PyTorchKR Papers

최신 논문

총 9,642편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2105.02216공식 코드 · Papers with Code

Self-Supervised Multi-Frame Monocular Scene Flow

Estimating 3D scene flow from a sequence of monocular images has been gaining increased attention due to the simple, economical capture setup. Owing to the severe ill-posedness of the problem, the accuracy of current methods has been limited, especially that of efficient, real-time approaches. In this paper, we introduce a multi-frame monocular scene flow network based on self-supervised learning, improving the accuracy over previous networks while retaining real-time efficiency. Based on an advanced two-frame baseline with a split-decoder design, we propose (i) a multi-frame model using a triple frame input and convolutional LSTM connections, (ii) an occlusion-aware census loss for better accuracy, and (iii) a gradient detaching strategy to improve training stability. On the KITTI dataset, we observe state-of-the-art accuracy among monocular scene flow methods based on self-supervised learning.

arXiv:2105.01218

Weakly-Supervised Universal Lesion Segmentation with Regional Level Set Loss

Accurately segmenting a variety of clinically significant lesions from whole body computed tomography (CT) scans is a critical task on precision oncology imaging, denoted as universal lesion segmentation (ULS). Manual annotation is the current clinical practice, being highly time-consuming and inconsistent on tumor's longitudinal assessment. Effectively training an automatic segmentation model is desirable but relies heavily on a large number of pixel-wise labelled data. Existing weakly-supervised segmentation approaches often struggle with regions nearby the lesion boundaries. In this paper, we present a novel weakly-supervised universal lesion segmentation method by building an attention enhanced model based on the High-Resolution Network (HRNet), named AHRNet, and propose a regional level set (RLS) loss for optimizing lesion boundary delineation. AHRNet provides advanced high-resolution deep image features by involving a decoder, dual-attention and scale attention mechanisms, which are crucial to performing accurate lesion segmentation. RLS can optimize the model reliably and effectively in a weakly-supervised fashion, forcing the segmentation close to lesion boundary. Extensive experimental results demonstrate that our method achieves the best performance on the publicly large-scale DeepLesion dataset and a hold-out test set.

arXiv:2105.01299

LAFFNet: A Lightweight Adaptive Feature Fusion Network for Underwater Image Enhancement

Underwater image enhancement is an important low-level computer vision task for autonomous underwater vehicles and remotely operated vehicles to explore and understand the underwater environments. Recently, deep convolutional neural networks (CNNs) have been successfully used in many computer vision problems, and so does underwater image enhancement. There are many deep-learning-based methods with impressive performance for underwater image enhancement, but their memory and model parameter costs are hindrances in practical application. To address this issue, we propose a lightweight adaptive feature fusion network (LAFFNet). The model is the encoder-decoder model with multiple adaptive feature fusion (AAF) modules. AAF subsumes multiple branches with different kernel sizes to generate multi-scale feature maps. Furthermore, channel attention is used to merge these feature maps adaptively. Our method reduces the number of parameters from 2.5M to 0.15M (around 94% reduction) but outperforms state-of-the-art algorithms by extensive experiments. Furthermore, we demonstrate our LAFFNet effectively improves high-level vision tasks like salience object detection and single image depth estimation.

arXiv:2105.00999공식 코드 · Papers with Code

Enhanced U-Net: A Feature Enhancement Network for Polyp Segmentation

Colonoscopy is a procedure to detect colorectal polyps which are the primary cause for developing colorectal cancer. However, polyp segmentation is a challenging task due to the diverse shape, size, color, and texture of polyps, shuttle difference between polyp and its background, as well as low contrast of the colonoscopic images. To address these challenges, we propose a feature enhancement network for accurate polyp segmentation in colonoscopy images. Specifically, the proposed network enhances the semantic information using the novel Semantic Feature Enhance Module (SFEM). Furthermore, instead of directly adding encoder features to the respective decoder layer, we introduce an Adaptive Global Context Module (AGCM), which focuses only on the encoder's significant and hard fine-grained features. The integration of these two modules improves the quality of features layer by layer, which in turn enhances the final feature representation. The proposed approach is evaluated on five colonoscopy datasets and demonstrates superior performance compared to other state-of-the-art models.

arXiv:2105.00967공식 코드 · Papers with Code

A lightweight deep learning based cloud detection method for Sentinel-2A imagery fusing multi-scale spectral and spatial features

Clouds are a very important factor in the availability of optical remote sensing images. Recently, deep learning-based cloud detection methods have surpassed classical methods based on rules and physical models of clouds. However, most of these deep models are very large which limits their applicability and explainability, while other models do not make use of the full spectral information in multi-spectral images such as Sentinel-2. In this paper, we propose a lightweight network for cloud detection, fusing multi-scale spectral and spatial features (CDFM3SF) and tailored for processing all spectral bands in Sentinel- 2A images. The proposed method consists of an encoder and a decoder. In the encoder, three input branches are designed to handle spectral bands at their native resolution and extract multiscale spectral features. Three novel components are designed: a mixed depth-wise separable convolution (MDSC) and a shared and dilated residual block (SDRB) to extract multi-scale spatial features, and a concatenation and sum (CS) operation to fuse multi-scale spectral and spatial features with little calculation and no additional parameters. The decoder of CD-FM3SF outputs three cloud masks at the same resolution as input bands to enhance the supervision information of small, middle and large clouds. To validate the performance of the proposed method, we manually labeled 36 Sentinel-2A scenes evenly distributed over mainland China. The experiment results demonstrate that CD-FM3SF outperforms traditional cloud detection methods and state-of-theart deep learning-based methods in both accuracy and speed.

arXiv:2105.00690공식 코드 · Papers with Code

Multi-modal Bifurcated Network for Depth Guided Image Relighting

Image relighting aims to recalibrate the illumination setting in an image. In this paper, we propose a deep learning-based method called multi-modal bifurcated network (MBNet) for depth guided image relighting. That is, given an image and the corresponding depth maps, a new image with the given illuminant angle and color temperature is generated by our network. This model extracts the image and the depth features by the bifurcated network in the encoder. To use the two features effectively, we adopt the dynamic dilated pyramid modules in the decoder. Moreover, to increase the variety of training data, we propose a novel data process pipeline to increase the number of the training data. Experiments conducted on the VIDIT dataset show that the proposed solution obtains the \textbf{1}$^{st}$ place in terms of SSIM and PMS in the NTIRE 2021 Depth Guide One-to-one Relighting Challenge.

arXiv:2105.00681공식 코드 · Papers with Code

S3Net: A Single Stream Structure for Depth Guided Image Relighting

Depth guided any-to-any image relighting aims to generate a relit image from the original image and corresponding depth maps to match the illumination setting of the given guided image and its depth map. To the best of our knowledge, this task is a new challenge that has not been addressed in the previous literature. To address this issue, we propose a deep learning-based neural Single Stream Structure network called S3Net for depth guided image relighting. This network is an encoder-decoder model. We concatenate all images and corresponding depth maps as the input and feed them into the model. The decoder part contains the attention module and the enhanced module to focus on the relighting-related regions in the guided images. Experiments performed on challenging benchmark show that the proposed model achieves the 3 rd highest SSIM in the NTIRE 2021 Depth Guided Any-to-any Relighting Challenge.

arXiv:2105.00273공식 코드 · Papers with Code

Blind microscopy image denoising with a deep residual and multiscale encoder/decoder network

In computer-aided diagnosis (CAD) focused on microscopy, denoising improves the quality of image analysis. In general, the accuracy of this process may depend both on the experience of the microscopist and on the equipment sensitivity and specificity. A medical image could be corrupted by both intrinsic noise, due to the device limitations, and, by extrinsic signal perturbations during image acquisition. Nowadays, CAD deep learning applications pre-process images with image denoising models to reinforce learning and prediction. In this work, an innovative and lightweight deep multiscale convolutional encoder-decoder neural network is proposed. Specifically, the encoder uses deterministic mapping to map features into a hidden representation. Then, the latent representation is rebuilt to generate the reconstructed denoised image. Residual learning strategies are used to improve and accelerate the training process using skip connections in bridging across convolutional and deconvolutional layers. The proposed model reaches on average 38.38 of PSNR and 0.98 of SSIM on a test set of 57458 images overcoming state-of-the-art models in the same application domain

arXiv:2105.00982

On the limit of English conversational speech recognition

In our previous work we demonstrated that a single headed attention encoder-decoder model is able to reach state-of-the-art results in conversational speech recognition. In this paper, we further improve the results for both Switchboard 300 and 2000. Through use of an improved optimizer, speaker vector embeddings, and alternative speech representations we reduce the recognition errors of our LSTM system on Switchboard-300 by 4% relative. Compensation of the decoder model with the probability ratio approach allows more efficient integration of an external language model, and we report 5.9% and 11.5% WER on the SWB and CHM parts of Hub5'00 with very simple LSTM models. Our study also considers the recently proposed conformer, and more advanced self-attention based language models. Overall, the conformer shows similar performance to the LSTM; nevertheless, their combination and decoding with an improved LM reaches a new record on Switchboard-300, 5.0% and 10.0% WER on SWB and CHM. Our findings are also confirmed on Switchboard-2000, and a new state of the art is reported, practically reaching the limit of the benchmark.

arXiv:2105.00573

Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks

End-to-end approaches for sequence tasks are becoming increasingly popular. Yet for complex sequence tasks, like speech translation, systems that cascade several models trained on sub-tasks have shown to be superior, suggesting that the compositionality of cascaded systems simplifies learning and enables sophisticated search capabilities. In this work, we present an end-to-end framework that exploits compositionality to learn searchable hidden representations at intermediate stages of a sequence model using decomposed sub-tasks. These hidden intermediates can be improved using beam search to enhance the overall performance and can also incorporate external models at intermediate stages of the network to re-score or adapt towards out-of-domain data. One instance of the proposed framework is a Multi-Decoder model for speech translation that extracts the searchable hidden intermediates from a speech recognition sub-task. The model demonstrates the aforementioned benefits and outperforms the previous state-of-the-art by around +6 and +3 BLEU on the two test sets of Fisher-CallHome and by around +3 and +4 BLEU on the English-German and English-French test sets of MuST-C.

arXiv:2105.00171공식 코드 · Papers with Code

AlloST: Low-resource Speech Translation without Source Transcription

The end-to-end architecture has made promising progress in speech translation (ST). However, the ST task is still challenging under low-resource conditions. Most ST models have shown unsatisfactory results, especially in the absence of word information from the source speech utterance. In this study, we survey methods to improve ST performance without using source transcription, and propose a learning framework that utilizes a language-independent universal phone recognizer. The framework is based on an attention-based sequence-to-sequence model, where the encoder generates the phonetic embeddings and phone-aware acoustic representations, and the decoder controls the fusion of the two embedding streams to produce the target token sequence. In addition to investigating different fusion strategies, we explore the specific usage of byte pair encoding (BPE), which compresses a phone sequence into a syllable-like segmented sequence. Due to the conversion of symbols, a segmented sequence represents not only pronunciation but also language-dependent information lacking in phones. Experiments conducted on the Fisher Spanish-English and Taigi-Mandarin drama corpora show that our method outperforms the conformer-based baseline, and the performance is close to that of the existing best method using source transcription.

arXiv:2105.00079공식 코드 · Papers with Code

Improving Response Quality with Backward Reasoning in Open-domain Dialogue Systems

Being able to generate informative and coherent dialogue responses is crucial when designing human-like open-domain dialogue systems. Encoder-decoder-based dialogue models tend to produce generic and dull responses during the decoding step because the most predictable response is likely to be a non-informative response instead of the most suitable one. To alleviate this problem, we propose to train the generation model in a bidirectional manner by adding a backward reasoning step to the vanilla encoder-decoder training. The proposed backward reasoning step pushes the model to produce more informative and coherent content because the forward generation step's output is used to infer the dialogue context in the backward direction. The advantage of our method is that the forward generation and backward reasoning steps are trained simultaneously through the use of a latent variable to facilitate bidirectional optimization. Our method can improve response quality without introducing side information (e.g., a pre-trained topic model). The proposed bidirectional response generation method achieves state-of-the-art performance for response quality.

arXiv:2105.00020

Continuous Face Aging via Self-estimated Residual Age Embedding

Face synthesis, including face aging, in particular, has been one of the major topics that witnessed a substantial improvement in image fidelity by using generative adversarial networks (GANs). Most existing face aging approaches divide the dataset into several age groups and leverage group-based training strategies, which lacks the ability to provide fine-controlled continuous aging synthesis in nature. In this work, we propose a unified network structure that embeds a linear age estimator into a GAN-based model, where the embedded age estimator is trained jointly with the encoder and decoder to estimate the age of a face image and provide a personalized target age embedding for age progression/regression. The personalized target age embedding is synthesized by incorporating both personalized residual age embedding of the current age and exemplar-face aging basis of the target age, where all preceding aging bases are derived from the learned weights of the linear age estimator. This formulation brings the unified perspective of estimating the age and generating personalized aged face, where self-estimated age embeddings can be learned for every single age. The qualitative and quantitative evaluations on different datasets further demonstrate the significant improvement in the continuous face aging aspect over the state-of-the-art.

arXiv:2105.00997공식 코드 · Papers with Code

Recovering Barabási-Albert Parameters of Graphs through Disentanglement

Classical graph modeling approaches such as Erd\H{o}s R\'{e}nyi (ER) random graphs or Barab\'asi-Albert (BA) graphs, here referred to as stylized models, aim to reproduce properties of real-world graphs in an interpretable way. While useful, graph generation with stylized models requires domain knowledge and iterative trial and error simulation. Previous work by Stoehr et al. (2019) addresses these issues by learning the generation process from graph data, using a disentanglement-focused deep autoencoding framework, more specifically, a $\beta$-Variational Autoencoder ($\beta$-VAE). While they successfully recover the generative parameters of ER graphs through the model's latent variables, their model performs badly on sequentially generated graphs such as BA graphs, due to their oversimplified decoder. We focus on recovering the generative parameters of BA graphs by replacing their $\beta$-VAE decoder with a sequential one. We first learn the generative BA parameters in a supervised fashion using a Graph Neural Network (GNN) and a Random Forest Regressor, by minimizing the squared loss between the true generative parameters and the latent variables. Next, we train a $\beta$-VAE model, combining the GNN encoder from the first stage with an LSTM-based decoder with a customized loss.

arXiv:2105.00250공식 코드 · Papers with Code

Incorporating Transformer and LSTM to Kalman Filter with EM algorithm for state estimation

Kalman Filter requires the true parameters of the model and solves optimal state estimation recursively. Expectation Maximization (EM) algorithm is applicable for estimating the parameters of the model that are not available before Kalman filtering, which is EM-KF algorithm. To improve the preciseness of EM-KF algorithm, the author presents a state estimation method by combining the Long-Short Term Memory network (LSTM), Transformer and EM-KF algorithm in the framework of Encoder-Decoder in Sequence to Sequence (seq2seq). Simulation on a linear mobile robot model demonstrates that the new method is more accurate. Source code of this paper is available at https://github.com/zshicode/Deep-Learning-Based-State-Estimation.

arXiv:2104.14735

DPR-CAE: Capsule Autoencoder with Dynamic Part Representation for Image Parsing

Parsing an image into a hierarchy of objects, parts, and relations is important and also challenging in many computer vision tasks. This paper proposes a simple and effective capsule autoencoder to address this issue, called DPR-CAE. In our approach, the encoder parses the input into a set of part capsules, including pose, intensity, and dynamic vector. The decoder introduces a novel dynamic part representation (DPR) by combining the dynamic vector and a shared template bank. These part representations are then regulated by corresponding capsules to composite the final output in an interpretable way. Besides, an extra translation-invariant module is proposed to avoid directly learning the uncertain scene-part relationship in our DPR-CAE, which makes the resulting method achieves a promising performance gain on $rm$-MNIST and $rm$-Fashion-MNIST. % to model the scene-object relationship DPR-CAE can be easily combined with the existing stacked capsule autoencoder and experimental results show it significantly improves performance in terms of unsupervised object classification. Our code is available in the Appendix.

arXiv:2104.14730

Perceptual Image Quality Assessment with Transformers

In this paper, we propose an image quality transformer (IQT) that successfully applies a transformer architecture to a perceptual full-reference image quality assessment (IQA) task. Perceptual representation becomes more important in image quality assessment. In this context, we extract the perceptual feature representations from each of input images using a convolutional neural network (CNN) backbone. The extracted feature maps are fed into the transformer encoder and decoder in order to compare a reference and distorted images. Following an approach of the transformer-based vision models, we use extra learnable quality embedding and position embedding. The output of the transformer is passed to a prediction head in order to predict a final quality score. The experimental results show that our proposed model has an outstanding performance for the standard IQA datasets. For a large-scale IQA dataset containing output images of generative model, our model also shows the promising results. The proposed IQT was ranked first among 13 participants in the NTIRE 2021 perceptual image quality assessment challenge. Our work will be an opportunity to further expand the approach for the perceptual IQA task.

arXiv:2104.14839

The Factual Inconsistency Problem in Abstractive Text Summarization: A Survey

Recently, various neural encoder-decoder models pioneered by Seq2Seq framework have been proposed to achieve the goal of generating more abstractive summaries by learning to map input text to output text. At a high level, such neural models can freely generate summaries without any constraint on the words or phrases used. Moreover, their format is closer to human-edited summaries and output is more readable and fluent. However, the neural model's abstraction ability is a double-edged sword. A commonly observed problem with the generated summaries is the distortion or fabrication of factual information in the article. This inconsistency between the original text and the summary has caused various concerns over its applicability, and the previous evaluation methods of text summarization are not suitable for this issue. In response to the above problems, the current research direction is predominantly divided into two categories, one is to design fact-aware evaluation metrics to select outputs without factual inconsistency errors, and the other is to develop new summarization systems towards factual consistency. In this survey, we focus on presenting a comprehensive review of these fact-specific evaluation methods and text summarization models.

arXiv:2104.14756

Predicting Intraoperative Hypoxemia with Hybrid Inference Sequence Autoencoder Networks

We present an end-to-end model using streaming physiological time series to predict near-term risk for hypoxemia, a rare, but life-threatening condition known to cause serious patient harm during surgery. Inspired by the fact that a hypoxemia event is defined based on a future sequence of low SpO2 (i.e., blood oxygen saturation) instances, we propose the hybrid inference network (hiNet) that makes hybrid inference on both future low SpO2 instances and hypoxemia outcomes. hiNet integrates 1) a joint sequence autoencoder that simultaneously optimizes a discriminative decoder for label prediction, and 2) two auxiliary decoders trained for data reconstruction and forecast, which seamlessly learn contextual latent representations that capture the transition from present states to future states. All decoders share a memory-based encoder that helps capture the global dynamics of patient measurement. For a large surgical cohort of 72,081 surgeries at a major academic medical center, our model outperforms strong baselines including the model used by the state-of-the-art hypoxemia prediction system. With its capability to make real-time predictions of near-term hypoxemic at clinically acceptable alarm rates, hiNet shows promise in improving clinical decision making and easing burden of perioperative care.

arXiv:2104.12631

Head-synchronous Decoding for Transformer-based Streaming ASR

Online Transformer-based automatic speech recognition (ASR) systems have been extensively studied due to the increasing demand for streaming applications. Recently proposed Decoder-end Adaptive Computation Steps (DACS) algorithm for online Transformer ASR was shown to achieve state-of-the-art performance and outperform other existing methods. However, like any other online approach, the DACS-based attention heads in each of the Transformer decoder layers operate independently (or asynchronously) and lead to diverged attending positions. Since DACS employs a truncation threshold to determine the halting position, some of the attention weights are cut off untimely and might impact the stability and precision of decoding. To overcome these issues, here we propose a head-synchronous (HS) version of the DACS algorithm, where the boundary of attention is jointly detected by all the DACS heads in each decoder layer. ASR experiments on Wall Street Journal (WSJ), AIShell-1 and Librispeech show that the proposed method consistently outperforms vanilla DACS and achieves state-of-the-art performance. We will also demonstrate that HS-DACS has reduced decoding cost when compared to vanilla DACS.