Query：
学者姓名：林洛君
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-
Language
Clean All
Abstract ：
Domain Generalization (DG) aims to generalize a model trained on multiple source domains to an unseen target domain. The source domains always require precise annotations, which can be cumbersome or even infeasible to obtain in practice due to the vast amount of data involved. Web data, namely web -crawled images, offers an opportunity to access large amounts of unlabeled images with rich style information, which can be leveraged to improve DG. From this perspective, we introduce a novel paradigm of DG, termed as Semi -Supervised Domain Generalization (SSDG), to explore how the labeled and unlabeled source domains can interact, and establish two settings, including the close -set and open -set SSDG. The close -set SSDG is based on existing public DG datasets, while the open -set SSDG, built on the newly -collected web -crawled datasets, presents a novel yet realistic challenge that pushes the limits of current technologies. A natural approach of SSDG is to transfer knowledge from labeled data to unlabeled data via pseudo labeling, and train the model on both labeled and pseudo -labeled data for generalization. Since there are conflicting goals between domain -oriented pseudo labeling and out -of -domain generalization, we develop a pseudo labeling phase and a generalization phase independently for SSDG. Unfortunately, due to the large domain gap, the pseudo labels provided in the pseudo labeling phase inevitably contain noise, which has negative affect on the subsequent generalization phase. Therefore, to improve the quality of pseudo labels and further enhance generalizability, we propose a cyclic learning framework to encourage a positive feedback between these two phases, utilizing an evolving intermediate domain that bridges the labeled and unlabeled domains in a curriculum learning manner. Extensive experiments are conducted to validate the effectiveness of our method. It is worth highlighting that web -crawled images can promote domain generalization as demonstrated by the experimental results.
Keyword ：
Domain generalization Domain generalization Semi-supervised learning Semi-supervised learning Transfer learning Transfer learning Unsupervised domain adaptation Unsupervised domain adaptation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Luojun , Xie, Han , Sun, Zhishu et al. Semi-supervised domain generalization with evolving intermediate domain [J]. | PATTERN RECOGNITION , 2024 , 149 . |
| MLA | Lin, Luojun et al. "Semi-supervised domain generalization with evolving intermediate domain" . | PATTERN RECOGNITION 149 (2024) . |
| APA | Lin, Luojun , Xie, Han , Sun, Zhishu , Chen, Weijie , Liu, Wenxi , Yu, Yuanlong et al. Semi-supervised domain generalization with evolving intermediate domain . | PATTERN RECOGNITION , 2024 , 149 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
With the growing significance of data privacy protection, Source-Free Domain Adaptation (SFDA) has gained attention as a research topic that aims to transfer knowledge from a labeled source domain to an unlabeled target domain without accessing source data. However, the absence of source data often leads to model collapse or restricts the performance improvements of SFDA methods, as there is insufficient true-labeled knowledge for each category. To tackle this, Source-Free Active Domain Adaptation (SFADA) has emerged as a new task that aims to improve SFDA by selecting a small set of informative target samples labeled by experts. Nevertheless, existing SFADA methods impose a significant burden on human labelers, requiring them to continuously label a substantial number of samples throughout the training period. In this paper, a novel approach is proposed to alleviate the labeling burden in SFADA by only necessitating the labeling of an extremely small number of samples on a one-time basis. Moreover, considering the inherent sparsity of these selected samples in the target domain, a Self-adaptive Clustering-based Active Learning (SCAL) method is proposed that propagates the labels of selected samples to other datapoints within the same cluster. To further enhance the accuracy of SCAL, a self-adaptive scale search method is devised that automatically determines the optimal clustering scale, using the entropy of the entire target dataset as a guiding criterion. The experimental evaluation presents compelling evidence of our method's supremacy. Specifically, it outstrips previous SFDA methods, delivering state-of-the-art (SOTA) results on standard benchmarks. Remarkably, it accomplishes this with less than 0.5% annotation cost, in stark contrast to the approximate 5% required by earlier techniques. The approach thus not only sets new performance benchmarks but also offers a markedly more practical and cost-effective solution for SFADA, making it an attractive choice for real-world applications where labeling resources are limited. We propose a novel approach to alleviate the labeling burden in SFADA by only necessitating the labeling of an extremely small number of samples on a one-time basis. Moreover, considering the inherent sparsity of these selected samples in the target domain, we propose a Self-adaptive Clustering-based Active Learning (SCAL) method that propagates the labels of selected samples to other datapoints within the same cluster. To further enhance the accuracy of SCAL, we devise an self-adaptive scale search method that automatically determines the optimal clustering scale, using the entropy of the entire target dataset as a guiding criterion.image
Keyword ：
computer vision computer vision image recognition image recognition
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Sun, Zhishu , Lin, Luojun , Yu, Yuanlong . You only label once: A self-adaptive clustering-based method for source-free active domain adaptation [J]. | IET IMAGE PROCESSING , 2024 , 18 (5) : 1268-1282 . |
| MLA | Sun, Zhishu et al. "You only label once: A self-adaptive clustering-based method for source-free active domain adaptation" . | IET IMAGE PROCESSING 18 . 5 (2024) : 1268-1282 . |
| APA | Sun, Zhishu , Lin, Luojun , Yu, Yuanlong . You only label once: A self-adaptive clustering-based method for source-free active domain adaptation . | IET IMAGE PROCESSING , 2024 , 18 (5) , 1268-1282 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Facial Beauty Prediction (FBP) is a significant pattern recognition task that aims to achieve consistent facial attractiveness assessment with human perception. Currently, Convolutional Neural Networks (CNNs) have become the mainstream method for FBP. The training objective of most conventional CNNs is usually to learn static convolution kernels, which, however, makes the network quite difficult to capture global attentive information, and thus usually ignores the key facial regions, e.g., eyes, and nose. To tackle this problem, we devise a new convolution manner, Dynamic Attentive Convolution (DyAttenConv), which integrates the dynamic and attention mechanism into convolution in kernel -level, with the aim of enforcing the convolution kernels adapted to each face dynamically. DyAttenConv is a plug -and -play module that can be flexibly combined with existing CNN architectures, making the acquisition of the beauty -related features more globally and attentively. Extensive ablation studies show that our method is superior to other fusion and attention mechanisms, and the comparison with other state -of -the -arts also demonstrates the effectiveness of DyAttenConv on facial beauty prediction task.
Keyword ：
dynamic convolution dynamic convolution facial beauty prediction facial beauty prediction kernel attention kernel attention
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Sun, Zhishu , Xiao, Zilong , Yu, Yuanlong et al. Dynamic Attentive Convolution for Facial Beauty Prediction [J]. | IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS , 2024 , E107 (2) : 239-243 . |
| MLA | Sun, Zhishu et al. "Dynamic Attentive Convolution for Facial Beauty Prediction" . | IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS E107 . 2 (2024) : 239-243 . |
| APA | Sun, Zhishu , Xiao, Zilong , Yu, Yuanlong , Lin, Luojun . Dynamic Attentive Convolution for Facial Beauty Prediction . | IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS , 2024 , E107 (2) , 239-243 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Self-ensemble adversarial training methods improve model robustness by ensembling models at different training epochs, such as model weight averaging (WA). However, previous research has shown that self-ensemble defense methods in adversarial training (AT) still suffer from robust overfitting, which severely affects the generalization performance. Empirically, in the late phases of training, the AT becomes more overfitting to the extent that the individuals for weight averaging also suffer from overfitting and produce anomalous weight values, which causes the self-ensemble model to continue to undergo robust overfitting due to the failure in removing the weight anomalies. To solve this problem, we aim to tackle the influence of outliers in the weight space in this work and propose an easy-to-operate and effective Median-Ensemble Adversarial Training (MEAT) method to solve the robust overfitting phenomenon existing in self-ensemble defense from the source by searching for the median of the historical model weights. Experimental results show that MEAT achieves the best robustness against the powerful AutoAttack and can effectively allievate the robust overfitting. We further demonstrate that most defense methods can improve robust generalization and robustness by combining with MEAT. © 2024 IEEE.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Hu, Zhaozhe , Yin, Jia-Li , Chen, Bin et al. MEAT: MEDIAN-ENSEMBLE ADVERSARIAL TRAINING FOR IMPROVING ROBUSTNESS AND GENERALIZATION [C] . 2024 : 5600-5604 . |
| MLA | Hu, Zhaozhe et al. "MEAT: MEDIAN-ENSEMBLE ADVERSARIAL TRAINING FOR IMPROVING ROBUSTNESS AND GENERALIZATION" . (2024) : 5600-5604 . |
| APA | Hu, Zhaozhe , Yin, Jia-Li , Chen, Bin , Lin, Luojun , Chen, Bo-Hao , Liu, Ximeng . MEAT: MEDIAN-ENSEMBLE ADVERSARIAL TRAINING FOR IMPROVING ROBUSTNESS AND GENERALIZATION . (2024) : 5600-5604 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Facial beauty prediction (FBP) aims to develop a system to assess facial attractiveness automatically. Through prior research and our own observations, it has become evident that attribute information, such as gender and race, is a key factor leading to the distribution discrepancy in the FBP data. Such distribution discrepancy hinders current conventional FBP models from generalizing effectively to unseen attribute domain data, thereby discounting further performance improvement. To address this problem, in this paper, we exploit the attribute information to guide the training of convolutional neural networks (CNNs), with the final purpose of implicit feature alignment across various attribute domain data. To this end, we introduce the attribute information into convolution layer and batch normalization (BN) layer, respectively, as they are the most crucial parts for representation learning in CNNs. Specifically, our method includes: 1) Attribute -guided convolution (AgConv) that dynamically updates convolutional filters based on attributes by parameter tuning or parameter rebirth; 2) Attribute -guided batch normalization (AgBN) is developed to compute the attribute -specific statistics through an attribute guided batch sampling strategy; 3) To benefit from both approaches, we construct an integrated framework by combining AgConv and AgBN to achieve a more thorough feature alignment across different attribute domains. Extensive qualitative and quantitative experiments have been conducted on the SCUTFBP, SCUT-FBP5500 and HotOrNot benchmark datasets. The results show that AgConv significantly improves the attribute -guided representation learning capacity and AgBN provides more stable optimization. Owing to the combination of AgConv and AgBN, the proposed framework (Ag-Net) achieves further performance improvement and is superior to other state-of-the-art approaches for FBP.
Keyword ：
Batch normalization Batch normalization Dynamic convolution Dynamic convolution Facial attractiveness assessment Facial attractiveness assessment Facial beauty prediction Facial beauty prediction
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Sun, Zhishu , Lin, Luojun , Yu, Yuanlong et al. Learning feature alignment across attribute domains for improving facial beauty prediction [J]. | EXPERT SYSTEMS WITH APPLICATIONS , 2024 , 249 . |
| MLA | Sun, Zhishu et al. "Learning feature alignment across attribute domains for improving facial beauty prediction" . | EXPERT SYSTEMS WITH APPLICATIONS 249 (2024) . |
| APA | Sun, Zhishu , Lin, Luojun , Yu, Yuanlong , Jin, Lianwen . Learning feature alignment across attribute domains for improving facial beauty prediction . | EXPERT SYSTEMS WITH APPLICATIONS , 2024 , 249 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Unsupervised Domain Adaptive Object Detection (DAOD) task can relax the domain shift problem between source and target domains, which requires to train models on labeled source and unlabeled target domains jointly. However, due to limitations of data privacy protection, the source domain data is usually inaccessible, which poses significant challenges for the DAOD task. Hence, Source-Free Object Detection (SFOD) task has been developed that aims to fine-tune a pre-trained source model with only unlabeled target domain data. Most of the existing SFOD methods are based on pseudo labeling using the student-teacher framework, where the teacher model is the Exponential Moving Average (EMA) of the student models in different time steps. However, these methods always exist a knowledge bias problem due to class imbalance, and therefore, a fixed EMA update rate is no longer suitable for different classes. For high-quality classes, a fast EMA rate can accelerate knowledge updating and promote model convergence, while for low-quality classes, a fast EMA rate can accelerate the accumulation of knowledge bias and lead to the collapse of such categories. To solve this problem, we propose a novel SFOD method called Slow-Fast Adaptation which develops two different teacher models, a slow teacher, and a fast teacher model, to jointly guide the student training. The slow and fast teacher models can provide richer supervision information and complement each other. The experiments on four benchmark datasets show that our method achieves state-of-the-art results and even outperforms DAOD methods in some cases, which demonstrate the effectiveness of our method on the SFOD task. © 2024 IEEE.
Keyword ：
Data privacy Data privacy Differential privacy Differential privacy Domain Knowledge Domain Knowledge Personnel training Personnel training Problem solving Problem solving Students Students Teaching Teaching
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Luojun , Liu, Qipeng , Zheng, Xiangwei et al. Slow-Fast Adaptation for Source-Free Object Detection [C] . 2024 . |
| MLA | Lin, Luojun et al. "Slow-Fast Adaptation for Source-Free Object Detection" . (2024) . |
| APA | Lin, Luojun , Liu, Qipeng , Zheng, Xiangwei , Lin, Zheng . Slow-Fast Adaptation for Source-Free Object Detection . (2024) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Image segmentation tasks aim to separate the image into masks that represent different objects or regions, where deep-learning-based methods have become mainstream. In the common practice, researchers utilize large-scale datasets including images along with their annotations to train their models, and evaluate the predictions with evaluation metrics. However, to our knowledge, no metrics have been proposed to assess the quality of the segmentation annotations, which will bring benefits to both the labeling and experimental process. In this paper, we fill this research gap and propose the first no-reference segmentation annotation quality assessment named SAQ. Based on our observation, we utilize the normal gradients of pixels on the annotation contours to represent the degree of fitting the real contours, which reflect the annotation accuracy. To alleviate the image differences, we adopt the gradient ranking score rather than directly using the gradient value. The multi-scale strategy is introduced to accommodate annotations of objects with different structures. Extensive experiments on datasets for various segmentation tasks have demonstrated the rationality of our proposed SAQ, and the assessment results of their annotation quality can serve as significant references for researchers. © 2024 IEEE.
Keyword ：
Deep learning Deep learning Image annotation Image annotation Image segmentation Image segmentation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Zheng , Duan, Zheng-Peng , Zhang, Xuying et al. No-Reference Segmentation Annotation Quality Assessment [C] . 2024 . |
| MLA | Lin, Zheng et al. "No-Reference Segmentation Annotation Quality Assessment" . (2024) . |
| APA | Lin, Zheng , Duan, Zheng-Peng , Zhang, Xuying , Lin, Luojun . No-Reference Segmentation Annotation Quality Assessment . (2024) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Facing complex remote sensing scenes, detection models with single detection mechanisms cannot always provide satisfactory detection capabilities. In order to obtain better detection performance in various remote sensing scenes, this paper constructs a novel ensemble model, namely: the multiple prediction mechanisms ensemble (MPME). In order to improve the feature representation ability and region recognition ability of the ensemble model, we build the ensemble of feature pyramids (EFP) and the ensemble of detection heads (EDH) respectively. In order to further improve the detection accuracy of the ensemble model, we propose a training strategy (k-Nearest Loss Learning), so that each sub-detector does not need to learn a trade-off among all training samples, and also reduces the possibility of model over-fitting. The experimental results show that our MPME is a more efficient and effective ensemble model. Compared with other ensemble models, our MPME has a faster detection speed and better detection accuracy. Compared with other state-of-the-art detectors, our detector also achieves superior detection performance. © 2023 ACM.
Keyword ：
ensemble model ensemble model object detection object detection remote sensing remote sensing
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Feng, L.Q. , Luo, Jun, L. , Yuan, Long, Y. et al. A Multiple Prediction Mechanisms Ensemble for Complex Remote Sensing Scenes [未知]. |
| MLA | Feng, L.Q. et al. "A Multiple Prediction Mechanisms Ensemble for Complex Remote Sensing Scenes" [未知]. |
| APA | Feng, L.Q. , Luo, Jun, L. , Yuan, Long, Y. , Fu, G. . A Multiple Prediction Mechanisms Ensemble for Complex Remote Sensing Scenes [未知]. |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Agnostic domain shift is the main reason of model degradation on the unknown target domains, which brings an urgent need to develop Domain generalization (DG). Recent advances at DG use dynamic networks to achieve training-free adaptation on the unknown target domains, termed Dynamic Domain Generalization (DDG), which compensates for the lack of self-adaptability in static models with fixed weights. The parameters of dynamic networks can be decoupled into a static and a dynamic component, which are designed to learn domain-invariant and domain-specific features, respectively. Based on the existing arts, in this work, we try to push the limits of DDG by disentangling the static and dynamic components more thoroughly from an optimization perspective. Our main consideration is that we can enable the static component to learn domain-invariant features more comprehensively by augmenting the domain-specific information. As a result, the more comprehensive domain-invariant features learned by the static component can then enforce the dynamic component to focus more on learning adaptive domain-specific features. To this end, we propose a simple yet effective Parameter Exchange (PE) method to perturb the combination between the static and dynamic components. We optimize the model using the gradients from both the perturbed and non-perturbed feed-forward jointly to implicitly achieve the aforementioned disentanglement. In this way, the two components can be optimized in a mutually-beneficial manner, which can resist the agnostic domain shifts and improve the self-adaptability on the unknown target domain. Extensive experiments show that PE can be easily plugged into existing dynamic networks to improve their generalization ability without bells and whistles. © 2023 ACM.
Keyword ：
domain generalization domain generalization dynamic network dynamic network transfer learning transfer learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, L. , Shen, Z. , Sun, Z. et al. Parameter Exchange for Robust Dynamic Domain Generalization [未知]. |
| MLA | Lin, L. et al. "Parameter Exchange for Robust Dynamic Domain Generalization" [未知]. |
| APA | Lin, L. , Shen, Z. , Sun, Z. , Yu, Y. , Zhang, L. , Chen, W. . Parameter Exchange for Robust Dynamic Domain Generalization [未知]. |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Predicting individual aesthetic preferences holds significant practical applications and academic implications for human society. However, existing studies mainly focus on learning and predicting the commonality of facial attractiveness, with little attention given to Personalized Facial Beauty Prediction (PFBP). PFBP aims to develop a machine that can adapt to individual aesthetic preferences with only a few images rated by each user. In this paper, we formulate this task from a meta-learning perspective that each user corresponds to a meta-task. To address such PFBP task, we draw inspiration from the human aesthetic mechanism that visual aesthetics in society follows a Gaussian distribution, which motivates us to disentangle user preferences into a commonality and an individuality part. To this end, we propose a novel MetaFBP framework, in which we devise a universal feature extractor to capture the aesthetic commonality and then optimize to adapt the aesthetic individuality by shifting the decision boundary of the predictor via a meta-learning mechanism. Unlike conventional meta-learning methods that may struggle with slow adaptation or overfitting to tiny support sets, we propose a novel approach that optimizes a high-order predictor for fast adaptation. In order to validate the performance of the proposed method, we build several PFBP benchmarks by using existing facial beauty prediction datasets rated by numerous users. Extensive experiments on these benchmarks demonstrate the effectiveness of the proposed MetaFBP method. © 2023 ACM.
Keyword ：
dynamic network dynamic network facial beauty prediction facial beauty prediction meta learning meta learning personalized recommendation personalized recommendation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, L. , Shen, Z. , Yin, J.-L. et al. MetaFBP: Learning to Learn High-Order Predictor for Personalized Facial Beauty Prediction [未知]. |
| MLA | Lin, L. et al. "MetaFBP: Learning to Learn High-Order Predictor for Personalized Facial Beauty Prediction" [未知]. |
| APA | Lin, L. , Shen, Z. , Yin, J.-L. , Liu, Q. , Yu, Y. , Chen, W. . MetaFBP: Learning to Learn High-Order Predictor for Personalized Facial Beauty Prediction [未知]. |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
