PyTorchKR Papers

최신 논문

총 9,642편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2105.10860공식 코드 · Papers with Code

FCCDN: Feature Constraint Network for VHR Image Change Detection

Change detection is the process of identifying pixelwise differences in bitemporal co-registered images. It is of great significance to Earth observations. Recently, with the emergence of deep learning (DL), the power and feasibility of deep convolutional neural network (CNN)-based methods have been shown in the field of change detection. However, there is still a lack of effective supervision for change feature learning. In this work, a feature constraint change detection network (FCCDN) is proposed. We constrain features both in bitemporal feature extraction and feature fusion. More specifically, we propose a dual encoder-decoder network backbone for the change detection task. At the center of the backbone, we design a nonlocal feature pyramid network to extract and fuse multiscale features. To fuse bitemporal features in a robust way, we build a dense connection-based feature fusion module. Moreover, a self-supervised learning-based strategy is proposed to constrain feature learning. Based on FCCDN, we achieve state-of-the-art performance on two building change detection datasets (LEVIR-CD and WHU). On the LEVIR-CD dataset, we achieve an IoU of 0.8569 and an F1 score of 0.9229. On the WHU dataset, we achieve an IoU of 0.8820 and an F1 score of 0.9373. Moreover, for the first time, the acquisition of accurate bitemporal semantic segmentation results is achieved without using semantic segmentation labels. This is vital for the application of change detection because it saves the cost of labeling.

arXiv:2105.10859공식 코드 · Papers with Code

Coarse to Fine Multi-Resolution Temporal Convolutional Network

Temporal convolutional networks (TCNs) are a commonly used architecture for temporal video segmentation. TCNs however, tend to suffer from over-segmentation errors and require additional refinement modules to ensure smoothness and temporal coherency. In this work, we propose a novel temporal encoder-decoder to tackle the problem of sequence fragmentation. In particular, the decoder follows a coarse-to-fine structure with an implicit ensemble of multiple temporal resolutions. The ensembling produces smoother segmentations that are more accurate and better-calibrated, bypassing the need for additional refinement modules. In addition, we enhance our training with a multi-resolution feature-augmentation strategy to promote robustness to varying temporal resolutions. Finally, to support our architecture and encourage further sequence coherency, we propose an action loss that penalizes misclassifications at the video level. Experiments show that our stand-alone architecture, together with our novel feature-augmentation strategy and new loss, outperforms the state-of-the-art on three temporal video segmentation benchmarks.

arXiv:2105.10465

Graph Convolutional Networks in Feature Space for Image Deblurring and Super-resolution

Graph convolutional networks (GCNs) have achieved great success in dealing with data of non-Euclidean structures. Their success directly attributes to fitting graph structures effectively to data such as in social media and knowledge databases. For image processing applications, the use of graph structures and GCNs have not been fully explored. In this paper, we propose a novel encoder-decoder network with added graph convolutions by converting feature maps to vertexes of a pre-generated graph to synthetically construct graph-structured data. By doing this, we inexplicitly apply graph Laplacian regularization to the feature maps, making them more structured. The experiments show that it significantly boosts performance for image restoration tasks, including deblurring and super-resolution. We believe it opens up opportunities for GCN-based approaches in more applications.

arXiv:2105.10430공식 코드 · Papers with Code

Multi-Horizon Forecasting for Limit Order Books: Novel Deep Learning Approaches and Hardware Acceleration using Intelligent Processing Units

We design multi-horizon forecasting models for limit order book (LOB) data by using deep learning techniques. Unlike standard structures where a single prediction is made, we adopt encoder-decoder models with sequence-to-sequence and Attention mechanisms to generate a forecasting path. Our methods achieve comparable performance to state-of-art algorithms at short prediction horizons. Importantly, they outperform when generating predictions over long horizons by leveraging the multi-horizon setup. Given that encoder-decoder models rely on recurrent neural layers, they generally suffer from slow training processes. To remedy this, we experiment with utilising novel hardware, so-called Intelligent Processing Units (IPUs) produced by Graphcore. IPUs are specifically designed for machine intelligence workload with the aim to speed up the computation process. We show that in our setup this leads to significantly faster training times when compared to training models with GPUs.

arXiv:2105.10203공식 코드 · Papers with Code

Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning

Hidden features in neural network usually fail to learn informative representation for 3D segmentation as supervisions are only given on output prediction, while this can be solved by omni-scale supervision on intermediate layers. In this paper, we bring the first omni-scale supervision method to point cloud segmentation via the proposed gradual Receptive Field Component Reasoning (RFCR), where target Receptive Field Component Codes (RFCCs) are designed to record categories within receptive fields for hidden units in the encoder. Then, target RFCCs will supervise the decoder to gradually infer the RFCCs in a coarse-to-fine categories reasoning manner, and finally obtain the semantic labels. Because many hidden features are inactive with tiny magnitude and make minor contributions to RFCC prediction, we propose a Feature Densification with a centrifugal potential to obtain more unambiguous features, and it is in effect equivalent to entropy regularization over features. More active features can further unleash the potential of our omni-supervision method. We embed our method into four prevailing backbones and test on three challenging benchmarks. Our method can significantly improve the backbones in all three datasets. Specifically, our method brings new state-of-the-art performances for S3DIS as well as Semantic3D and ranks the 1st in the ScanNet benchmark among all the point-based methods. Code will be publicly available at https://github.com/azuki-miho/RFCR.

arXiv:2105.10067

Towards Automatic Sizing for PPE with a Point Cloud Based Variational Autoencoder

Sizing and fitting of Personal Protective Equipment (PPE) is a critical part of the product creation process; however, traditional methods to do this type of work can be labor intensive and based on limited or non-representative anthropomorphic data. In the case of PPE, a poor fit can jeopardize an individual's health and safety. In this paper we present an unsupervised machine learning algorithm that can identify a representative set of exemplars, individuals that can be utilized by designers as idealized sizing models. The algorithm is based around a Variational Autoencoder (VAE) with a Point-Net inspired encoder and decoder architecture trained on Human point-cloud data obtained from the CEASAR dataset. The learned latent space is then clustered to identify a specified number of sizing groups. We demonstrate this technique on scans of human faces to provide designers of masks and facial coverings a reference set of individuals to test existing mask styles.

arXiv:2105.10095

Variational Gaussian Topic Model with Invertible Neural Projections

Neural topic models have triggered a surge of interest in extracting topics from text automatically since they avoid the sophisticated derivations in conventional topic models. However, scarce neural topic models incorporate the word relatedness information captured in word embedding into the modeling process. To address this issue, we propose a novel topic modeling approach, called Variational Gaussian Topic Model (VaGTM). Based on the variational auto-encoder, the proposed VaGTM models each topic with a multivariate Gaussian in decoder to incorporate word relatedness. Furthermore, to address the limitation that pre-trained word embeddings of topic-associated words do not follow a multivariate Gaussian, Variational Gaussian Topic Model with Invertible neural Projections (VaGTM-IP) is extended from VaGTM. Three benchmark text corpora are used in experiments to verify the effectiveness of VaGTM and VaGTM-IP. The experimental results show that VaGTM and VaGTM-IP outperform several competitive baselines and obtain more coherent topics.

arXiv:2105.09907

Joint Face Image Restoration and Frontalization for Recognition

In real-world scenarios, many factors may harm face recognition performance, e.g., large pose, bad illumination,low resolution, blur and noise. To address these challenges, previous efforts usually first restore the low-quality faces to high-quality ones and then perform face recognition. However, most of these methods are stage-wise, which is sub-optimal and deviates from the reality. In this paper, we address all these challenges jointly for unconstrained face recognition. We propose an Multi-Degradation Face Restoration (MDFR) model to restore frontalized high-quality faces from the given low-quality ones under arbitrary facial poses, with three distinct novelties. First, MDFR is a well-designed encoder-decoder architecture which extracts feature representation from an input face image with arbitrary low-quality factors and restores it to a high-quality counterpart. Second, MDFR introduces a pose residual learning strategy along with a 3D-based Pose Normalization Module (PNM), which can perceive the pose gap between the input initial pose and its real-frontal pose to guide the face frontalization. Finally, MDFR can generate frontalized high-quality face images by a single unified network, showing a strong capability of preserving face identity. Qualitative and quantitative experiments on both controlled and in-the-wild benchmarks demonstrate the superiority of MDFR over state-of-the-art methods on both face frontalization and face restoration.

arXiv:2105.09906

Empirical Analysis of Image Caption Generation using Deep Learning

Automated image captioning is one of the applications of Deep Learning which involves fusion of work done in computer vision and natural language processing, and it is typically performed using Encoder-Decoder architectures. In this project, we have implemented and experimented with various flavors of multi-modal image captioning networks where ResNet101, DenseNet121 and VGG19 based CNN Encoders and Attention based LSTM Decoders were explored. We have studied the effect of beam size and the use of pretrained word embeddings and compared them to baseline CNN encoder and RNN decoder architecture. The goal is to analyze the performance of each approach using various evaluation metrics including BLEU, CIDEr, ROUGE and METEOR. We have also explored model explainability using Visual Attention Maps (VAM) to highlight parts of the images which has maximum contribution for predicting each word of the generated caption.

arXiv:2105.09601

See, Hear, Read: Leveraging Multimodality with Guided Attention for Abstractive Text Summarization

In recent years, abstractive text summarization with multimodal inputs has started drawing attention due to its ability to accumulate information from different source modalities and generate a fluent textual summary. However, existing methods use short videos as the visual modality and short summary as the ground-truth, therefore, perform poorly on lengthy videos and long ground-truth summary. Additionally, there exists no benchmark dataset to generalize this task on videos of varying lengths. In this paper, we introduce AVIATE, the first large-scale dataset for abstractive text summarization with videos of diverse duration, compiled from presentations in well-known academic conferences like NDSS, ICML, NeurIPS, etc. We use the abstract of corresponding research papers as the reference summaries, which ensure adequate quality and uniformity of the ground-truth. We then propose FLORAL, a factorized multi-modal Transformer based decoder-only language model, which inherently captures the intra-modal and inter-modal dynamics within various input modalities for the text summarization task. FLORAL utilizes an increasing number of self-attentions to capture multimodality and performs significantly better than traditional encoder-decoder based networks. Extensive experiments illustrate that FLORAL achieves significant improvement over the baselines in both qualitative and quantitative evaluations on the existing How2 dataset for short videos and newly introduced AVIATE dataset for videos with diverse duration, beating the best baseline on the two datasets by $1.39$ and $2.74$ ROUGE-L points respectively.

arXiv:2105.09458공식 코드 · Papers with Code

MLBiNet: A Cross-Sentence Collective Event Detection Network

We consider the problem of collectively detecting multiple events, particularly in cross-sentence settings. The key to dealing with the problem is to encode semantic information and model event inter-dependency at a document-level. In this paper, we reformulate it as a Seq2Seq task and propose a Multi-Layer Bidirectional Network (MLBiNet) to capture the document-level association of events and semantic information simultaneously. Specifically, a bidirectional decoder is firstly devised to model event inter-dependency within a sentence when decoding the event tag vector sequence. Secondly, an information aggregation module is employed to aggregate sentence-level semantic and event tag information. Finally, we stack multiple bidirectional decoders and feed cross-sentence information, forming a multi-layer bidirectional tagging architecture to iteratively propagate information across sentences. We show that our approach provides significant improvement in performance compared to the current state-of-the-art results.

arXiv:2105.09040공식 코드 · Papers with Code

Advances in integration of end-to-end neural and clustering-based diarization for real conversational speech

Recently, we proposed a novel speaker diarization method called End-to-End-Neural-Diarization-vector clustering (EEND-vector clustering) that integrates clustering-based and end-to-end neural network-based diarization approaches into one framework. The proposed method combines advantages of both frameworks, i.e. high diarization performance and handling of overlapped speech based on EEND, and robust handling of long recordings with an arbitrary number of speakers based on clustering-based approaches. However, the method was only evaluated so far on simulated 2-speaker meeting-like data. This paper is to (1) report recent advances we made to this framework, including newly introduced robust constrained clustering algorithms, and (2) experimentally show that the method can now significantly outperform competitive diarization methods such as Encoder-Decoder Attractor (EDA)-EEND, on CALLHOME data which comprises real conversational speech data including overlapped speech and an arbitrary number of speakers. By further analyzing the experimental results, this paper also discusses pros and cons of the proposed method and reveals potential for further improvement. A set of the code to reproduce the results is available at https://github.com/nttcslab-sp/EEND-vector-clustering.

arXiv:2105.08963공식 코드 · Papers with Code

Long Text Generation by Modeling Sentence-Level and Discourse-Level Coherence

Generating long and coherent text is an important but challenging task, particularly for open-ended language generation tasks such as story generation. Despite the success in modeling intra-sentence coherence, existing generation models (e.g., BART) still struggle to maintain a coherent event sequence throughout the generated text. We conjecture that this is because of the difficulty for the decoder to capture the high-level semantics and discourse structures in the context beyond token-level co-occurrence. In this paper, we propose a long text generation model, which can represent the prefix sentences at sentence level and discourse level in the decoding process. To this end, we propose two pretraining objectives to learn the representations by predicting inter-sentence semantic similarity and distinguishing between normal and shuffled sentence orders. Extensive experiments show that our model can generate more coherent texts than state-of-the-art baselines.

arXiv:2105.08901공식 코드 · Papers with Code

A Sequence-to-Set Network for Nested Named Entity Recognition

Named entity recognition (NER) is a widely studied task in natural language processing. Recently, a growing number of studies have focused on the nested NER. The span-based methods, considering the entity recognition as a span classification task, can deal with nested entities naturally. But they suffer from the huge search space and the lack of interactions between entities. To address these issues, we propose a novel sequence-to-set neural network for nested NER. Instead of specifying candidate spans in advance, we provide a fixed set of learnable vectors to learn the patterns of the valuable spans. We utilize a non-autoregressive decoder to predict the final set of entities in one pass, in which we are able to capture dependencies between entities. Compared with the sequence-to-sequence method, our model is more suitable for such unordered recognition task as it is insensitive to the label order. In addition, we utilize the loss function based on bipartite matching to compute the overall training loss. Experimental results show that our proposed model achieves state-of-the-art on three nested NER corpora: ACE 2004, ACE 2005 and KBP 2017. The code is available at https://github.com/zqtan1024/sequence-to-set.

arXiv:2105.08840공식 코드 · Papers with Code

Training Heterogeneous Features in Sequence to Sequence Tasks: Latent Enhanced Multi-filter Seq2Seq Model

In language processing, training data with extremely large variance may lead to difficulty in the language model's convergence. It is difficult for the network parameters to adapt sentences with largely varied semantics or grammatical structures. To resolve this problem, we introduce a model that concentrates the each of the heterogeneous features in the input sentences. Building upon the encoder-decoder architecture, we design a latent-enhanced multi-filter seq2seq model (LEMS) that analyzes the input representations by introducing a latent space transformation and clustering. The representations are extracted from the final hidden state of the encoder and lie in the latent space. A latent space transformation is applied for enhancing the quality of the representations. Thus the clustering algorithm can easily separate samples based on the features of these representations. Multiple filters are trained by the features from their corresponding clusters, and the heterogeneity of the training data can be resolved accordingly. We conduct two sets of comparative experiments on semantic parsing and machine translation, using the Geo-query dataset and Multi30k English-French to demonstrate the enhancement our model has made respectively.

arXiv:2105.08807

Exploring Text-to-Text Transformers for English to Hinglish Machine Translation with Synthetic Code-Mixing

We describe models focused at the understudied problem of translating between monolingual and code-mixed language pairs. More specifically, we offer a wide range of models that convert monolingual English text into Hinglish (code-mixed Hindi and English). Given the recent success of pretrained language models, we also test the utility of two recent Transformer-based encoder-decoder models (i.e., mT5 and mBART) on the task finding both to work well. Given the paucity of training data for code-mixing, we also propose a dependency-free method for generating code-mixed texts from bilingual distributed representations that we exploit for improving language model performance. In particular, armed with this additional data, we adopt a curriculum learning approach where we first finetune the language models on synthetic data then on gold code-mixed data. We find that, although simple, our synthetic code-mixing method is competitive with (and in some cases is even superior to) several standard methods (backtranslation, method based on equivalence constraint theory) under a diverse set of conditions. Our work shows that the mT5 model, finetuned following the curriculum learning procedure, achieves best translation performance (12.67 BLEU). Our models place first in the overall ranking of the English-Hinglish official shared task.

arXiv:2105.09076공식 코드 · Papers with Code

Light-weight Document Image Cleanup using Perceptual Loss

Smartphones have enabled effortless capturing and sharing of documents in digital form. The documents, however, often undergo various types of degradation due to aging, stains, or shortcoming of capturing environment such as shadow, non-uniform lighting, etc., which reduces the comprehensibility of the document images. In this work, we consider the problem of document image cleanup on embedded applications such as smartphone apps, which usually have memory, energy, and latency limitations due to the device and/or for best human user experience. We propose a light-weight encoder decoder based convolutional neural network architecture for removing the noisy elements from document images. To compensate for generalization performance with a low network capacity, we incorporate the perceptual loss for knowledge transfer from pre-trained deep CNN network in our loss function. In terms of the number of parameters and product-sum operations, our models are 65-1030 and 3-27 times, respectively, smaller than existing state-of-the-art document enhancement models. Overall, the proposed models offer a favorable resource versus accuracy trade-off and we empirically illustrate the efficacy of our approach on several real-world benchmark datasets.

arXiv:2105.08970

Disentanglement Learning for Variational Autoencoders Applied to Audio-Visual Speech Enhancement

Recently, the standard variational autoencoder has been successfully used to learn a probabilistic prior over speech signals, which is then used to perform speech enhancement. Variational autoencoders have then been conditioned on a label describing a high-level speech attribute (e.g. speech activity) that allows for a more explicit control of speech generation. However, the label is not guaranteed to be disentangled from the other latent variables, which results in limited performance improvements compared to the standard variational autoencoder. In this work, we propose to use an adversarial training scheme for variational autoencoders to disentangle the label from the other latent variables. At training, we use a discriminator that competes with the encoder of the variational autoencoder. Simultaneously, we also use an additional encoder that estimates the label for the decoder of the variational autoencoder, which proves to be crucial to learn disentanglement. We show the benefit of the proposed disentanglement learning when a voice activity label, estimated from visual data, is used for speech enhancement.

arXiv:2105.08879공식 코드 · Papers with Code

Font Style that Fits an Image -- Font Generation Based on Image Context

When fonts are used on documents, they are intentionally selected by designers. For example, when designing a book cover, the typography of the text is an important factor in the overall feel of the book. In addition, it needs to be an appropriate font for the rest of the book cover. Thus, we propose a method of generating a book title image based on its context within a book cover. We propose an end-to-end neural network that inputs the book cover, a target location mask, and a desired book title and outputs stylized text suitable for the cover. The proposed network uses a combination of a multi-input encoder-decoder, a text skeleton prediction network, a perception network, and an adversarial discriminator. We demonstrate that the proposed method can effectively produce desirable and appropriate book cover text through quantitative and qualitative results.

arXiv:2105.08865

Learning optimally separated class-specific subspace representations using convolutional autoencoder

In this work, we propose a novel convolutional autoencoder based architecture to generate subspace specific feature representations that are best suited for classification task. The class-specific data is assumed to lie in low dimensional linear subspaces, which could be noisy and not well separated, i.e., subspace distance (principal angle) between two classes is very low. The proposed network uses a novel class-specific self expressiveness (CSSE) layer sandwiched between encoder and decoder networks to generate class-wise subspace representations which are well separated. The CSSE layer along with encoder/ decoder are trained in such a way that data still lies in subspaces in the feature space with minimum principal angle much higher than that of the input space. To demonstrate the effectiveness of the proposed approach, several experiments have been carried out on state-of-the-art machine learning datasets and a significant improvement in classification performance is observed over existing subspace based transformation learning methods.