检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Herold, Christian Ney, Hermann Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University AachenD-52056 Germany

Compared to sentence-level systems, document-level neural machine translation (NMT) models produce a more consistent output across a document and are able to better resolve ambiguities within the input. There are many works on document-level NMT, mostly focusing on modifying the model architecture or training strategy to better accommodate the additional context-input. On the other hand, in most works, the question on how to perform search with the trained model is scarcely discussed, sometimes not mentioned at all. In this work, we aim to answer the question how to best utilize a context-aware translation model in decoding. We start with the most popular document-level NMT approach and compare different decoding schemes, some from the literature and others proposed by us. In the comparison, we are using both, standard automatic metrics, as well as specific linguistic phenomena on three standard document-level translation benchmarks. We find that most commonly used decoding strategies perform similar to each other and that higher quality context information has the potential to further improve the translation. Copyright © 2023, The Authors. All rights reserved.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Reference Algorithms for the Mitosis Domain Generalization (MIDOG) 2022 Challenge 25th

Reference Algorithms for the Mitosis Domain Generalization...

引用

25th International Conference on Medical Image Computing and computer-Assisted Intervention , MICCAI 2022

作者： Ammeling, Jonas Wilm, Frauke Ganz, Jonathan Breininger, Katharina Aubreville, Marc Technische Hochschule Ingolstadt Ingolstadt Germany Pattern Recognition Lab Computer Sciences Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany Department Artificial Intelligence in Biomedical Engineering Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany

ISBN: (纸本)9783031336577

Robust mitosis detection on images from different tumor types, pathology labs, and species is a challenging task that was addressed in the MICCAI Mitosis Domain Generalization (MIDOG) 2022 challenge. In this work, we describe three reference algorithms that were provided as a baseline for the challenge: A Mask-RCNN-based instance segmentation model trained on the MIDOG 2022 dataset, and two different versions of the domain-adversarial RetinaNet which already served as the baseline for MIDOG 2021 challenge, one trained on the MIDOG 2022 dataset and the other trained only on human breast carcinoma from MIDOG 2021. The domain-adversarial RetinaNet trained on the MIDOG 2022 dataset had the highest F 1 score of 0.7135 on the final test set. When trained on breast carcinoma only, the same network had a much lower F 1 score of 0.4719, indicating a significant domain shift between mitotic figure and tissue representation in different tumor types. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Improving Long Context Document-Level Machine Translation

arXiv

引用

arXiv 2023年

作者： Herold, Christian Ney, Hermann Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University AachenD-52056 Germany

Document-level context for neural machine translation (NMT) is crucial to improve the translation consistency and cohesion, the translation of ambiguous inputs, as well as several other linguistic phenomena. Many works have been published on the topic of document-level NMT, but most restrict the system to only local context, typically including just the one or two preceding sentences as additional information. This might be enough to resolve some ambiguous inputs, but it is probably not sufficient to capture some document-level information like the topic or style of a conversation. When increasing the context size beyond just the local context, there are two challenges: (i) the memory usage increases exponentially (ii) the translation performance starts to degrade. We argue that the widely-used attention mechanism is responsible for both issues. Therefore, we propose a constrained attention variant that focuses the attention on the most relevant parts of the sequence, while simultaneously reducing the memory consumption. For evaluation, we utilize targeted test sets in combination with novel evaluation techniques to analyze the translations in regards to specific discourse-related phenomena. We find that our approach is a good compromise between sentence-level NMT vs attending to the full context, especially in low resource scenarios. Copyright © 2023, The Authors. All rights reserved.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

NORPPA: NOvel Ringed Seal Re-Identification by Pelage pattern Aggregation

NORPPA: NOvel Ringed Seal Re-Identification by Pelage Patter...

引用

IEEE Winter Applications and computer Vision Workshops (WACVW)

作者： Ekaterina Nepovinnykh Tuomas Eerola Heikki Kälviäinen Ilia Chelak Department of Computational Engineering School of Engineering Sciences Computer Vision and Pattern Recognition Laboratory (CVPRL) Lappeenranta-Lahti University of Technology LUT Lappeenranta Finland Department of Computer Science Faculty of Science University of Helsinki Helsinki Finland

We propose a method for Saimaa ringed seal (Pusa hispida saimensis) re-identification. Access to large image volumes through camera trapping and crowdsourcing provides novel possibilities for animal conservation and monitoring and calls for automatic methods for analysis, in particular, when re-identifying individual animals from the images. The proposed method NOvel Ringed seal re-identification by Pelage pattern Aggregation (NORPPA) utilizes the permanent and unique pelage pattern of Saimaa ringed seals and content-based image retrieval techniques. First, the query image is preprocessed, and each seal instance is segmented. Next, the seal's pelage pattern is extracted using a U-net encoder-decoder based method. Then, CNN-based affine invariant features are embedded and aggregated into Fisher Vectors. Finally, the cosine distance between the Fisher Vectors is used to find the best match from a database of known individuals. We perform extensive experiments of various modifications of the method on challenging Saimaa ringed seals re-identification dataset. The proposed method is shown to produce the best re-identification accuracy on our dataset in comparisons with alternative approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

OrdinalNet: A Deep Learning-based Relative Image Quality Metric for Motion Compensation in CBCT

OrdinalNet: A Deep Learning-based Relative Image Quality Met...

引用

IEEE Symposium on Nuclear science (NSS/MIC)

作者： M. Meier M. Manhart A. Preuhs F. Goldmann M. Kowarschik A. Maier Computer Science 5 / Pattern Recognition Lab Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Bavaria Germany Siemens Healthineers AG Forchheim Bavaria Germany

ISBN: (数字)9798350388152

ISBN: (纸本)9798350388169

Interventional C-arm cone beam CT significantly reduces time-to-therapy for patients suffering from acute stroke. Extended acquisition times as compared to modern helical CT systems make rigid patient motion more likely, introducing a mismatch with the geometry alignment presupposed during reconstruction, leading to typical blurring or streaking artifacts. Different autofocus methods exist which aim to find a compensation trajectory and reestablish a motion-free reconstruction by optimizing a quality metric on the reconstructed images. However, depending on the type of implemented metric, these methods show diminished performance for larger motion amplitudes, often converging into local minima. To overcome these drawbacks, we present OrdinalNet, a deep learning model predicting a pseudo-binary score to assess motion artifact deterioration or improvement between two reconstructions resulting from slightly different motion trajectories. Our method eliminates the necessity for absolute artifact quantification in each image, along with establishing a relative ordering among data points which is sufficient for effective simplex-based optimization. The model is trained and evaluated on simulated motion applied to motion-free clinical acquisitions. When presented 1000 motion-affected pairs from previously unseen patients, it shows superior performance on a threshold-dependent binary classification task when compared to an entropy-based metric, resulting in areas under the curve of $\mathrm{AUC}_{\text {ONet }}=0.9295$ and $\mathrm{AUC}_{\mathrm{Ent}}=0.6366$

关键词： Measurement Semiconductor detectors Computed tomography Stroke (medical condition) Predictive models Motion compensation Trajectory

来源：评论

学校读者我要写书评

暂无评论

GENERATION OF ANONYMOUS CHEST RADIOGRAPHS USING LATENT DIFFUSION MODELS FOR TRAINING THORACIC ABNORMALITY CLASSIFICATION SYSTEMS

arXiv

引用

arXiv 2022年

作者： Packhäuser, Kai Folle, Lukas Thamm, Florian Maier, Andreas Pattern Recognition Lab Department of Computer Science Friedrich-Alexander-Universität Erlangen-Nürnberg Germany

The availability of large-scale chest X-ray datasets is a requirement for developing well-performing deep learning-based algorithms in thoracic abnormality detection and classification. However, biometric identifiers in chest radiographs hinder the public sharing of such data for research purposes due to the risk of patient re-identification. To counteract this issue, synthetic data generation offers a solution for anonymizing medical images. This work employs a latent diffusion model to synthesize an anonymous chest X-ray dataset of high-quality class-conditional images. We propose a privacy-enhancing sampling strategy to ensure the non-transference of biometric information during the image generation process. The quality of the generated images and the feasibility of serving as exclusive training data are evaluated on a thoracic abnormality classification task. Compared to a real classifier, we achieve competitive results with a performance gap of only 3.5% in the area under the receiver operating characteristic curve. © 2022, CC BY.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

FAST AND INTERPRETABLE 2D HOMOGRAPHY DECOMPOSITION: SIMILARITY-KERNEL-SIMILARITY AND AFFINE-CORE-AFFINE TRANSFORMATIONS

arXiv

引用

arXiv 2024年

作者： Cai, Shen Wu, Zhanhao Guo, Lingxi Wang, Jiachun Zhang, Siyu Yan, Junchi Shen, Shuhan Visual and Geometric Perception Lab Donghua University China Department of Computer Science and Engineering Shanghai Jiao Tong University China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China

In this paper, we present two fast and interpretable decomposition methods for 2D homography, which are named Similarity-Kernel-Similarity (SKS) and Affine-Core-Affine (ACA) transformations respectively. Under the minimal 4-point configuration, the first and the last similarity transformations in SKS are computed by two anchor points on target and source planes, respectively. Then, the other two point correspondences can be exploited to compute the middle kernel transformation with only four parameters. Furthermore, ACA uses three anchor points to compute the first and the last affine transformations, followed by computation of the middle core transformation utilizing the other one point correspondence. ACA can compute a homography up to a scale with only 85 floating-point operations (FLOPs), without even any division operations. Therefore, as a plug-in module, ACA facilitates the traditional feature-based Random Sample Consensus (RANSAC) pipeline, as well as deep homography pipelines estimating 4-point offsets. In addition to the advantages of geometric parameterization and computational efficiency, SKS and ACA can express each element of homography by a polynomial of input coordinates (7th degree to 9th degree), extend the existing essential Similarity-Affine-Projective (SAP) decomposition and calculate 2D affine transformations in a unified way. Source codes are released in https://***/cscvlab/SKS-Homography. Copyright © 2024, The Authors. All rights reserved.

关键词： Linear systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing and Adversarial: Improve ASR with Speaker labels

Enhancing and Adversarial: Improve ASR with Speaker Labels

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Wei Zhou Haotian Wu Jingjing Xu Mohammad Zeineldeen Christoph Lüscher Ralf Schlüter Hermann Ney Computer Science Department Human Language Technology and Pattern Recognition RWTH Aachen University Aachen Germany AppTek GmbH Aachen Germany

ASR can be improved by multi-task learning (MTL) with domain enhancing or domain adversarial training, which are two opposite objectives with the aim to increase/decrease domain variance towards domain-aware/agnostic ASR, respectively. In this work, we study how to best apply these two opposite objectives with speaker labels to improve conformer-based ASR. We also propose a novel adaptive gradient reversal layer for stable and effective adversarial training without tuning effort. Detailed analysis and experimental verification are conducted to show the optimal positions in the ASR neural network (NN) to apply speaker enhancing and adversarial training. We also explore their combination for further improvement, achieving the same performance as i-vectors plus adversarial training. Our best speaker-based MTL achieves 7% relative improvement on the Switchboard Hub5’00 set. We also investigate the effect of such speaker-based MTL w.r.t. cleaner dataset and weaker ASR NN.

关键词： Training Artificial neural networks Switches Signal processing Multitasking Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

Robust Knowledge Distillation from RNN-T Models with Noisy Training labels Using Full-Sum Loss

Robust Knowledge Distillation from RNN-T Models with Noisy T...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Mohammad Zeineldeen Kartik Audhkhasi Murali Karthick Baskar Bhuvana Ramabhadran Computer Science Department Human Language Technology and Pattern Recognition RWTH Aachen University Aachen Germany Google LLC New York

This work studies knowledge distillation (KD) and addresses its constraints for recurrent neural network transducer (RNN-T) models. In hard distillation, a teacher model transcribes large amounts of unlabelled speech to train a student model. Soft distillation is another popular KD method that distills the output logits of the teacher model. Due to the nature of RNN-T alignments, applying soft distillation between RNNT architectures having different posterior distributions is challenging. In addition, bad teachers having high word-error-rate (WER) reduce the efficacy of KD. We investigate how to effectively distill knowledge from variable quality ASR teachers, which has not been studied before to the best of our knowledge. We show that a sequence-level KD, full-sum distillation, outperforms other distillation methods for RNN-T models, especially for bad teachers. We also propose a variant of full-sum distillation that distills the sequence discriminative knowledge of the teacher leading to further improvement in WER. We conduct experiments on public datasets namely SpeechStew and LibriSpeech, and on in-house production data.

关键词： Knowledge engineering Training Recurrent neural networks Transducers Production Signal processing Acoustics

来源：评论

学校读者我要写书评

暂无评论

Lattice-Free Sequence Discriminative Training for Phoneme-Based Neural Transducers

Lattice-Free Sequence Discriminative Training for Phoneme-Ba...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zijian Yang Wei Zhou Ralf Schlüter Hermann Ney Computer Science Department Human Language Technology and Pattern Recognition RWTH Aachen University Aachen Germany AppTek GmbH Aachen Germany

Recently, RNN-Transducers have achieved remarkable results on various automatic speech recognition tasks. However, lattice-free sequence discriminative training methods, which obtain superior performance in hybrid models, are rarely investigated in RNN-Transducers. In this work, we propose three lattice-free training objectives, namely lattice-free maximum mutual information, lattice-free segment-level minimum Bayes risk, and lattice-free minimum Bayes risk, which are used for the final posterior output of the phoneme-based neural transducer with a limited context dependency. Compared to criteria using N-best lists, lattice-free methods eliminate the decoding step for hypotheses generation during training, which leads to more efficient training. Experimental results show that lattice-free methods gain up to 6.5% relative improvement in word error rate compared to a sequence-level cross-entropy trained model. Compared to the N-best-list based minimum Bayes risk objectives, lattice-free methods gain 40% - 70% relative training time speedup with a small degradation in performance.

关键词： Training Degradation Transducers Error analysis Signal processing Decoding Speech processing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：