra-class variations, it is desirable to capture the subtle differences between these sub-categories, which is crucial but challenging for fine-grained recognition. Recently, language modality aggregation has been proved as a successful technique to improve visual recognition in the experience. In this paper, we introduce an end-to-end trainable Progressive Mask Attention (PMA) model for fine-grained recognition by leveraging both visual and language modalities. Our Bi-Modal PMA model can not only stage-by-stage capture the most discriminative part in the visual modality by our mask-based fashion, but also explore the out-of-visual-domain knowledge from the language modality in an interactional alignment paradigm. Specifically, at each stage, a self-attention module is proposed to attend to the key patch from images or text descriptions. Besides, a query-relational module is designed to seize the key words/phrases of texts and further bridge the connection between two modalities. Later, the learned representations of bi-modality from multiple stages are aggregated as the final features for recognition. Our Bi-Modal PMA model only needs raw images and raw text descriptions, without requiring bounding boxes/part annotations in images or key word annotations in texts. By conducting comprehensive experiments on fine-grained benchmark datasets, we demonstrate that the proposed method achieves superior performance over the competing baselines, on either vision and language bi-modality or single visual modality.

We aim to provide a computationally cheap yet effective approach for fine-grained image classification (FGIC) in this letter. Unlike previous methods that rely on complex part localization modules, our approach learns fine-grained features by enhancing the semantics of sub-features of a global feature. Specifically, we first achieve the sub-feature semantic by arranging feature channels of a CNN into different groups through channel permutation. Meanwhile, to enhance the discriminability of sub-features, the groups are guided to be activated on object parts with strong discriminability by a weighted combination regularization. Our approach is parameter parsimonious and can be easily integrated into the backbone model as a plug-and-play module for end-to-end training with only image-level supervision. Experiments verified the effectiveness of our approach and validated its comparable performance to the state-of-the-art methods. Code is available at https://github.com/cswluo/SEF, Comment: Accepted by IEEE Signal Processing Letters. 5 pages, 4 figures, 4 tables

Reusable model design becomes desirable with the rapid expansion of computer vision and pattern recognition applications. In this paper, we focus on the reusability of pre-trained deep convolutional models. Specifically, different from treating pre-trained models as feature extractors, we reveal more treasures beneath convolutional layers, i.e., the convolutional activations could act as a detector for the common object in the object co-localization problem. We propose a simple yet effective method, termed Deep Descriptor Transformation (DDT), for evaluating the correlations of descriptors and then obtaining the category-consistent regions, which can accurately locate the common object in a set of unlabeled images, i.e., object co-localization. Empirical studies validate the effectiveness of the proposed DDT method. On benchmark object co-localization datasets, DDT consistently outperforms existing state-of-the-art methods by a large margin. Moreover, DDT also demonstrates good generalization ability for unseen categories and robustness for dealing with noisy data. Beyond those, DDT can be also employed for harvesting web images into valid external data sources for improving performance of both image recognition and object detection.

DOI: 10.3969/j.issn.1672-6731.2019.04.013

One single instance could possess multiple portraits and reveal diverse relationships with others according to different contexts. Those ambiguities increase the difficulty of learning a generalizable model when there exists one concept or mixed concepts in a task. We propose a general approach Learning to Decompose Network (LeadNet) for both two cases, which contextualizes a model through meta-learning multiple maps for concepts discovery -- the representations of instances are decomposed and adapted conditioned on the contexts. Through taking a holistic view over multiple latent components over instances in a sampled pseudo task, LeadNet learns to automatically select the right concept via incorporating those rich semantics inside and between objects. LeadNet demonstrates its superiority in various applications, including exploring multiple views of confusing tasks, out-of-distribution recognition, and few-shot image classification.

Separators play a vital role in electronic insulation and ionic conduction in lithium-ion batteries. The common improvement strategy of polyolefin separators is mostly based on modifications with a coating layer, which is simple and effective to some extent. However, the improvement is often accompanied by negative effects such as the increase of the thickness and the blockage of the porous structure, resulting in the decrease of energy density and power density. The porous structure of the separators serves as a conduction path for ions to travel back and forth between the anode and cathode, which has an important impact on the performance of lithium-ion batteries. If the porous structure of the separators can be modified, it will essentially affect the ionic transport behavior through the whole conduction path. Herein, we provide a simple and effective method to functionalize the porous polyolefin separator via the γ-ray co-irradiation grafting process, where high-energy γ-ray is used to generate active sites on the polymer chain to initiate the grafting polymerization of chosen monomers with selected functional groups. In this work, 4,4,5,5-tetramethyl-2-vinyl-1,3,2-dioxaborolane, a kind of borane molecule with an electron-deficient group, was chosen as the grafting monomer. After the γ-ray co-irradiation grafting process, both the surface and pores of the polyolefin separators were functionalized by electron-deficient groups in the borane molecule and the whole electrolyte conduction path within the separator was activated. Due to the electron-deficient effect of the B atom, the lithium-ion conduction is promoted and the lithium-ion transference number can be increased to 0.5. As a result, the half-cell assembled with the functionalized separator shows better cycle stability and better capacity retention under high current rate.

Learning discriminative image representations plays a vital role in long-tailed image classification because it can ease the classifier learning in imbalanced cases. Given the promising performance contrastive learning has shown recently in representation learning, in this work, we explore effective supervised contrastive learning strategies and tailor them to learn better image representations from imbalanced data in order to boost the classification accuracy thereon. Specifically, we propose a novel hybrid network structure being composed of a supervised contrastive loss to learn image representations and a cross-entropy loss to learn classifiers, where the learning is progressively transited from feature learning to the classifier learning to embody the idea that better features make better classifiers. We explore two variants of contrastive loss for feature learning, which vary in the forms but share a common idea of pulling the samples from the same class together in the normalized embedding space and pushing the samples from different classes apart. One of them is the recently proposed supervised contrastive (SC) loss, which is designed on top of the state-of-the-art unsupervised contrastive loss by incorporating positive samples from the same class. The other is a prototypical supervised contrastive (PSC) learning strategy which addresses the intensive memory consumption in standard SC loss and thus shows more promise under limited memory budget. Extensive experiments on three long-tailed classification datasets demonstrate the advantage of the proposed contrastive learning based hybrid networks in long-tailed classification., Comment: CVPR 2021

Circular RNAs (circRNAs) are stable covalently closed non-coding RNAs (ncRNAs). Many studies indicate that circRNAs are involved in the pathological and physiological processes of liver cancer. However, the functions of circRNAs in liver cancer immunity are less known. In this review, we summarized the functions of circRNAs in liver cancer, including proliferative, metastasis and apoptosis, liver cancer stemness, cell cycle, immune evasion, glycolysis, angiogenesis, drug resistance/sensitizer, and senescence. Immune escape is considered to be one of the hallmarks of cancer development, and circRNA participates in the immune escape of liver cancer cells by regulating natural killer (NK) cell function. CircRNAs may provide new ideas for immunotherapy in liver cancer.

The commercial electrolyte of lithium-ion batteries (LIBs) is usually liquid state supplemented by a porous polyolefin separator to prevent short circuit. Recent years, polymer electrolyte shows great potential for its flexibility and enhanced safety. And novel single-ion conductor gel polymer electrolyte (SIGPE) could effectively suppress the anion polarization by immobilizing anions on the polymer bone. Further enhancing the thermal stability of SIGPE plays a significant role for the safety of the LIBs. Herein, a novel bifunctional core–shell structured composite was prepared, consisting of thermal stable polyimide as core and a composite single-ion conductor polymer. The relations of fiber morphology with spinning parameters and heat-treatment temperature were studied carefully. As a result, the composite core–shell structured membrane shows excellent high dimensional thermal stability up to 190 °C. Moreover, when the charged half battery was stored at 150 °C, the core–shell structured SIGPE cell shows excellent potential stability while ordinary cell quickly short out, greatly enhancing the safety of the LIBs. The ionic conductivity of the plasticized gel electrolyte could reach 1.7*10−5 S cm−1 with a Li-ion transference number of 0.76. The assembled LiFePO4 battery shows stable cycle performance and remained 85% capacity after 100 cycles.