检索结果-内蒙古大学图书馆

Flip-chip bonded 8-channel DFB laser array with highly uniform 400 GHz spacing and high output power for optical I/O technology

学校读者我要写书评

暂无评论

Chinese Optics Letters 2025年第4期 104-110页

作者：赵杰孙振兴戴攀张进许艳秋张悦汪卓颖聂佳强王文轩肖如磊陈向飞 Key Laboratory of Intelligent Optical Sensing and Manipulation of the Ministry of Education & National Laboratory of Solid State Microstructures & College of Engineering and Applied Sciences & Institute of Optical Communication Engineering & Nanjing University-Tongding Joint Lab for Large-Scale Photonic Integrated Circuits Nanjing University Nanjing Branch China United Network Communications Corporation Limited Ocean College Jiangsu University of Science and Technology

In this paper, we proposed and experimentally demonstrated an 8-channel O-band distributed feedback(DFB) laser array with highly uniform 400 GHz spacing and high output power for optical input/output(I/O) technology. The grating phase is precisely controlled, and an equivalent π phase shift is implemented in the laser cavity via the reconstruction equivalent chirp(REC) technology. Anti-reflection(AR) and high-reflection(HR) films are coated on the front and rear facets, respectively, to enhance output power. The equivalent π phase shift is strategically placed near the HR film facet to improve the yield of the single longitudinal mode. Operating with a 400 GHz wavelength spacing, the proposed DFB laser array meets the continuous wave-wavelength division multiplexing multi-source agreement(CW-WDM MSA) specifications. The proposed DFB laser array is flip-chip bonded to a thin-film circuit with an aluminum nitride(AlN) submount to reduce the thermal resistance and enhance the output power. Compared to the p-side-up structure, the flip-chip bonding design significantly reduces junction temperature by 28% and increases maximum output power by approximately 20%. This design effectively lowers the thermal resistance of the chip and enhances its heat dissipation properties. At a bias current of 110 mA, the laser demonstrates wavelength deviations below 1.579 GHz and side-mode suppression ratios above 50 dB. The far-field divergence is measured at 25.8° × 30.1°, and the Lorentzian linewidth is 3.28 MHz. Increasing the bias current to250 mA results in a laser output power exceeding 80 mW. Furthermore, the relative intensity noise(RIN) for all 8 channels is below-135.3 d B/Hz. The proposed flip-chip bonded 8-channel high-power DFB laser array demonstrates uniform wavelength spacing, high output power, and stable single longitudinal mode performance, making it a promising candidate for multiple wavelength laser sources in optical I/O technology.

关键词：

Better Pseudo-label: Joint Domain-aware label and Dual-classifier for Semi-supervised Domain Generalization

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Ruiqi Qi, Lei Shi, Yinghuan Gao, Yang State Key Laboratory for Novel Software Technology Nanjing University Nanjing China National Institute of Healthcare Data Science Nanjing University Nanjing China School of Computer Science and Engineering Key Lab of Computer Network and Information Integration Ministry of Education Southeast University Nanjing China

With the goal of directly generalizing trained model to unseen target domains, domain generalization (DG), a newly proposed learning paradigm, has attracted considerable attention. Previous DG models usually require a sufficient quantity of annotated samples from observed source domains during training. In this paper, we relax this requirement about full annotation and investigate semisupervised domain generalization (SSDG) where only one source domain is fully annotated along with the other domains totally unlabeled in the training process. With the challenges of tackling the domain gap between observed source domains and predicting unseen target domains, we propose a novel deep framework via joint domain-aware labels and dual-classifier to produce high-quality pseudo-labels. Concretely, to predict accurate pseudo-labels under domain shift, a domain-aware pseudo-labeling module is developed. Also, considering inconsistent goals between generalization and pseudo-labeling: former prevents overfitting on all source domains while latter might overfit the unlabeled source domains for high accuracy, we employ a dual-classifier to independently perform pseudo-labeling and domain generalization in the training process. When accurate pseudo-labels are generated for unlabeled source domains, the domain mixup operation is applied to augment new domains between labeled and unlabeled domains, which is beneficial for boosting the generalization capability of the model. Extensive results on publicly available DG benchmark datasets show the efficacy of our proposed SSDG method. Copyright © 2021, The Authors. All rights reserved.

关键词： Image recognition

LAVS: A LIGHTWEIGHT AUDIO-VISUAL SALIENCY PREDICTION MODEL

学校读者我要写书评

暂无评论

LAVS: A LIGHTWEIGHT AUDIO-VISUAL SALIENCY PREDICTION MODEL

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Zhu, Dandan Zhao, Defang Min, Xiongkuo Han, Tian Zhou, Qiangqiang Yu, Shaobo Chen, Yongqing Zhai, Guangtao Yang, Xiaokang MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China School of Software Engineering Tongji University China Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Department of Computer Science Stevens Institute of Technology United States School of Software Jiangxi Normal University China Information Technology Services East China Normal University China College of Information and Communication Hainan University China

ISBN: (纸本)9781665438643

Audio information is essential for guiding human attention and visual perception, which has been verified by many comprehensive psychological studies. However, the audio modality has been rather neglected in modeling visual attention, most of the current visual attention models heavily depend on visual information. Additionally, current existing high-performing visual attention models rely on deeper convolution neural networks (CNNs), benefiting from their extraordinary feature learning ability but incurring high computational cost. To this end, we propose a novel lightweight audio-visual saliency (LAVS) model to efficiently address the problem of fixation prediction in videos. To the best of our knowledge, our proposed model constitutes the first attempt to exploit a lightweight network and combines the visual and audio cues to perform saliency estimation in videos. Specifically, our proposed model consists of four modules, which are spatial-temporal visual saliency estimation module, audio features extraction module, source sound localization module, and audio-visual saliency fusion module. Extensive experiments across datasets validate the effectiveness and real-time performance of the proposed LAVS model, which outperforms the other state-of-the-art methods. © 2021 IEEE

关键词： Behavioral research

Interpreting dense retrieval as mixture of topics

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhan, Jingtao Mao, Jiaxin Liu, Yiqun Guo, Jiafeng Zhang, Min Ma, Shaoping Department of Computer Science and Technology Institute for Artificial Intelligence Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China Beijing Key Laboratory of Big Data Management and Analysis Methods Gaoling School of Artificial Intelligence Renmin University of China Beijing100872 China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

Dense Retrieval (DR) reaches state-of-the-art results in first-stage retrieval, but little is known about the mechanisms that contribute to its success. Therefore, in this work, we conduct an interpretation study of recently proposed DR models. Specifically, we first discretize the embeddings output by the document and query encoders. Based on the discrete representations, we analyze the attribution of input tokens. Both qualitative and quantitative experiments are carried out on public test collections. Results suggest that DR models pay attention to different aspects of input and extract various high-level topic representations. Therefore, we can regard the representations learned by DR models as a mixture of high-level topics. Copyright © 2021, The Authors. All rights reserved.

关键词： Mixtures

Are Neural Ranking Models Robust?

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wu, Chen Zhang, Ruqing Guo, Jiafeng Fan, Yixing Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing NO. 6 Kexueyuan South Road Haidian District Beijing100190 China

Recently, we have witnessed the bloom of neural ranking models in the information retrieval (IR) field. So far, much effort has been devoted to developing effective neural ranking models that can generalize well on new data. There has been less attention paid to the robustness perspective. Unlike the effectiveness which is about the average performance of a system under normal purpose, robustness cares more about the system performance in the worst case or under malicious operations instead. When a new technique enters into the real-world application, it is critical to know not only how it works in average, but also how would it behave in abnormal situations. So we raise the question in this work: Are neural ranking models robust? To answer this question, firstly, we need to clarify what we refer to when we talk about the robustness of ranking models in IR. We show that robustness is actually a multi-dimensional concept and there are three ways to define it in IR: 1) The performance variance under the independent and identically distributed (I.I.D.) setting;2) The out-of-distribution (OOD) generalizability;and 3) The defensive ability against adversarial operations. The latter two definitions can be further specified into two different perspectives respectively, leading to 5 robustness tasks in total. Based on this taxonomy, we build corresponding benchmark datasets, design empirical experiments, and systematically analyze the robustness of several representative neural ranking models against traditional probabilistic ranking models and learning-to-rank (LTR) models. The empirical results show that there is no simple answer to our question. While neural ranking models are less robust against other IR models in most cases, some of them can still win 2 out of 5 tasks. This is the first comprehensive study on the robustness of neural ranking models. We believe the way we study the robustness as well as our findings would be beneficial to the IR community. We will also

关键词： Machine learning

Learning discrete representations via constrained clustering for effective and efficient dense retrieval

学校读者我要写书评

暂无评论

arXiv 2021年

Dense Retrieval (DR) has achieved state-of-the-art first-stage ranking effectiveness. However, the efficiency of most existing DR models is limited by the large memory cost of storing dense vectors and the time-consuming nearest neighbor search (NNS) in vector space. Therefore, we present RepCONC, a novel retrieval model that learns discrete Representations via CONstrained Clustering. RepCONC jointly trains dual-encoders and the Product Quantization (PQ) method to learn discrete document representations and enables fast approximate NNS with compact indexes. It models quantization as a constrained clustering process, which requires the document embeddings to be uniformly clustered around the quantization centroids and supports end-to-end optimization of the quantization method and dual-encoders. We theoretically demonstrate the importance of the uniform clustering constraint in RepCONC and derive an efficient approximate solution for constrained clustering by reducing it to an instance of the optimal transport problem. Besides constrained clustering, RepCONC further adopts a vector-based inverted file system (IVF) to support highly efficient vector search on CPUs. Extensive experiments on two popular ad-hoc retrieval benchmarks show that RepCONC achieves better ranking effectiveness than competitive vector quantization baselines under different compression ratio settings. It also substantially outperforms a wide range of existing retrieval models in terms of retrieval effectiveness, memory efficiency, and time efficiency. Copyright © 2021, The Authors. All rights reserved.

关键词： Signal encoding

Noise-Tolerant Learning for Audio-Visual Action Recognition

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Han, Haochen Zheng, Qinghua Luo, Minnan Miao, Kaiyao Tian, Feng Chen, Yan The National Engineering Lab for Big Data Analytics Xi’an Jiaotong University Xi’an710049 China The School of Computer Science and Technology Xi’an Jiaotong University Xi’an710049 China The Key Laboratory of Intelligent Networks and Network Security Xi’an Jiaotong University Ministry of Education Xi’an710049 China The School of Cyber Science and Engineering Xi’an Jiaotong University Xi’an710049 China

Recently, video recognition is emerging with the help of multi-modal learning, which focuses on integrating distinct modalities to improve the performance or robustness of the model. Although various multi-modal learning methods have been proposed and offer remarkable recognition results, almost all of these methods rely on high-quality manual annotations and assume that modalities among multi-modal data provide semantically relevant information. Unfortunately, the widely used video datasets are usually coarse-annotated or collected from the Internet. Thus, it inevitably contains a portion of noisy labels and noisy correspondence. To address this challenge, we use the audio-visual action recognition task as a proxy and propose a noise-tolerant learning framework to find anti-interference model parameters against both noisy labels and noisy correspondence. Specifically, our method consists of two phases that aim to rectify noise by the inherent correlation between modalities. First, a noise-tolerant contrastive training phase is performed to make the model immune to the possible noisy-labeled data. Despite the benefits brought by contrastive training, it would overfit the noisy correspondence and thus provide false supervision. To alleviate the influence of noisy correspondence, we propose a cross-modal noise estimation component to adjust the consistency between different modalities. As the noisy correspondence existed at the instance level, we further propose a category-level contrastive loss to reduce its interference. Second, in the hybrid-supervised training phase, we calculate the distance metric among features to obtain corrected labels, which are used as complementary supervision to guide the training. Furthermore, due to the lack of suitable datasets, we establish a benchmark of real-world noisy correspondence in audio-visual data by relabeling the Kinetics dataset. Extensive experiments on a wide range of noisy levels demonstrate that our method significant

关键词： Modal analysis

RCDNet: An Interpretable Rain Convolutional Dictionary network for Single Image Deraining

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Hong Xie, Qi Zhao, Qian Li, Yuexiang Liang, Yong Zheng, Yefeng Meng, Deyu Tencent Jarvis Lab Shenzhen China School of Mathematics and Statistics Ministry of Education Key Lab of Intelligent Networks and Network Security Xi'an Jiaotong University Shaanxi China Peng Cheng Laboratory Shenzhen China Macao Institute of Systems Engineering Macau University of Science and Technology Taipa China The Faculty of Information Technology Macau University of Science and Technology China

As a common weather, rain streaks adversely degrade the image quality and tend to negatively affect the performance of outdoor computer vision systems. Hence, removing rains from an image has become an important issue in the field. To handle such an ill-posed single image deraining task, in this paper, we specifically build a novel deep architecture, called rain convolutional dictionary network (RCDNet), which embeds the intrinsic priors of rain streaks and has clear interpretability. In specific, we first establish a RCD model for representing rain streaks and utilize the proximal gradient descent technique to design an iterative algorithm only containing simple operators for solving the model. By unfolding it, we then build the RCDNet in which every network module has clear physical meanings and corresponds to each operation involved in the algorithm. This good interpretability greatly facilitates an easy visualization and analysis on what happens inside the network and why it works well in inference process. Moreover, taking into account the domain gap issue in real scenarios, we further design a novel dynamic RCDNet, where the rain kernels can be dynamically inferred corresponding to input rainy images and then help shrink the space for rain layer estimation with few rain maps so as to ensure a fine generalization performance in the inconsistent scenarios of rain types between training and testing data. By end-to-end training such an interpretable network, all involved rain kernels and proximal operators can be automatically extracted, faithfully characterizing the features of both rain and clean background layers, and thus naturally leading to better deraining performance. Comprehensive experiments implemented on a series of representative synthetic and real datasets substantiate the superiority of our method, especially on its well generality to diverse testing scenarios and good interpretability for all its modules, as compared with state-of-the-art single im

关键词： Rain

Instructing Text-to-Image Diffusion Models via Classifier-Guided Semantic Optimization

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Chang, Yuanyuan Yao, Yinghua Qin, Tao Wang, Mengmeng Tsang, Ivor Dai, Guang MOE Key Laboratory for Intelligent Networks and Network Security Xi’an Jiaotong University China Center for Frontier AI Research Agency for Science Technology and Research Singapore Institute of High Performance Computing Agency for Science Technology and Research Singapore Zhejiang University of Technology China SGIT AI Lab State Grid Corporation of China China

Text-to-image diffusion models have emerged as powerful tools for high-quality image generation and editing. Many existing approaches rely on text prompts as editing guidance. However, these methods are constrained by the need for manual prompt crafting, which can be time-consuming, introduce irrelevant details, and significantly limit editing performance. In this work, we propose optimizing semantic embeddings guided by attribute classifiers to steer text-to-image models toward desired edits, without relying on text prompts or requiring any training or fine-tuning of the diffusion model. We utilize classifiers to learn precise semantic embeddings at the dataset level. The learned embeddings are theoretically justified as the optimal representation of attribute semantics, enabling disentangled and accurate edits. Experiments further demonstrate that our method achieves high levels of disentanglement and strong generalization across different domains of data. Code is available at https://***/Chang-yuanyuan/CASO. Copyright © 2025, The Authors. All rights reserved.

关键词：