Font generation is a difficult and time-consuming task, especially in those languages using ideograms that have complicated structures with a large number of characters, such as Chinese. To solve this problem, few-shot font generation and even one-shot font generation have attracted a lot of attention. However, most existing font generation methods may still suffer from (i) large cross-font gap challenge; (ii) subtle cross-font variation problem; and (iii) incorrect generation of complicated characters. In this paper, we propose a novel one-shot font generation method based on a diffusion model, named Diff-Font, which can be stably trained on large datasets. The proposed model aims to generate the entire font library by giving only one sample as the reference. Specifically, a large stroke-wise dataset is constructed, and a stroke-wise diffusion model is proposed to preserve the structure and the completion of each generated character. To our best knowledge, the proposed Diff-Font is the first work that developed diffusion models to handle the font generation task. The well-trained Diff-Font is not only robust to font gap and font variation, but also achieved promising performance on difficult character generation. Compared to previous font generation methods, our model reaches state-of-the-art performance both qualitatively and quantitatively.
translated by 谷歌翻译
This technical report briefly describes our JDExplore d-team's Vega v2 submission on the SuperGLUE leaderboard. SuperGLUE is more challenging than the widely used general language understanding evaluation (GLUE) benchmark, containing eight difficult language understanding tasks, including question answering, natural language inference, word sense disambiguation, coreference resolution, and reasoning. [Method] Instead of arbitrarily increasing the size of a pretrained language model (PLM), our aim is to 1) fully extract knowledge from the input pretraining data given a certain parameter budget, e.g., 6B, and 2) effectively transfer this knowledge to downstream tasks. To achieve goal 1), we propose self-evolution learning for PLMs to wisely predict the informative tokens that should be masked, and supervise the masked language modeling (MLM) process with rectified smooth labels. For goal 2), we leverage the prompt transfer technique to improve the low-resource tasks by transferring the knowledge from the foundation model and related downstream tasks to the target task. [Results] According to our submission record (Oct. 2022), with our optimized pretraining and fine-tuning strategies, our 6B Vega method achieved new state-of-the-art performance on 4/8 tasks, sitting atop the SuperGLUE leaderboard on Oct. 8, 2022, with an average score of 91.3.
translated by 谷歌翻译
迅速调整,它冻结了预审计的语言模型(PLM),只有微调的几个额外软提示的参数,在PLM具有数十亿个参数时,对全参数微调(即模型调整)显示出具有竞争性的性能,但仍然显示出竞争力。在较小的PLM的情况下,性能差。因此,迅速转移(POT),通过训练有素的类似源任务的提示来初始化目标提示,最近提议改善及时调整。但是,这样的香草锅方法通常会实现次优的性能,因为(i)锅对源目标对的相似性和(ii)直接对目标提示进行初始提示的提示敏感,而目标任务可能会导致灾难性忘记来源知识。为了解决这些问题,我们提出了一个新的指标,以准确预测及时的转移性(关于(i)),以及一种利用知识蒸馏技术将“知识”从源提示转移到的新颖的锅方法(即熊猫)目标以微妙的方式提示,并有效缓解灾难性遗忘(关于(ii))。此外,为了实现每个源目标对的自适应及时转移,我们使用指标来控制熊猫方法中的知识转移。对PLM的5个量表的21个源和9个目标数据集的189组组合进行了广泛而系统的实验,表明:1)我们提出的指标很好地预测了及时的可传递性; 2)在所有任务和型号中,我们的熊猫始终优于香草锅的平均得分2.3%(最高24.1%); 3)通过我们的熊猫方法,及时调整可以比在各种PLM量表场景中的模型调整来实现竞争性甚至更好的性能。接受代码和模型将在接受后发布。
translated by 谷歌翻译
最近,基于变压器的方法可预测多边形点或偏斜的曲线控制点可以定位文本,在场景文本检测中非常受欢迎。但是,使用的点标签形式意味着人类的阅读顺序,这会影响变压器模型的鲁棒性。至于模型体系结构,以前的方法尚未完全探索解码器中使用的查询的公式。在本文中,我们提出了一个简洁的动态点场景文本检测,称为dptext-detr,它直接将点坐标用作查询,并在解码器层之间动态更新它们。我们指出了一种简单而有效的位置标签形式,以应对原始效果。此外,增强的分解自我发项模块旨在显式地模拟多边形点序列的圆形形状,而不是非本地关注。广泛的实验证明了各种任意形状场景文本基准的训练效率,鲁棒性和最先进的性能。除了探测器之外,我们观察到现有的端到端观察者难以识别类似逆的文本。为了客观地评估他们的绩效并促进未来的研究,我们提出了一个逆文本测试集,其中包含500个手动标记图像。代码和反文本测试集将在https://github.com/ymy-k/dptext-detr上找到。
translated by 谷歌翻译
Sequence-to-sequence (seq2seq) learning is a popular fashion for large-scale pretraining language models. However, the prior seq2seq pretraining models generally focus on reconstructive objectives on the decoder side and neglect the effect of encoder-side supervision, which we argue may lead to sub-optimal performance. To verify our hypothesis, we first empirically study the functionalities of the encoder and decoder in seq2seq pretrained language models, and find that the encoder takes an important but under-exploitation role than the decoder regarding the downstream performance and neuron activation. Therefore, we propose an encoding-enhanced seq2seq pretraining strategy, namely E2S2, which improves the seq2seq models via integrating more efficient self-supervised information into the encoders. Specifically, E2S2 adopts two self-supervised objectives on the encoder side from two aspects: 1) locally denoising the corrupted sentence (denoising objective); and 2) globally learning better sentence representations (contrastive objective). With the help of both objectives, the encoder can effectively distinguish the noise tokens and capture high-level (i.e. syntactic and semantic) knowledge, thus strengthening the ability of seq2seq model to accurately achieve the conditional generation. On a large diversity of downstream natural language understanding and generation tasks, E2S2 dominantly improves the performance of its powerful backbone models, e.g. BART and T5. For example, upon BART backbone, we achieve +1.1% averaged gain on the general language understanding evaluation (GLUE) benchmark and +1.75% F_0.5 score improvement on CoNLL2014 dataset. We also provide in-depth analyses to show the improvement stems from better linguistic representation. We hope that our work will foster future self-supervision research on seq2seq language model pretraining.
translated by 谷歌翻译
现有的基于深度学习的变更检测方法试图精心设计具有功能强大特征表示的复杂神经网络,但忽略了随时间变化的土地覆盖变化引起的通用域转移,包括亮度波动和事件前和事后图像之间的季节变化,从而产生亚最佳结果。在本文中,我们提出了一个端到端监督域的适应框架,用于跨域变更检测,即SDACD,以有效地减轻双期颞图像之间的域移位,以更好地变更预测。具体而言,我们的SDACD通过有监督的学习从图像和特征角度介绍了合作改编。图像适应性利用了具有循环矛盾的限制来利用生成的对抗学习,以执行跨域样式转换,从而有效地以两边的方式缩小了域间隙。为了特征适应性,我们提取域不变特征以对齐特征空间中的不同特征分布,这可以进一步减少跨域图像的域间隙。为了进一步提高性能,我们结合了三种类型的双颞图像,以进行最终变化预测,包括初始输入双期图像和两个来自事件前和事后域的生成的双颞图像。对两个基准的广泛实验和分析证明了我们提出的框架的有效性和普遍性。值得注意的是,我们的框架将几个代表性的基线模型推向了新的最先进的记录,分别在CDD和WHU建筑数据集上分别达到97.34%和92.36%。源代码和模型可在https://github.com/perfect-you/sdacd上公开获得。
translated by 谷歌翻译
基于宽高的情绪分析(ABSA)是一种细粒度的情绪分析任务。为了更好地理解长期复杂的句子,并获得准确的方面的信息,这项任务通常需要语言和致辞知识。然而,大多数方法采用复杂和低效的方法来结合外部知识,例如,直接搜索图形节点。此外,尚未彻底研究外部知识和语言信息之间的互补性。为此,我们提出了一个知识图形增强网络(kgan),该网络(kgan)旨在有效地将外部知识与明确的句法和上下文信息纳入。特别是,kgan从多个不同的角度来看,即基于上下文,语法和知识的情绪表示。首先,kgan通过并行地了解上下文和句法表示,以完全提取语义功能。然后,KGAN将知识图形集成到嵌入空间中,基于该嵌入空间,基于该嵌入空间,通过注意机制进一步获得了方面特异性知识表示。最后,我们提出了一个分层融合模块,以便以本地到全局方式补充这些多视图表示。关于三个流行的ABSA基准测试的广泛实验证明了我们康复的效果和坚固性。值得注意的是,在罗伯塔的预用模型的帮助下,Kggan实现了最先进的性能的新记录。
translated by 谷歌翻译
现有场景文本识别(str)方法通常使用语言模型来优化通过视觉识别(VR)模型预测的1D字符序列的联合概率,该模型忽略了字符实例内和之间的视觉语义的2D空间上下文不概括为任意形状的场景文本。要解决此问题,我们首次尝试根据本文的视觉语义进行文本推理。从技术上讲,给定VR模型预测的字符分割映射,我们为每个实例构造一个子图,其中节点表示基于它们的空间相似度之间的节点中的像素和边缘。然后,这些子图通过其根节点顺序连接并合并到完整的图表中。基于此图,我们通过通过跨熵损失监督它来设计图表卷积网络以进行文本推理(GTR)。 GTR可以轻松插入代表性的STR模型,以提高其性能,因为较好的文本推理。具体而言,我们通过将GTR并将GTR与基于分段的STR基线中的语言模型并联的语言模型进行了构建模型,即,通过相互学习可以有效利用视觉语言互补性。 S-GTR在六个挑战性的STR基准上套装新的最先进的基准,并概括为多语言数据集。代码可用于https://github.com/adeline-cs/gtr。
translated by 谷歌翻译
集群歧视是无监督的代表学习的有效借口任务,这通常由两个阶段组成:聚类和歧视。群集是为每个实例分配伪标签,该标签将用于学习歧视中的表示。主要挑战驻留在群集中,因为普遍的聚类方法(例如,k-means)必须以批处理模式运行,并且可以有一个琐碎的解决方案由主导集群组成。为解决这些挑战,我们首先调查基于聚类的代表学习的目标。基于此,我们提出了一种新的基于聚类的借口任务,具有在线受限的K-means(可乐)。与每个群集具有完全相同的大小的平衡集群相比,我们只限制每个群集的最小大小,以灵活地捕获固有的数据结构。更重要的是,我们的在线分配方法具有接近全球最佳的理论保证。通过解耦聚类和歧视,可焦炭可以在每个实例中仅优化单个视图时实现竞争性能。关于Imagenet的广泛实验验证了我们提案的效力和效率。代码将被释放。
translated by 谷歌翻译
In this paper, we propose a robust 3D detector, named Cross Modal Transformer (CMT), for end-to-end 3D multi-modal detection. Without explicit view transformation, CMT takes the image and point clouds tokens as inputs and directly outputs accurate 3D bounding boxes. The spatial alignment of multi-modal tokens is performed implicitly, by encoding the 3D points into multi-modal features. The core design of CMT is quite simple while its performance is impressive. CMT obtains 73.0% NDS on nuScenes benchmark. Moreover, CMT has a strong robustness even if the LiDAR is missing. Code will be released at https://github.com/junjie18/CMT.
translated by 谷歌翻译