PyTorchKR Papers

최신 논문

총 9,642편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2107.05246

Joint Activity Detection, Channel Estimation, and Data Decoding for Grant-free Massive Random Access

In the massive machine-type communication (mMTC) scenario, a large number of devices with sporadic traffic need to access the network on limited radio resources. While grant-free random access has emerged as a promising mechanism for massive access, its potential has not been fully unleashed. In particular, the common sparsity pattern in the received pilot and data signal has been ignored in most existing studies, and auxiliary information of channel decoding has not been utilized for user activity detection. This paper endeavors to develop advanced receivers in a holistic manner for joint activity detection, channel estimation, and data decoding. In particular, a turbo receiver based on the bilinear generalized approximate message passing (BiG-AMP) algorithm is developed. In this receiver, all the received symbols will be utilized to jointly estimate the channel state, user activity, and soft data symbols, which effectively exploits the common sparsity pattern. Meanwhile, the extrinsic information from the channel decoder will assist the joint channel estimation and data detection. To reduce the complexity, a low-cost side information-aided receiver is also proposed, where the channel decoder provides side information to update the estimates on whether a user is active or not. Simulation results show that the turbo receiver is able to reduce the activity detection, channel estimation, and data decoding errors effectively, while the side information-aided receiver notably outperforms the conventional method with a relatively low complexity.

arXiv:2107.04973

A Deep-Bayesian Framework for Adaptive Speech Duration Modification

We propose the first method to adaptively modify the duration of a given speech signal. Our approach uses a Bayesian framework to define a latent attention map that links frames of the input and target utterances. We train a masked convolutional encoder-decoder network to produce this attention map via a stochastic version of the mean absolute error loss function; our model also predicts the length of the target speech signal using the encoder embeddings. The predicted length determines the number of steps for the decoder operation. During inference, we generate the attention map as a proxy for the similarity matrix between the given input speech and an unknown target speech signal. Using this similarity matrix, we compute a warping path of alignment between the two signals. Our experiments demonstrate that this adaptive framework produces similar results to dynamic time warping, which relies on a known target signal, on both voice conversion and emotion conversion tasks. We also show that our technique results in a high quality of generated speech that is on par with state-of-the-art vocoders.

arXiv:2107.04644

Self-Supervised Generative Adversarial Network for Depth Estimation in Laparoscopic Images

Dense depth estimation and 3D reconstruction of a surgical scene are crucial steps in computer assisted surgery. Recent work has shown that depth estimation from a stereo images pair could be solved with convolutional neural networks. However, most recent depth estimation models were trained on datasets with per-pixel ground truth. Such data is especially rare for laparoscopic imaging, making it hard to apply supervised depth estimation to real surgical applications. To overcome this limitation, we propose SADepth, a new self-supervised depth estimation method based on Generative Adversarial Networks. It consists of an encoder-decoder generator and a discriminator to incorporate geometry constraints during training. Multi-scale outputs from the generator help to solve the local minima caused by the photometric reprojection loss, while the adversarial learning improves the framework generation quality. Extensive experiments on two public datasets show that SADepth outperforms recent state-of-the-art unsupervised methods by a large margin, and reduces the gap between supervised and unsupervised depth estimation in laparoscopic images.

arXiv:2107.05274공식 코드 · Papers with Code

TransAttUnet: Multi-level Attention-guided U-Net with Transformer for Medical Image Segmentation

Accurate segmentation of organs or lesions from medical images is crucial for reliable diagnosis of diseases and organ morphometry. In recent years, convolutional encoder-decoder solutions have achieved substantial progress in the field of automatic medical image segmentation. Due to the inherent bias in the convolution operations, prior models mainly focus on local visual cues formed by the neighboring pixels, but fail to fully model the long-range contextual dependencies. In this paper, we propose a novel Transformer-based Attention Guided Network called TransAttUnet, in which the multi-level guided attention and multi-scale skip connection are designed to jointly enhance the performance of the semantical segmentation architecture. Inspired by Transformer, the self-aware attention (SAA) module with Transformer Self Attention (TSA) and Global Spatial Attention (GSA) is incorporated into TransAttUnet to effectively learn the non-local interactions among encoder features. Moreover, we also use additional multi-scale skip connections between decoder blocks to aggregate the upsampled features with different semantic scales. In this way, the representation ability of multi-scale context information is strengthened to generate discriminative features. Benefitting from these complementary components, the proposed TransAttUnet can effectively alleviate the loss of fine details caused by the stacking of convolution layers and the consecutive sampling operations, finally improving the segmentation quality of medical images. Extensive experiments on multiple medical image segmentation datasets from different imaging modalities demonstrate that the proposed method consistently outperforms the state-of-the-art baselines. Our code and pre-trained models are available at: https://github.com/YishuLiu/TransAttUnet.

arXiv:2107.04396공식 코드 · Papers with Code

Multi-Modal Association based Grouping for Form Structure Extraction

Document structure extraction has been a widely researched area for decades. Recent work in this direction has been deep learning-based, mostly focusing on extracting structure using fully convolution NN through semantic segmentation. In this work, we present a novel multi-modal approach for form structure extraction. Given simple elements such as textruns and widgets, we extract higher-order structures such as TextBlocks, Text Fields, Choice Fields, and Choice Groups, which are essential for information collection in forms. To achieve this, we obtain a local image patch around each low-level element (reference) by identifying candidate elements closest to it. We process textual and spatial representation of candidates sequentially through a BiLSTM to obtain context-aware representations and fuse them with image patch features obtained by processing it through a CNN. Subsequently, the sequential decoder takes this fused feature vector to predict the association type between reference and candidates. These predicted associations are utilized to determine larger structures through connected components analysis. Experimental results show the effectiveness of our approach achieving a recall of 90.29%, 73.80%, 83.12%, and 52.72% for the above structures, respectively, outperforming semantic segmentation baselines significantly. We show the efficacy of our method through ablations, comparing it against using individual modalities. We also introduce our new rich human-annotated Forms Dataset.

arXiv:2107.04292공식 코드 · Papers with Code

UniRE: A Unified Label Space for Entity Relation Extraction

Many joint entity relation extraction models setup two separated label spaces for the two sub-tasks (i.e., entity detection and relation classification). We argue that this setting may hinder the information interaction between entities and relations. In this work, we propose to eliminate the different treatment on the two sub-tasks' label spaces. The input of our model is a table containing all word pairs from a sentence. Entities and relations are represented by squares and rectangles in the table. We apply a unified classifier to predict each cell's label, which unifies the learning of two sub-tasks. For testing, an effective (yet fast) approximate decoder is proposed for finding squares and rectangles from tables. Experiments on three benchmarks (ACE04, ACE05, SciERC) show that, using only half the number of parameters, our model achieves competitive accuracy with the best extractor, and is faster.

arXiv:2107.04152공식 코드 · Papers with Code

Levi Graph AMR Parser using Heterogeneous Attention

Coupled with biaffine decoders, transformers have been effectively adapted to text-to-graph transduction and achieved state-of-the-art performance on AMR parsing. Many prior works, however, rely on the biaffine decoder for either or both arc and label predictions although most features used by the decoder may be learned by the transformer already. This paper presents a novel approach to AMR parsing by combining heterogeneous data (tokens, concepts, labels) as one input to a transformer to learn attention, and use only attention matrices from the transformer to predict all elements in AMR graphs (concepts, arcs, labels). Although our models use significantly fewer parameters than the previous state-of-the-art graph parser, they show similar or better accuracy on AMR 2.0 and 3.0.

arXiv:2107.03688

An Embedded Iris Recognition System Optimization using Dynamically ReconfigurableDecoder with LDPC Codes

Extracting and analyzing iris textures for biometric recognition has been extensively studied. As the transition of iris recognition from lab technology to nation-scale applications, most systems are facing high complexity in either time or space, leading to unfitness for embedded devices. In this paper, the proposed design includes a minimal set of computer vision modules and multi-mode QC-LDPC decoder which can alleviate variability and noise caused by iris acquisition and follow-up process. Several classes of QC-LDPC code from IEEE 802.16 are tested for the validity of accuracy improvement. Some of the codes mentioned above are used for further QC-LDPC decoder quantization, validation and comparison to each other. We show that we can apply Dynamic Partial Reconfiguration technology to implement the multi-mode QC-LDPC decoder for the iris recognition system. The results show that the implementation is power-efficient and good for edge applications.

arXiv:2107.03069

Efficient Transformer for Direct Speech Translation

The advent of Transformer-based models has surpassed the barriers of text. When working with speech, we must face a problem: the sequence length of an audio input is not suitable for the Transformer. To bypass this problem, a usual approach is adding strided convolutional layers, to reduce the sequence length before using the Transformer. In this paper, we propose a new approach for direct Speech Translation, where thanks to an efficient Transformer we can work with a spectrogram without having to use convolutional layers before the Transformer. This allows the encoder to learn directly from the spectrogram and no information is lost. We have created an encoder-decoder model, where the encoder is an efficient Transformer -- the Longformer -- and the decoder is a traditional Transformer decoder. Our results, which are close to the ones obtained with the standard approach, show that this is a promising research direction.

arXiv:2107.03377공식 코드 · Papers with Code

Long Short-Term Transformer for Online Action Detection

We present Long Short-term TRansformer (LSTR), a temporal modeling algorithm for online action detection, which employs a long- and short-term memory mechanism to model prolonged sequence data. It consists of an LSTR encoder that dynamically leverages coarse-scale historical information from an extended temporal window (e.g., 2048 frames spanning of up to 8 minutes), together with an LSTR decoder that focuses on a short time window (e.g., 32 frames spanning 8 seconds) to model the fine-scale characteristics of the data. Compared to prior work, LSTR provides an effective and efficient method to model long videos with fewer heuristics, which is validated by extensive empirical analysis. LSTR achieves state-of-the-art performance on three standard online action detection benchmarks, THUMOS'14, TVSeries, and HACS Segment. Code has been made available at: https://xumingze0308.github.io/projects/lstr

arXiv:2107.03312

SoundStream: An End-to-End Neural Audio Codec

We present SoundStream, a novel neural audio codec that can efficiently compress speech, music and general audio at bitrates normally targeted by speech-tailored codecs. SoundStream relies on a model architecture composed by a fully convolutional encoder/decoder network and a residual vector quantizer, which are trained jointly end-to-end. Training leverages recent advances in text-to-speech and speech enhancement, which combine adversarial and reconstruction losses to allow the generation of high-quality audio content from quantized embeddings. By training with structured dropout applied to quantizer layers, a single model can operate across variable bitrates from 3kbps to 18kbps, with a negligible quality loss when compared with models trained at fixed bitrates. In addition, the model is amenable to a low latency implementation, which supports streamable inference and runs in real time on a smartphone CPU. In subjective evaluations using audio at 24kHz sampling rate, SoundStream at 3kbps outperforms Opus at 12kbps and approaches EVS at 9.6kbps. Moreover, we are able to perform joint compression and enhancement either at the encoder or at the decoder side with no additional latency, which we demonstrate through background noise suppression for speech.

arXiv:2107.03172공식 코드 · Papers with Code

Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in the Real World

Common fully glazed facades and transparent objects present architectural barriers and impede the mobility of people with low vision or blindness, for instance, a path detected behind a glass door is inaccessible unless it is correctly perceived and reacted. However, segmenting these safety-critical objects is rarely covered by conventional assistive technologies. To tackle this issue, we construct a wearable system with a novel dual-head Transformer for Transparency (Trans4Trans) model, which is capable of segmenting general and transparent objects and performing real-time wayfinding to assist people walking alone more safely. Especially, both decoders created by our proposed Transformer Parsing Module (TPM) enable effective joint learning from different datasets. Besides, the efficient Trans4Trans model composed of symmetric transformer-based encoder and decoder, requires little computational expenses and is readily deployed on portable GPUs. Our Trans4Trans model outperforms state-of-the-art methods on the test sets of Stanford2D3D and Trans10K-v2 datasets and obtains mIoU of 45.13% and 75.14%, respectively. Through various pre-tests and a user study conducted in indoor and outdoor scenarios, the usability and reliability of our assistive system have been extensively verified.

arXiv:2107.02958

End-to-End Simultaneous Learning of Single-particle Orientation and 3D Map Reconstruction from Cryo-electron Microscopy Data

Cryogenic electron microscopy (cryo-EM) provides images from different copies of the same biomolecule in arbitrary orientations. Here, we present an end-to-end unsupervised approach that learns individual particle orientations from cryo-EM data while reconstructing the average 3D map of the biomolecule, starting from a random initialization. The approach relies on an auto-encoder architecture where the latent space is explicitly interpreted as orientations used by the decoder to form an image according to the linear projection model. We evaluate our method on simulated data and show that it is able to reconstruct 3D particle maps from noisy- and CTF-corrupted 2D projection images of unknown particle orientations.

arXiv:2107.02530

AdaSpeech 3: Adaptive Text to Speech for Spontaneous Style

While recent text to speech (TTS) models perform very well in synthesizing reading-style (e.g., audiobook) speech, it is still challenging to synthesize spontaneous-style speech (e.g., podcast or conversation), mainly because of two reasons: 1) the lack of training data for spontaneous speech; 2) the difficulty in modeling the filled pauses (um and uh) and diverse rhythms in spontaneous speech. In this paper, we develop AdaSpeech 3, an adaptive TTS system that fine-tunes a well-trained reading-style TTS model for spontaneous-style speech. Specifically, 1) to insert filled pauses (FP) in the text sequence appropriately, we introduce an FP predictor to the TTS model; 2) to model the varying rhythms, we introduce a duration predictor based on mixture of experts (MoE), which contains three experts responsible for the generation of fast, medium and slow speech respectively, and fine-tune it as well as the pitch predictor for rhythm adaptation; 3) to adapt to other speaker timbre, we fine-tune some parameters in the decoder with few speech data. To address the challenge of lack of training data, we mine a spontaneous speech dataset to support our research this work and facilitate future research on spontaneous TTS. Experiments show that AdaSpeech 3 synthesizes speech with natural FP and rhythms in spontaneous styles, and achieves much better MOS and SMOS scores than previous adaptive TTS systems.

arXiv:2107.02380

Learning Disentangled Representation Implicitly via Transformer for Occluded Person Re-Identification

Person re-identification (re-ID) under various occlusions has been a long-standing challenge as person images with different types of occlusions often suffer from misalignment in image matching and ranking. Most existing methods tackle this challenge by aligning spatial features of body parts according to external semantic cues or feature similarities but this alignment approach is complicated and sensitive to noises. We design DRL-Net, a disentangled representation learning network that handles occluded re-ID without requiring strict person image alignment or any additional supervision. Leveraging transformer architectures, DRL-Net achieves alignment-free re-ID via global reasoning of local features of occluded person images. It measures image similarity by automatically disentangling the representation of undefined semantic components, e.g., human body parts or obstacles, under the guidance of semantic preference object queries in the transformer. In addition, we design a decorrelation constraint in the transformer decoder and impose it over object queries for better focus on different semantic components. To better eliminate interference from occlusions, we design a contrast feature learning technique (CFL) for better separation of occlusion features and discriminative ID features. Extensive experiments over occluded and holistic re-ID benchmarks (Occluded-DukeMTMC, Market1501 and DukeMTMC) show that the DRL-Net achieves superior re-ID performance consistently and outperforms the state-of-the-art by large margins for Occluded-DukeMTMC.

arXiv:2107.02368공식 코드 · Papers with Code

UACANet: Uncertainty Augmented Context Attention for Polyp Segmentation

We propose Uncertainty Augmented Context Attention network (UACANet) for polyp segmentation which consider a uncertain area of the saliency map. We construct a modified version of U-Net shape network with additional encoder and decoder and compute a saliency map in each bottom-up stream prediction module and propagate to the next prediction module. In each prediction module, previously predicted saliency map is utilized to compute foreground, background and uncertain area map and we aggregate the feature map with three area maps for each representation. Then we compute the relation between each representation and each pixel in the feature map. We conduct experiments on five popular polyp segmentation benchmarks, Kvasir, CVC-ClinicDB, ETIS, CVC-ColonDB and CVC-300, and achieve state-of-the-art performance. Especially, we achieve 76.6% mean Dice on ETIS dataset which is 13.8% improvement compared to the previous state-of-the-art method. Source code is publicly available at https://github.com/plemeri/UACANet

arXiv:2107.02319

Exploring Deep Learning Methods for Real-Time Surgical Instrument Segmentation in Laparoscopy

Minimally invasive surgery is a surgical intervention used to examine the organs inside the abdomen and has been widely used due to its effectiveness over open surgery. Due to the hardware improvements such as high definition cameras, this procedure has significantly improved and new software methods have demonstrated potential for computer-assisted procedures. However, there exists challenges and requirements to improve detection and tracking of the position of the instruments during these surgical procedures. To this end, we evaluate and compare some popular deep learning methods that can be explored for the automated segmentation of surgical instruments in laparoscopy, an important step towards tool tracking. Our experimental results exhibit that the Dual decoder attention network (DDANet) produces a superior result compared to other recent deep learning methods. DDANet yields a Dice coefficient of 0.8739 and mean intersection-over-union of 0.8183 for the Robust Medical Instrument Segmentation (ROBUST-MIS) Challenge 2019 dataset, at a real-time speed of 101.36 frames-per-second that is critical for such procedures.

arXiv:2107.01431공식 코드 · Papers with Code

Neural-Symbolic Solver for Math Word Problems with Auxiliary Tasks

Previous math word problem solvers following the encoder-decoder paradigm fail to explicitly incorporate essential math symbolic constraints, leading to unexplainable and unreasonable predictions. Herein, we propose Neural-Symbolic Solver (NS-Solver) to explicitly and seamlessly incorporate different levels of symbolic constraints by auxiliary tasks. Our NS-Solver consists of a problem reader to encode problems, a programmer to generate symbolic equations, and a symbolic executor to obtain answers. Along with target expression supervision, our solver is also optimized via 4 new auxiliary objectives to enforce different symbolic reasoning: a) self-supervised number prediction task predicting both number quantity and number locations; b) commonsense constant prediction task predicting what prior knowledge (e.g. how many legs a chicken has) is required; c) program consistency checker computing the semantic loss between predicted equation and target equation to ensure reasonable equation mapping; d) duality exploiting task exploiting the quasi duality between symbolic equation generation and problem's part-of-speech generation to enhance the understanding ability of a solver. Besides, to provide a more realistic and challenging benchmark for developing a universal and scalable solver, we also construct a new large-scale MWP benchmark CM17K consisting of 4 kinds of MWPs (arithmetic, one-unknown linear, one-unknown non-linear, equation set) with more than 17K samples. Extensive experiments on Math23K and our CM17k demonstrate the superiority of our NS-Solver compared to state-of-the-art methods.

arXiv:2107.01569

Cross-Modal Transformer-Based Neural Correction Models for Automatic Speech Recognition

We propose a cross-modal transformer-based neural correction models that refines the output of an automatic speech recognition (ASR) system so as to exclude ASR errors. Generally, neural correction models are composed of encoder-decoder networks, which can directly model sequence-to-sequence mapping problems. The most successful method is to use both input speech and its ASR output text as the input contexts for the encoder-decoder networks. However, the conventional method cannot take into account the relationships between these two different modal inputs because the input contexts are separately encoded for each modal. To effectively leverage the correlated information between the two different modal inputs, our proposed models encode two different contexts jointly on the basis of cross-modal self-attention using a transformer. We expect that cross-modal self-attention can effectively capture the relationships between two different modals for refining ASR hypotheses. We also introduce a shallow fusion technique to efficiently integrate the first-pass ASR model and our proposed neural correction model. Experiments on Japanese natural language ASR tasks demonstrated that our proposed models achieve better ASR performance than conventional neural correction models.

arXiv:2107.01275공식 코드 · Papers with Code

Relaxed Attention: A Simple Method to Boost Performance of End-to-End Automatic Speech Recognition

Recently, attention-based encoder-decoder (AED) models have shown high performance for end-to-end automatic speech recognition (ASR) across several tasks. Addressing overconfidence in such models, in this paper we introduce the concept of relaxed attention, which is a simple gradual injection of a uniform distribution to the encoder-decoder attention weights during training that is easily implemented with two lines of code. We investigate the effect of relaxed attention across different AED model architectures and two prominent ASR tasks, Wall Street Journal (WSJ) and Librispeech. We found that transformers trained with relaxed attention outperform the standard baseline models consistently during decoding with external language models. On WSJ, we set a new benchmark for transformer-based end-to-end speech recognition with a word error rate of 3.65%, outperforming state of the art (4.20%) by 13.1% relative, while introducing only a single hyperparameter.