Chen Yang

Yongxin Cao, Fanghua Liu, Lai Jiang et al.

In recent years, deep learning has made significant progress in wood panel defect detection. However, there are still challenges such as low detection , slow detection speed, and difficulties in deploying embedded devices on wood panel surfaces. To overcome these issues, we propose a lightweight wood panel defect detection method called YOLOv5-LW, which incorporates attention mechanisms and a feature fusion network.Firstly, to enhance the detection capability of acceptable defects, we introduce the Multi-scale Bi-directional Feature Pyramid Network (MBiFPN) as a feature fusion network. The MBiFPN reduces feature loss, enriches local and detailed features, and improves the model's detection capability for acceptable defects.Secondly, to achieve a lightweight design, we reconstruct the ShuffleNetv2 network model as the backbone network. This reconstruction reduces the number of parameters and computational requirements while maintaining performance. We also introduce the Stem Block and Spatial Pyramid Pooling Fast (SPPF) models to compensate for any accuracy loss resulting from the lightweight design, ensuring the model's detection capabilities remain intact while being computationally efficient.Thirdly, we enhance the backbone network by incorporating Efficient Channel Attention (ECA), which improves the network's focus on key information relevant to defect detection. By attending to essential features, the model becomes more proficient in accurately identifying and localizing defects.We validate the proposed method using a self-developed wood panel defect dataset.The experimental results demonstrate the effectiveness of the improved YOLOv5-LW method. Compared to the original model, our approach achieves a 92.8\% accuracy rate, reduces the number of parameters by 27.78\%, compresses computational volume by 41.25\%, improves detection inference speed by 10.16\%

Zhen Chen, Meilu Zhu, Chen Yang et al.

Nowadays, deep learning methods with large-scale datasets can produce clinically useful models for computer-aided diagnosis. However, the privacy and ethical concerns are increasingly critical, which make it difficult to collect large quantities of data from multiple institutions. Federated Learning (FL) provides a promising decentralized solution to train model collaboratively by exchanging client models instead of private data. However, the server aggregation of existing FL methods is observed to degrade the model performance in real-world medical FL setting, which is termed as retrogress. To address this problem, we propose a personalized retrogress-resilient framework to produce a superior personalized model for each client. Specifically, we devise a Progressive Fourier Aggregation (PFA) at the server to achieve more stable and effective global knowledge gathering by integrating client models from low-frequency to high-frequency gradually. Moreover, with an introduced deputy model to receive the aggregated server model, we design a Deputy-Enhanced Transfer (DET) strategy at the client and conduct three steps of Recover-Exchange-Sublimate to ameliorate the personalized local model by transferring the global knowledge smoothly. Extensive experiments on real-world dermoscopic FL dataset prove that our personalized retrogress-resilient framework outperforms state-of-the-art FL methods, as well as the generalization on an out-of-distribution cohort. The code and dataset are available at https://github.com/CityU-AIM-Group/PRR-FL.

Wuwei Lan, Yang Chen, Wei Xu et al.

Multilingual pre-trained Transformers, such as mBERT (Devlin et al., 2019) and XLM-RoBERTa (Conneau et al., 2020a), have been shown to enable the effective cross-lingual zero-shot transfer. However, their performance on Arabic information extraction (IE) tasks is not very well studied. In this paper, we pre-train a customized bilingual BERT, dubbed GigaBERT, that is designed specifically for Arabic NLP and English-to-Arabic zero-shot transfer learning. We study GigaBERT's effectiveness on zero-short transfer across four IE tasks: named entity recognition, part-of-speech tagging, argument role labeling, and relation extraction. Our best model significantly outperforms mBERT, XLM-RoBERTa, and AraBERT (Antoun et al., 2020) in both the supervised and zero-shot transfer settings. We have made our pre-trained models publicly available at https://github.com/lanwuwei/GigaBERT.

Duong Minh Le, Yang Chen, Alan Ritter et al.

Zero-shot cross-lingual transfer utilizing multilingual LLMs has become a popular learning paradigm for low-resource languages with no labeled training data. However, for NLP tasks that involve fine-grained predictions on words and phrases, the performance of zero-shot cross-lingual transfer learning lags far behind supervised fine-tuning methods. Therefore, it is common to exploit translation and label projection to further improve the performance by (1) translating training data that is available in a high-resource language (e.g., English) together with the gold labels into low-resource languages, and/or (2) translating test data in low-resource languages to a high-source language to run inference on, then projecting the predicted span-level labels back onto the original test data. However, state-of-the-art marker-based label projection methods suffer from translation quality degradation due to the extra label markers injected in the input to the translation model. In this work, we explore a new direction that leverages constrained decoding for label projection to overcome the aforementioned issues. Our new method not only can preserve the quality of translated texts but also has the versatility of being applicable to both translating training and translating test data strategies. This versatility is crucial as our experiments reveal that translating test data can lead to a considerable boost in performance compared to translating only training data. We evaluate on two cross-lingual transfer tasks, namely Named Entity Recognition and Event Argument Extraction, spanning 20 languages. The results demonstrate that our approach outperforms the state-of-the-art marker-based method by a large margin and also shows better performance than other label projection methods that rely on external word alignment.

Shulin Lan, Kanlin Liu, Yazhou Zhao et al.

Current passive deepfake face-swapping detection methods encounter significance bottlenecks in model generalization capabilities. Meanwhile, proactive detection methods often use fixed watermarks which lack a close relationship with the content they protect and are vulnerable to security risks. Dynamic watermarks based on facial features offer a promising solution, as these features provide unique identifiers. Therefore, this paper proposes a Facial Feature-based Proactive deepfake detection method (FaceProtect), which utilizes changes in facial characteristics during deepfake manipulation as a novel detection mechanism. We introduce a GAN-based One-way Dynamic Watermark Generating Mechanism (GODWGM) that uses 128-dimensional facial feature vectors as inputs. This method creates irreversible mappings from facial features to watermarks, enhancing protection against various reverse inference attacks. Additionally, we propose a Watermark-based Verification Strategy (WVS) that combines steganography with GODWGM, allowing simultaneous transmission of the benchmark watermark representing facial features within the image. Experimental results demonstrate that our proposed method maintains exceptional detection performance and exhibits high practicality on images altered by various deepfake techniques.

Xiaoqing Guo, Chen Yang, Baopu Li et al.

Unsupervised domain adaptation (UDA) aims to transfer the knowledge from the labeled source domain to the unlabeled target domain. Existing self-training based UDA approaches assign pseudo labels for target data and treat them as ground truth labels to fully leverage unlabeled target data for model adaptation. However, the generated pseudo labels from the model optimized on the source domain inevitably contain noise due to the domain gap. To tackle this issue, we advance a MetaCorrection framework, where a Domain-aware Meta-learning strategy is devised to benefit Loss Correction (DMLC) for UDA semantic segmentation. In particular, we model the noise distribution of pseudo labels in target domain by introducing a noise transition matrix (NTM) and construct meta data set with domain-invariant source data to guide the estimation of NTM. Through the risk minimization on the meta data set, the optimized NTM thus can correct the noisy issues in pseudo labels and enhance the generalization ability of the model on the target data. Considering the capacity gap between shallow and deep features, we further employ the proposed DMLC strategy to provide matched and compatible supervision signals for different level features, thereby ensuring deep adaptation. Extensive experimental results highlight the effectiveness of our method against existing state-of-the-art methods on three benchmarks.

Junfu Chen, Yue Pan, Yang Chen

Remote sensing image fusion technology (pan-sharpening) is an important means to improve the information capacity of remote sensing images. Inspired by the efficient arameter space posteriori sampling of Bayesian neural networks, in this paper we propose a Bayesian Generative Adversarial Network based on Preconditioned Stochastic Gradient Langevin Dynamics (PGSLD-BGAN) to improve pan-sharpening tasks. Unlike many traditional generative models that consider only one optimal solution (might be locally optimal), the proposed PGSLD-BGAN performs Bayesian inference on the network parameters, and explore the generator posteriori distribution, which assists selecting the appropriate generator parameters. First, we build a two-stream generator network with PAN and MS images as input, which consists of three parts: feature extraction, feature fusion and image reconstruction. Then, we leverage Markov discriminator to enhance the ability of generator to reconstruct the fusion image, so that the result image can retain more details. Finally, introducing Preconditioned Stochastic Gradient Langevin Dynamics policy, we perform Bayesian inference on the generator network. Experiments on QuickBird and WorldView datasets show that the model proposed in this paper can effectively fuse PAN and MS images, and be competitive with even superior to state of the arts in terms of subjective and objective metrics.

Yang Chen, Martin Alain, Aljosa Smolic

High angular resolution is advantageous for practical applications of light fields. In order to enhance the angular resolution of light fields, view synthesis methods can be utilized to generate dense intermediate views from sparse light field input. Most successful view synthesis methods are learning-based approaches which require a large amount of training data paired with ground truth. However, collecting such large datasets for light fields is challenging compared to natural images or videos. To tackle this problem, we propose a self-supervised light field view synthesis framework with cycle consistency. The proposed method aims to transfer prior knowledge learned from high quality natural video datasets to the light field view synthesis task, which reduces the need for labeled light field data. A cycle consistency constraint is used to build bidirectional mapping enforcing the generated views to be consistent with the input views. Derived from this key concept, two loss functions, cycle loss and reconstruction loss, are used to fine-tune the pre-trained model of a state-of-the-art video interpolation method. The proposed method is evaluated on various datasets to validate its robustness, and results show it not only achieves competitive performance compared to supervised fine-tuning, but also outperforms state-of-the-art light field view synthesis methods, especially when generating multiple intermediate views. Besides, our generic light field view synthesis framework can be adopted to any pre-trained model for advanced video interpolation.

Xiaoqing Guo, Chen Yang, Pak Lun Lam et al.

Automatically segmenting sub-regions of gliomas (necrosis, edema and enhancing tumor) and accurately predicting overall survival (OS) time from multimodal MRI sequences have important clinical significance in diagnosis, prognosis and treatment of gliomas. However, due to the high degree variations of heterogeneous appearance and individual physical state, the segmentation of sub-regions and OS prediction are very challenging. To deal with these challenges, we utilize a 3D dilated multi-fiber network (DMFNet) with weighted dice loss for brain tumor segmentation, which incorporates prior volume statistic knowledge and obtains a balance between small and large objects in MRI scans. For OS prediction, we propose a DenseNet based 3D neural network with position encoding convolutional layer (PECL) to extract meaningful features from T1 contrast MRI, T2 MRI and previously segmented subregions. Both labeled data and unlabeled data are utilized to prevent over-fitting for semi-supervised learning. Those learned deep features along with handcrafted features (such as ages, volume of tumor) and position encoding segmentation features are fed to a Gradient Boosting Decision Tree (GBDT) to predict a specific OS day

Cai Ning, Shi Fei, Hu Dianlin et al.

In this work we propose a ResNet-based universal method for speckle reduction in optical coherence tomography (OCT) images. The proposed model contains 3 main modules: Convolution-BN-ReLU, Branch and Residual module. Unlike traditional algorithms, the model can learn from training data instead of selecting parameters manually such as noise level. Application of this proposed method to the OCT images shows a more than 22 dB signal-to-noise ratio improvement in speckle noise reduction with minimal structure blurring. The proposed method provides strong generalization ability and can process noisy other types of OCT images without retraining. It outperforms other filtering methods in suppressing speckle noises and revealing subtle features.