PyTorchKR Papers

최신 논문

총 9,642편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2104.11180공식 코드 · Papers with Code

Maneuver-based Anchor Trajectory Hypotheses at Roundabouts

Predicting future behavior of the surrounding vehicles is crucial for self-driving platforms to safely navigate through other traffic. This is critical when making decisions like crossing an unsignalized intersection. We address the problem of vehicle motion prediction in a challenging roundabout environment by learning from human driver data. We extend existing recurrent encoder-decoder models to be advantageously combined with anchor trajectories to predict vehicle behaviors on a roundabout. Drivers' intentions are encoded by a set of maneuvers that correspond to semantic driving concepts. Accordingly, our model employs a set of maneuver-specific anchor trajectories that cover the space of possible outcomes at the roundabout. The proposed model can output a multi-modal distribution over the predicted future trajectories based on the maneuver-specific anchors. We evaluate our model using the public RounD dataset and the experiment results show the effectiveness of the proposed maneuver-based anchor regression in improving prediction accuracy, reducing the average RMSE to 28% less than the best baseline. Our code is available at https://github.com/m-hasan-n/roundabout.

arXiv:2104.11028

Semi-Supervised Segmentation of Concrete Aggregate Using Consensus Regularisation and Prior Guidance

In order to leverage and profit from unlabelled data, semi-supervised frameworks for semantic segmentation based on consistency training have been proven to be powerful tools to significantly improve the performance of purely supervised segmentation learning. However, the consensus principle behind consistency training has at least one drawback, which we identify in this paper: imbalanced label distributions within the data. To overcome the limitations of standard consistency training, we propose a novel semi-supervised framework for semantic segmentation, introducing additional losses based on prior knowledge. Specifically, we propose a light-weight architecture consisting of a shared encoder and a main decoder, which is trained in a supervised manner. An auxiliary decoder is added as additional branch in order to make use of unlabelled data based on consensus training, and we add additional constraints derived from prior information on the class distribution and on auto-encoder regularisation. Experiments performed on our "concrete aggregate dataset" presented in this paper demonstrate the effectiveness of the proposed approach, outperforming the segmentation results achieved by purely supervised segmentation and standard consistency training.

arXiv:2104.10328

Label-Synchronous Speech-to-Text Alignment for ASR Using Forward and Backward Transformers

This paper proposes a novel label-synchronous speech-to-text alignment technique for automatic speech recognition (ASR). The speech-to-text alignment is a problem of splitting long audio recordings with un-aligned transcripts into utterance-wise pairs of speech and text. Unlike conventional methods based on frame-synchronous prediction, the proposed method re-defines the speech-to-text alignment as a label-synchronous text mapping problem. This enables an accurate alignment benefiting from the strong inference ability of the state-of-the-art attention-based encoder-decoder models, which cannot be applied to the conventional methods. Two different Transformer models named forward Transformer and backward Transformer are respectively used for estimating an initial and final tokens of a given speech segment based on end-of-sentence prediction with teacher-forcing. Experiments using the corpus of spontaneous Japanese (CSJ) demonstrate that the proposed method provides an accurate utterance-wise alignment, that matches the manually annotated alignment with as few as 0.2% errors. It is also confirmed that a Transformer-based hybrid CTC/Attention ASR model using the aligned speech and text pairs as an additional training data reduces character error rates relatively up to 59.0%, which is significantly better than 39.0% reduction by a conventional alignment method based on connectionist temporal classification model.

arXiv:2104.10611공식 코드 · Papers with Code

FourierNets enable the design of highly non-local optical encoders for computational imaging

Differentiable simulations of optical systems can be combined with deep learning-based reconstruction networks to enable high performance computational imaging via end-to-end (E2E) optimization of both the optical encoder and the deep decoder. This has enabled imaging applications such as 3D localization microscopy, depth estimation, and lensless photography via the optimization of local optical encoders. More challenging computational imaging applications, such as 3D snapshot microscopy which compresses 3D volumes into single 2D images, require a highly non-local optical encoder. We show that existing deep network decoders have a locality bias which prevents the optimization of such highly non-local optical encoders. We address this with a decoder based on a shallow neural network architecture using global kernel Fourier convolutional neural networks (FourierNets). We show that FourierNets surpass existing deep network based decoders at reconstructing photographs captured by the highly non-local DiffuserCam optical encoder. Further, we show that FourierNets enable E2E optimization of highly non-local optical encoders for 3D snapshot microscopy. By combining FourierNets with a large-scale multi-GPU differentiable optical simulation, we are able to optimize non-local optical encoders 170$\times$ to 7372$\times$ larger than prior state of the art, and demonstrate the potential for ROI-type specific optical encoding with a programmable microscope.

arXiv:2104.09752

Flow-based Video Segmentation for Human Head and Shoulders

Video segmentation for the human head and shoulders is essential in creating elegant media for videoconferencing and virtual reality applications. The main challenge is to process high-quality background subtraction in a real-time manner and address the segmentation issues under motion blurs, e.g., shaking the head or waving hands during conference video. To overcome the motion blur problem in video segmentation, we propose a novel flow-based encoder-decoder network (FUNet) that combines both traditional Horn-Schunck optical-flow estimation technique and convolutional neural networks to perform robust real-time video segmentation. We also introduce a video and image segmentation dataset: ConferenceVideoSegmentationDataset. Code and pre-trained models are available on our GitHub repository: \url{https://github.com/kuangzijian/Flow-Based-Video-Matting}.

arXiv:2104.09715

AdaSpeech 2: Adaptive Text to Speech with Untranscribed Data

Text to speech (TTS) is widely used to synthesize personal voice for a target speaker, where a well-trained source TTS model is fine-tuned with few paired adaptation data (speech and its transcripts) on this target speaker. However, in many scenarios, only untranscribed speech data is available for adaptation, which brings challenges to the previous TTS adaptation pipelines (e.g., AdaSpeech). In this paper, we develop AdaSpeech 2, an adaptive TTS system that only leverages untranscribed speech data for adaptation. Specifically, we introduce a mel-spectrogram encoder to a well-trained TTS model to conduct speech reconstruction, and at the same time constrain the output sequence of the mel-spectrogram encoder to be close to that of the original phoneme encoder. In adaptation, we use untranscribed speech data for speech reconstruction and only fine-tune the TTS decoder. AdaSpeech 2 has two advantages: 1) Pluggable: our system can be easily applied to existing trained TTS models without re-training. 2) Effective: our system achieves on-par voice quality with the transcribed TTS adaptation (e.g., AdaSpeech) with the same amount of untranscribed data, and achieves better voice quality than previous untranscribed adaptation methods. Synthesized speech samples can be found at https://speechresearch.github.io/adaspeech2/.

arXiv:2104.09480

FPGA Implementations of Layered MinSum LDPC Decoders Using RCQ Message Passing

Non-uniform message quantization techniques such as reconstruction-computation-quantization (RCQ) improve error-correction performance and decrease hardware complexity of low-density parity-check (LDPC) decoders that use a flooding schedule. Layered MinSum RCQ (L-msRCQ) enables message quantization to be utilized for layered decoders and irregular LDPC codes. We investigate field-programmable gate array (FPGA) implementations of L-msRCQ decoders. Three design methods for message quantization are presented, which we name the Lookup, Broadcast, and Dribble methods. The decoding performance and hardware complexity of these schemes are compared to a layered offset MinSum (OMS) decoder. Simulation results on a (16384, 8192) protograph-based raptor-like (PBRL) LDPC code show that a 4-bit L-msRCQ decoder using the Broadcast method can achieve a 0.03 dB improvement in error-correction performance while using 12% fewer registers than the OMS decoder. A Broadcast-based 3-bit L-msRCQ decoder uses 15% fewer lookup tables, 18% fewer registers, and 13% fewer routed nets than the OMS decoder, but results in a 0.09 dB loss in performance.

arXiv:2104.09103

Conditional Coding and Variable Bitrate for Practical Learned Video Coding

This paper introduces a practical learned video codec. Conditional coding and quantization gain vectors are used to provide flexibility to a single encoder/decoder pair, which is able to compress video sequences at a variable bitrate. The flexibility is leveraged at test time by choosing the rate and GOP structure to optimize a rate-distortion cost. Using the CLIC21 video test conditions, the proposed approach shows performance on par with HEVC.

arXiv:2104.08400공식 코드 · Papers with Code

Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs

Abstractive conversation summarization has received much attention recently. However, these generated summaries often suffer from insufficient, redundant, or incorrect content, largely due to the unstructured and complex characteristics of human-human interactions. To this end, we propose to explicitly model the rich structures in conversations for more precise and accurate conversation summarization, by first incorporating discourse relations between utterances and action triples ("who-doing-what") in utterances through structured graphs to better encode conversations, and then designing a multi-granularity decoder to generate summaries by combining all levels of information. Experiments show that our proposed models outperform state-of-the-art methods and generalize well in other domains in terms of both automatic evaluations and human judgments. We have publicly released our code at https://github.com/GT-SALT/Structure-Aware-BART.

arXiv:2104.08857

Emotion-Regularized Conditional Variational Autoencoder for Emotional Response Generation

This paper presents an emotion-regularized conditional variational autoencoder (Emo-CVAE) model for generating emotional conversation responses. In conventional CVAE-based emotional response generation, emotion labels are simply used as additional conditions in prior, posterior and decoder networks. Considering that emotion styles are naturally entangled with semantic contents in the language space, the Emo-CVAE model utilizes emotion labels to regularize the CVAE latent space by introducing an extra emotion prediction network. In the training stage, the estimated latent variables are required to predict the emotion labels and token sequences of the input responses simultaneously. Experimental results show that our Emo-CVAE model can learn a more informative and structured latent space than a conventional CVAE model and output responses with better content and emotion performance than baseline CVAE and sequence-to-sequence (Seq2Seq) models.

arXiv:2104.08757공식 코드 · Papers with Code

Zero-shot Cross-lingual Transfer of Neural Machine Translation with Multilingual Pretrained Encoders

Previous work mainly focuses on improving cross-lingual transfer for NLU tasks with a multilingual pretrained encoder (MPE), or improving the performance on supervised machine translation with BERT. However, it is under-explored that whether the MPE can help to facilitate the cross-lingual transferability of NMT model. In this paper, we focus on a zero-shot cross-lingual transfer task in NMT. In this task, the NMT model is trained with parallel dataset of only one language pair and an off-the-shelf MPE, then it is directly tested on zero-shot language pairs. We propose SixT, a simple yet effective model for this task. SixT leverages the MPE with a two-stage training schedule and gets further improvement with a position disentangled encoder and a capacity-enhanced decoder. Using this method, SixT significantly outperforms mBART, a pretrained multilingual encoder-decoder model explicitly designed for NMT, with an average improvement of 7.1 BLEU on zero-shot any-to-English test sets across 14 source languages. Furthermore, with much less training computation cost and training data, our model achieves better performance on 15 any-to-English test sets than CRISS and m2m-100, two strong multilingual NMT baselines.

arXiv:2104.08409

Model-Based Deep Autoencoder Networks for Nonlinear Hyperspectral Unmixing

Autoencoder (AEC) networks have recently emerged as a promising approach to perform unsupervised hyperspectral unmixing (HU) by associating the latent representations with the abundances, the decoder with the mixing model and the encoder with its inverse. AECs are especially appealing for nonlinear HU since they lead to unsupervised and model-free algorithms. However, existing approaches fail to explore the fact that the encoder should invert the mixing process, which might reduce their robustness. In this paper, we propose a model-based AEC for nonlinear HU by considering the mixing model a nonlinear fluctuation over a linear mixture. Differently from previous works, we show that this restriction naturally imposes a particular structure to both the encoder and to the decoder networks. This introduces prior information in the AEC without reducing the flexibility of the mixing model. Simulations with synthetic and real data indicate that the proposed strategy improves nonlinear HU.

arXiv:2104.09453공식 코드 · Papers with Code

Inharmonious Region Localization

The advance of image editing techniques allows users to create artistic works, but the manipulated regions may be incompatible with the background. Localizing the inharmonious region is an appealing yet challenging task. Realizing that this task requires effective aggregation of multi-scale contextual information and suppression of redundant information, we design novel Bi-directional Feature Integration (BFI) block and Global-context Guided Decoder (GGD) block to fuse multi-scale features in the encoder and decoder respectively. We also employ Mask-guided Dual Attention (MDA) block between the encoder and decoder to suppress the redundant information. Experiments on the image harmonization dataset demonstrate that our method achieves competitive performance for inharmonious region localization. The source code is available at https://github.com/bcmi/DIRL.

arXiv:2104.09134

Restoration of Video Frames from a Single Blurred Image with Motion Understanding

We propose a novel framework to generate clean video frames from a single motion-blurred image. While a broad range of literature focuses on recovering a single image from a blurred image, in this work, we tackle a more challenging task i.e. video restoration from a blurred image. We formulate video restoration from a single blurred image as an inverse problem by setting clean image sequence and their respective motion as latent factors, and the blurred image as an observation. Our framework is based on an encoder-decoder structure with spatial transformer network modules to restore a video sequence and its underlying motion in an end-to-end manner. We design a loss function and regularizers with complementary properties to stabilize the training and analyze variant models of the proposed network. The effectiveness and transferability of our network are highlighted through a large set of experiments on two different types of datasets: camera rotation blurs generated from panorama scenes and dynamic motion blurs in high speed videos.

arXiv:2104.08554

Objective-Dependent Uncertainty Driven Retinal Vessel Segmentation

From diagnosing neovascular diseases to detecting white matter lesions, accurate tiny vessel segmentation in fundus images is critical. Promising results for accurate vessel segmentation have been known. However, their effectiveness in segmenting tiny vessels is still limited. In this paper, we study retinal vessel segmentation by incorporating tiny vessel segmentation into our framework for the overall accurate vessel segmentation. To achieve this, we propose a new deep convolutional neural network (CNN) which divides vessel segmentation into two separate objectives. Specifically, we consider the overall accurate vessel segmentation and tiny vessel segmentation as two individual objectives. Then, by exploiting the objective-dependent (homoscedastic) uncertainty, we enable the network to learn both objectives simultaneously. Further, to improve the individual objectives, we propose: (a) a vessel weight map based auxiliary loss for enhancing tiny vessel connectivity (i.e., improving tiny vessel segmentation), and (b) an enhanced encoder-decoder architecture for improved localization (i.e., for accurate vessel segmentation). Using 3 public retinal vessel segmentation datasets (CHASE_DB1, DRIVE, and STARE), we verify the superiority of our proposed framework in segmenting tiny vessels (8.3% average improvement in sensitivity) while achieving better area under the receiver operating characteristic curve (AUC) compared to state-of-the-art methods.

arXiv:2104.08838공식 코드 · Papers with Code

Multi-scale Self-calibrated Network for Image Light Source Transfer

Image light source transfer (LLST), as the most challenging task in the domain of image relighting, has attracted extensive attention in recent years. In the latest research, LLST is decomposed three sub-tasks: scene reconversion, shadow estimation, and image re-rendering, which provides a new paradigm for image relighting. However, many problems for scene reconversion and shadow estimation tasks, including uncalibrated feature information and poor semantic information, are still unresolved, thereby resulting in insufficient feature representation. In this paper, we propose novel down-sampling feature self-calibrated block (DFSB) and up-sampling feature self-calibrated block (UFSB) as the basic blocks of feature encoder and decoder to calibrate feature representation iteratively because the LLST is similar to the recalibration of image light source. In addition, we fuse the multi-scale features of the decoder in scene reconversion task to further explore and exploit more semantic information, thereby providing more accurate primary scene structure for image re-rendering. Experimental results in the VIDIT dataset show that the proposed approach significantly improves the performance for LLST.

arXiv:2104.08109

Split Learning Meets Koopman Theory for Wireless Remote Monitoring and Prediction

Remote state monitoring over wireless is envisaged to play a pivotal role in enabling beyond 5G applications ranging from remote drone control to remote surgery. One key challenge is to identify the system dynamics that is non-linear with a large dimensional state. To obviate this issue, in this article we propose to train an autoencoder whose encoder and decoder are split and stored at a state sensor and its remote observer, respectively. This autoencoder not only decreases the remote monitoring payload size by reducing the state representation dimension, but also learns the system dynamics by lifting it via a Koopman operator, thereby allowing the observer to locally predict future states after training convergence. Numerical results under a non-linear cart-pole environment demonstrate that the proposed split learning of a Koopman autoencoder can locally predict future states, and the prediction accuracy increases with the representation dimension and transmission power.

arXiv:2104.07787

Rethinking Text Line Recognition Models

In this paper, we study the problem of text line recognition. Unlike most approaches targeting specific domains such as scene-text or handwritten documents, we investigate the general problem of developing a universal architecture that can extract text from any image, regardless of source or input modality. We consider two decoder families (Connectionist Temporal Classification and Transformer) and three encoder modules (Bidirectional LSTMs, Self-Attention, and GRCLs), and conduct extensive experiments to compare their accuracy and performance on widely used public datasets of scene and handwritten text. We find that a combination that so far has received little attention in the literature, namely a Self-Attention encoder coupled with the CTC decoder, when compounded with an external language model and trained on both public and internal data, outperforms all the others in accuracy and computational complexity. Unlike the more common Transformer-based models, this architecture can handle inputs of arbitrary length, a requirement for universal line recognition. Using an internal dataset collected from multiple sources, we also expose the limitations of current public datasets in evaluating the accuracy of line recognizers, as the relatively narrow image width and sequence length distributions do not allow to observe the quality degradation of the Transformer approach when applied to the transcription of long lines.

논문 ID: document/9052912

Coupled Training of Sequence-to-Sequence Models for Accented Speech Recognition

Accented speech poses significant challenges for state-of-the-art automatic speech recognition (ASR) systems. Accent is a property of speech that lasts throughout an utterance in varying degrees of strength. This makes it hard to isolate the influence of accent on individual speech sounds. We propose coupled training for encoder-decoder ASR models that acts on pairs of utterances corresponding to the same text spoken by speakers with different accents. This training regime introduces an L2 loss between the attention-weighted representations corresponding to pairs of utterances with the same text, thus acting as a regularizer and encouraging representations from the encoder to be more accent-invariant. We focus on recognizing accented English samples from the Mozilla Common Voice corpus. We obtain significant error rate reductions on accented samples from a large set of diverse accents using coupled training. We also show consistent improvements in performance on heavily accented samples (as determined by a standalone accent classifier).

arXiv:2104.07877공식 코드 · Papers with Code

A De-raining semantic segmentation network for real-time foreground segmentation

Few researches have been proposed specifically for real-time semantic segmentation in rainy environments. However, the demand in this area is huge and it is challenging for lightweight networks. Therefore, this paper proposes a lightweight network which is specially designed for the foreground segmentation in rainy environments, named De-raining Semantic Segmentation Network (DRSNet). By analyzing the characteristics of raindrops, the MultiScaleSE Block is targetedly designed to encode the input image, it uses multi-scale dilated convolutions to increase the receptive field, and SE attention mechanism to learn the weights of each channels. In order to combine semantic information between different encoder and decoder layers, it is proposed to use Asymmetric Skip, that is, the higher semantic layer of encoder employs bilinear interpolation and the output passes through pointwise convolution, then added element-wise to the lower semantic layer of decoder. According to the control experiments, the performances of MultiScaleSE Block and Asymmetric Skip compared with SEResNet18 and Symmetric Skip respectively are improved to a certain degree on the Foreground Accuracy index. The parameters and the floating point of operations (FLOPs) of DRSNet is only 0.54M and 0.20GFLOPs separately. The state-of-the-art results and real-time performances are achieved on both the UESTC all-day Scenery add rain (UAS-add-rain) and the Baidu People Segmentation add rain (BPS-add-rain) benchmarks with the input sizes of 192*128, 384*256 and 768*512. The speed of DRSNet exceeds all the networks within 1GFLOPs, and Foreground Accuracy index is also the best among the similar magnitude networks on both benchmarks.