Vision Transformers (ViTs) have achieved overwhelming success, yet they suffer from vulnerable resolution scalability, i.e., the performance drops drastically when presented with input resolutions that are unseen during training. We introduce, ResFormer, a framework that is built upon the seminal idea of multi-resolution training for improved performance on a wide spectrum of, mostly unseen, testing resolutions. In particular, ResFormer operates on replicated images of different resolutions and enforces a scale consistency loss to engage interactive information across different scales. More importantly, to alternate among varying resolutions, we propose a global-local positional embedding strategy that changes smoothly conditioned on input sizes. This allows ResFormer to cope with novel resolutions effectively. We conduct extensive experiments for image classification on ImageNet. The results provide strong quantitative evidence that ResFormer has promising scaling abilities towards a wide range resolutions. For instance, ResFormer-B-MR achieves a Top-1 accuracy of 75.86% and 81.72% when evaluated on relatively low and high resolutions respectively (i.e., 96 and 640), which are 48% and 7.49% better than DeiT-B. We also demonstrate, among other things, ResFormer is flexible and can be easily extended to semantic segmentation and video action recognition.
translated by 谷歌翻译
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total). We find that BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning. To facilitate future research and applications using LLMs, we publicly release our models and code under the Responsible AI License.
translated by 谷歌翻译
Recent cross-lingual cross-modal works attempt to extend Vision-Language Pre-training (VLP) models to non-English inputs and achieve impressive performance. However, these models focus only on understanding tasks utilizing encoder-only architecture. In this paper, we propose ERNIE-UniX2, a unified cross-lingual cross-modal pre-training framework for both generation and understanding tasks. ERNIE-UniX2 integrates multiple pre-training paradigms (e.g., contrastive learning and language modeling) based on encoder-decoder architecture and attempts to learn a better joint representation across languages and modalities. Furthermore, ERNIE-UniX2 can be seamlessly fine-tuned for varieties of generation and understanding downstream tasks. Pre-trained on both multilingual text-only and image-text datasets, ERNIE-UniX2 achieves SOTA results on various cross-lingual cross-modal generation and understanding tasks such as multimodal machine translation and multilingual visual question answering.
translated by 谷歌翻译
Speech representation learning has improved both speech understanding and speech synthesis tasks for single language. However, its ability in cross-lingual scenarios has not been explored. In this paper, we extend the pretraining method for cross-lingual multi-speaker speech synthesis tasks, including cross-lingual multi-speaker voice cloning and cross-lingual multi-speaker speech editing. We propose a speech-text joint pretraining framework, where we randomly mask the spectrogram and the phonemes given a speech example and its transcription. By learning to reconstruct the masked parts of the input in different languages, our model shows great improvements over speaker-embedding-based multi-speaker TTS methods. Moreover, our framework is end-to-end for both the training and the inference without any finetuning effort. In cross-lingual multi-speaker voice cloning and cross-lingual multi-speaker speech editing tasks, our experiments show that our model outperforms speaker-embedding-based multi-speaker TTS methods. The code and model are publicly available at PaddleSpeech.
translated by 谷歌翻译
CNN-based surrogates have become prevalent in scientific applications to replace conventional time-consuming physical approaches. Although these surrogates can yield satisfactory results with significantly lower computation costs over small training datasets, our benchmarking results show that data-loading overhead becomes the major performance bottleneck when training surrogates with large datasets. In practice, surrogates are usually trained with high-resolution scientific data, which can easily reach the terabyte scale. Several state-of-the-art data loaders are proposed to improve the loading throughput in general CNN training; however, they are sub-optimal when applied to the surrogate training. In this work, we propose SOLAR, a surrogate data loader, that can ultimately increase loading throughput during the training. It leverages our three key observations during the benchmarking and contains three novel designs. Specifically, SOLAR first generates a pre-determined shuffled index list and accordingly optimizes the global access order and the buffer eviction scheme to maximize the data reuse and the buffer hit rate. It then proposes a tradeoff between lightweight computational imbalance and heavyweight loading workload imbalance to speed up the overall training. It finally optimizes its data access pattern with HDF5 to achieve a better parallel I/O throughput. Our evaluation with three scientific surrogates and 32 GPUs illustrates that SOLAR can achieve up to 24.4X speedup over PyTorch Data Loader and 3.52X speedup over state-of-the-art data loaders.
translated by 谷歌翻译
最先进的(SOTA)深度学习乳房X线照片分类器接受了弱标记的图像训练,通常依赖于产生有限解释性预测的全球模型,这是他们成功地转化为临床实践的关键障碍。另一方面,基于原型的模型通过将预测与训练图像原型相关联,改善了可解释性,但是它们的准确性不如全球模型,其原型往往具有差的多样性。我们通过BraixProtopnet ++的建议解决了这两个问题,该问题通过将基于原型的模型结合起来,为全局模型增添了解释性。 BraixProtopnet ++在训练基于原型的模型以提高合奏的分类精度时,会提炼全局模型的知识。此外,我们提出了一种方法来通过保证所有原型都与不同的训练图像相关联,以增加原型多样性。对弱标记的私人和公共数据集进行的实验表明,BraixProtopnet ++的分类精度比基于SOTA Global和基于原型的模型具有更高的分类精度。使用病变定位来评估模型可解释性,我们显示BraixProtopnet ++比其他基于原型的模型和全球模型的事后解释更有效。最后,我们表明,BraixProtopnet ++学到的原型的多样性优于基于SOTA原型的方法。
translated by 谷歌翻译
在本文中,我们提出了广义参数对比度学习(GPACO/PACO),该学习在不平衡和平衡数据上都很好地工作。基于理论分析,我们观察到,受监督的对比损失倾向于偏向高频类别,从而增加了学习不平衡的学习难度。我们从优化的角度介绍了一组参数班的可学习中心,以重新平衡。此外,我们在平衡的环境下分析了GPACO/PACO损失。我们的分析表明,GPACO/PACO可以适应地增强同一等级样品的强度,因为将更多的样品与相应的中心一起拉在一起并有益于艰难的示例学习。长尾基准测试的实验表明了长尾识别的新最先进。在完整的Imagenet上,与MAE模型相比,从CNN到接受GPACO损失训练的视觉变压器的模型显示出更好的泛化性能和更强的鲁棒性。此外,GPACO可以应用于语义分割任务,并在4个最受欢迎的基准测试中观察到明显的改进。我们的代码可在https://github.com/dvlab-research/parametric-contrastive-learning上找到。
translated by 谷歌翻译
在分析筛查乳房X线照片时,放射科医生可以自然处理每个乳房的两个同侧视图,即颅底审计(CC)和中外侧 - 粘合剂(MLO)视图。这些多个相关图像提供了互补的诊断信息,并可以提高放射科医生的分类准确性。不幸的是,大多数现有的深度学习系统,受过全球标记的图像培训,缺乏从这些多种观点中共同分析和整合全球和本地信息的能力。通过忽略筛选发作的多个图像中存在的潜在有价值的信息,人们限制了这些系统的潜在准确性。在这里,我们提出了一种新的多视图全球分析方法,该方法基于全球一致性学习和对乳房X线照片中同侧观点的局部同时学习,模仿放射科医生的阅读程序。广泛的实验表明,在大规模的私人数据集和两个公开可用的数据集上,我们的模型在分类准确性和概括方面优于竞争方法,在该数据集和两个公开可用的数据集上,模型仅受到全球标签的培训和测试。
translated by 谷歌翻译
在卷积神经网络(CNN)的动力下,医学图像分类迅速发展。由于卷积内核的接受场的固定尺寸,很难捕获医学图像的全局特征。尽管基于自发的变压器可以对远程依赖性进行建模,但它具有很高的计算复杂性,并且缺乏局部电感偏见。许多研究表明,全球和本地特征对于图像分类至关重要。但是,医学图像具有许多嘈杂,分散的特征,类内的变化和类间的相似性。本文提出了三个分支分层的多尺度特征融合网络结构,称为医学图像分类为新方法。它可以融合多尺度层次结构的变压器和CNN的优势,而不会破坏各自的建模,从而提高各种医学图像的分类精度。局部和全局特征块的平行层次结构旨在有效地提取各种语义尺度的本地特征和全局表示,并灵活地在不同的尺度上建模,并与图像大小相关的线性计算复杂性。此外,自适应分层特征融合块(HFF块)旨在全面利用在不同层次级别获得的功能。 HFF块包含空间注意力,通道注意力,残留的倒置MLP和快捷方式,以在每个分支的各个规模特征之间适应融合语义信息。我们在ISIC2018数据集上提出的模型的准确性比基线高7.6%,COVID-19数据集的准确性为21.5%,Kvasir数据集的准确性为10.4%。与其他高级模型相比,HIFUSE模型表现最好。我们的代码是开源的,可从https://github.com/huoxiangzuo/hifuse获得。
translated by 谷歌翻译
需要高质量的面部图像来保证在监视和安全场景中自动识别系统(FR)系统的稳定性和可靠性。但是,由于传输或存储的限制,在分析之前,通常会压缩大量的面部数据。压缩图像可能会失去强大的身份信息,从而导致FR系统的性能降低。在此,我们首次尝试研究FR系统的明显差异(JND),可以将其定义为FR系统无法注意到的最大失真。更具体地说,我们建立了一个JND数据集,其中包括3530个原始图像和137,670个由高级参考编码/解码软件生成的压缩图像,该图像基于多功能视频编码(VVC)标准(VTM-15.0)。随后,我们开发了一种新型的JND预测模型,以直接推断FR系统的JND图像。特别是,为了最大程度地删除冗余性,在不损害鲁棒身份信息的情况下,我们将编码器应用于多个功能提取和基于注意力的特征分解模块,以将面部特征逐渐分解为两个不相关的组件,即身份和残差特征,通过自我 - 监督学习。然后,剩余特征被馈入解码器以生成残差图。最后,通过从原始图像中减去残差图来获得预测的JND映射。实验结果表明,与最先进的JND模型相比,所提出的模型可以实现JND MAP预测的更高准确性,并且能够在维持FR系统的性能的同时保存更多的位置,而与VTM-15.0相比。
translated by 谷歌翻译