PyTorchKR Papers

최신 논문

총 9,339편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2203.02181공식 코드 · Papers with Code

MANNER: Multi-view Attention Network for Noise Erasure

In the field of speech enhancement, time domain methods have difficulties in achieving both high performance and efficiency. Recently, dual-path models have been adopted to represent long sequential features, but they still have limited representations and poor memory efficiency. In this study, we propose Multi-view Attention Network for Noise ERasure (MANNER) consisting of a convolutional encoder-decoder with a multi-view attention block, applied to the time-domain signals. MANNER efficiently extracts three different representations from noisy speech and estimates high-quality clean speech. We evaluated MANNER on the VoiceBank-DEMAND dataset in terms of five objective speech quality metrics. Experimental results show that MANNER achieves state-of-the-art performance while efficiently processing noisy speech.

arXiv:2203.02094공식 코드 · Papers with Code

LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models

The Transformer architecture is ubiquitously used as the building block of large-scale autoregressive language models. However, finding architectures with the optimal trade-off between task performance (perplexity) and hardware constraints like peak memory utilization and latency is non-trivial. This is exacerbated by the proliferation of various hardware. We leverage the somewhat surprising empirical observation that the number of decoder parameters in autoregressive Transformers has a high rank correlation with task performance, irrespective of the architecture topology. This observation organically induces a simple Neural Architecture Search (NAS) algorithm that uses decoder parameters as a proxy for perplexity without need for any model training. The search phase of our training-free algorithm, dubbed Lightweight Transformer Search (LTS), can be run directly on target devices since it does not require GPUs. Using on-target-device measurements, LTS extracts the Pareto-frontier of perplexity versus any hardware performance cost. We evaluate LTS on diverse devices from ARM CPUs to NVIDIA GPUs and two popular autoregressive Transformer backbones: GPT-2 and Transformer-XL. Results show that the perplexity of 16-layer GPT-2 and Transformer-XL can be achieved with up to 1.5x, 2.5x faster runtime and 1.2x, 2.0x lower peak memory utilization. When evaluated in zero and one-shot settings, LTS Pareto-frontier models achieve higher average accuracy compared to the 350M parameter OPT across 14 tasks, with up to 1.6x lower latency. LTS extracts the Pareto-frontier in under 3 hours while running on a commodity laptop. We effectively remove the carbon footprint of hundreds of GPU hours of training during search, offering a strong simple baseline for future NAS methods in autoregressive language modeling.

arXiv:2203.02057

Interpretable Latent Variables in Deep State Space Models

We introduce a new version of deep state-space models (DSSMs) that combines a recurrent neural network with a state-space framework to forecast time series data. The model estimates the observed series as functions of latent variables that evolve non-linearly through time. Due to the complexity and non-linearity inherent in DSSMs, previous works on DSSMs typically produced latent variables that are very difficult to interpret. Our paper focus on producing interpretable latent parameters with two key modifications. First, we simplify the predictive decoder by restricting the response variables to be a linear transformation of the latent variables plus some noise. Second, we utilize shrinkage priors on the latent variables to reduce redundancy and improve robustness. These changes make the latent variables much easier to understand and allow us to interpret the resulting latent variables as random effects in a linear mixed model. We show through two public benchmark datasets the resulting model improves forecasting performances.

arXiv:2203.02055

Deep Latent-Variable Models for Text Generation

Text generation aims to produce human-like natural language output for down-stream tasks. It covers a wide range of applications like machine translation, document summarization, dialogue generation and so on. Recently deep neural network-based end-to-end architectures have been widely adopted. The end-to-end approach conflates all sub-modules, which used to be designed by complex handcrafted rules, into a holistic encode-decode architecture. Given enough training data, it is able to achieve state-of-the-art performance yet avoiding the need of language/domain-dependent knowledge. Nonetheless, deep learning models are known to be extremely data-hungry, and text generated from them usually suffer from low diversity, interpretability and controllability. As a result, it is difficult to trust the output from them in real-life applications. Deep latent-variable models, by specifying the probabilistic distribution over an intermediate latent process, provide a potential way of addressing these problems while maintaining the expressive power of deep neural networks. This dissertation presents how deep latent-variable models can improve over the standard encoder-decoder model for text generation.

arXiv:2203.02286공식 코드 · Papers with Code

Semi-parametric Makeup Transfer via Semantic-aware Correspondence

The large discrepancy between the source non-makeup image and the reference makeup image is one of the key challenges in makeup transfer. Conventional approaches for makeup transfer either learn disentangled representation or perform pixel-wise correspondence in a parametric way between two images. We argue that non-parametric techniques have a high potential for addressing the pose, expression, and occlusion discrepancies. To this end, this paper proposes a \textbf{S}emi-\textbf{p}arametric \textbf{M}akeup \textbf{T}ransfer (SpMT) method, which combines the reciprocal strengths of non-parametric and parametric mechanisms. The non-parametric component is a novel \textbf{S}emantic-\textbf{a}ware \textbf{C}orrespondence (SaC) module that explicitly reconstructs content representation with makeup representation under the strong constraint of component semantics. The reconstructed representation is desired to preserve the spatial and identity information of the source image while "wearing" the makeup of the reference image. The output image is synthesized via a parametric decoder that draws on the reconstructed representation. Extensive experiments demonstrate the superiority of our method in terms of visual quality, robustness, and flexibility. Code and pre-trained model are available at \url{https://github.com/AnonymScholar/SpMT.

arXiv:2203.02113공식 코드 · Papers with Code

FS-COCO: Towards Understanding of Freehand Sketches of Common Objects in Context

We advance sketch research to scenes with the first dataset of freehand scene sketches, FS-COCO. With practical applications in mind, we collect sketches that convey scene content well but can be sketched within a few minutes by a person with any sketching skills. Our dataset comprises 10,000 freehand scene vector sketches with per point space-time information by 100 non-expert individuals, offering both object- and scene-level abstraction. Each sketch is augmented with its text description. Using our dataset, we study for the first time the problem of fine-grained image retrieval from freehand scene sketches and sketch captions. We draw insights on: (i) Scene salience encoded in sketches using the strokes temporal order; (ii) Performance comparison of image retrieval from a scene sketch and an image caption; (iii) Complementarity of information in sketches and image captions, as well as the potential benefit of combining the two modalities. In addition, we extend a popular vector sketch LSTM-based encoder to handle sketches with larger complexity than was supported by previous work. Namely, we propose a hierarchical sketch decoder, which we leverage at a sketch-specific "pre-text" task. Our dataset enables for the first time research on freehand scene sketch understanding and its practical applications.

arXiv:2203.01767

Estimating the HEVC Decoding Energy Using the Decoder Processing Time

This paper presents a method to accurately estimate the required decoding energy for a given HEVC software decoding solution. We show that the decoder's processing time as returned by common C++ and UNIX functions is a highly suitable parameter to obtain valid estimations for the actual decoding energy. We verify this hypothesis by performing an exhaustive measurement series using different decoder setups and video bit streams. Our findings can be used by developers and researchers in the search for new energy saving video compression algorithms.

arXiv:2203.01765

Joint Optimization of Rate, Distortion, and Decoding Energy for HEVC Intraframe Coding

This paper presents a novel algorithm that aims at minimizing the required decoding energy by exploiting a general energy model for HEVC-decoder solutions. We incorporate the energy model into the HEVC encoder such that it is capable of constructing a bit stream whose decoding process consumes less energy than the decoding process of a conventional bit stream. To achieve this, we propose to extend the traditional Rate-Distortion-Optimization scheme to a Decoding-Energy-Rate-Distortion approach. To obtain fast encoding decisions in the optimization process, we derive a fixed relation between the quantization parameter and the Lagrange multiplier for energy optimization. Our experiments show that this concept is applicable for intraframe-coded videos and that for local playback as well as online streaming scenarios, up to 15% of the decoding energy can be saved at the expense of a bitrate increase of approximately the same magnitude.

arXiv:2203.01755

Modeling the Energy Consumption of HEVC Intra Decoding

Battery life is one of the major limitations to mobile device use, which makes research on energy efficient soft- and hardware an important task. This paper investigates the energy required by a CPU when decoding compressed bitstream videos on mobile platforms. A model is derived that describes the energy consumption of the new HEVC decoder for intra coded videos. We show that the relative estimation error of the model is smaller than 3.2% and that the model can be used to build encoders aiming at minimizing decoding energy.

arXiv:2203.01601공식 코드 · Papers with Code

Syntax-Aware Network for Handwritten Mathematical Expression Recognition

Handwritten mathematical expression recognition (HMER) is a challenging task that has many potential applications. Recent methods for HMER have achieved outstanding performance with an encoder-decoder architecture. However, these methods adhere to the paradigm that the prediction is made "from one character to another", which inevitably yields prediction errors due to the complicated structures of mathematical expressions or crabbed handwritings. In this paper, we propose a simple and efficient method for HMER, which is the first to incorporate syntax information into an encoder-decoder network. Specifically, we present a set of grammar rules for converting the LaTeX markup sequence of each expression into a parsing tree; then, we model the markup sequence prediction as a tree traverse process with a deep neural network. In this way, the proposed method can effectively describe the syntax context of expressions, alleviating the structure prediction errors of HMER. Experiments on three benchmark datasets demonstrate that our method achieves better recognition performance than prior arts. To further validate the effectiveness of our method, we create a large-scale dataset consisting of 100k handwritten mathematical expression images acquired from ten thousand writers. The source code, new dataset, and pre-trained models of this work will be publicly available.

arXiv:2203.01594

A Deep Neural Framework for Image Caption Generation Using GRU-Based Attention Mechanism

Image captioning is a fast-growing research field of computer vision and natural language processing that involves creating text explanations for images. This study aims to develop a system that uses a pre-trained convolutional neural network (CNN) to extract features from an image, integrates the features with an attention mechanism, and creates captions using a recurrent neural network (RNN). To encode an image into a feature vector as graphical attributes, we employed multiple pre-trained convolutional neural networks. Following that, a language model known as GRU is chosen as the decoder to construct the descriptive sentence. In order to increase performance, we merge the Bahdanau attention model with GRU to allow learning to be focused on a specific portion of the image. On the MSCOCO dataset, the experimental results achieve competitive performance against state-of-the-art approaches.

arXiv:2203.01502공식 코드 · Papers with Code

NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation

Estimating the accurate depth from a single image is challenging since it is inherently ambiguous and ill-posed. While recent works design increasingly complicated and powerful networks to directly regress the depth map, we take the path of CRFs optimization. Due to the expensive computation, CRFs are usually performed between neighborhoods rather than the whole graph. To leverage the potential of fully-connected CRFs, we split the input into windows and perform the FC-CRFs optimization within each window, which reduces the computation complexity and makes FC-CRFs feasible. To better capture the relationships between nodes in the graph, we exploit the multi-head attention mechanism to compute a multi-head potential function, which is fed to the networks to output an optimized depth map. Then we build a bottom-up-top-down structure, where this neural window FC-CRFs module serves as the decoder, and a vision transformer serves as the encoder. The experiments demonstrate that our method significantly improves the performance across all metrics on both the KITTI and NYUv2 datasets, compared to previous methods. Furthermore, the proposed method can be directly applied to panorama images and outperforms all previous panorama methods on the MatterPort3D dataset. Project page: https://weihaosky.github.io/newcrfs.

논문 ID: 2022.10238

StaSiS-Net: a stacked and siamese stereo network for depth reconstruction in modern 3D laparoscopy.

Accurate and real-time methodologies for a non-invasive three-dimensional representa-tion and reconstruction of internal patient structures is one of the main research fieldsin computer-assisted surgery and endoscopy. Mono and stereo endoscopic images ofsoft tissues are converted into a three-dimensional representation by the estimation ofdepth maps. However, automatic, detailed, accurate and robust depth map estimationis a challenging problem which, moreover, is strictly dependent on a robust estimateof the disparity map. Many traditional algorithms are often inefficient or not accu-rate. In this work, novel self-supervised stacked and Siamese encoder/decoder neuralnetworks are proposed to compute accurate disparity maps for 3D laparoscopy depthreconstructions. These networks produce disparities in real-time on standard GPU-equipped desktop computers and after, with a minimal parameter configuration theirdepth reconstruction. We compare their performance on three different public datasetsand on a new challenging simulated dataset and they outperform state-of-the-art monoand stereo depth estimation methods. Extensive robustness and sensitivity analyses onmore than 30 000 frames has been performed. This work leads to important improve-ments in mono and stereo real-time depth estimations of soft tissues and organs with avery low average mean absolute disparity reconstruction error with respect to groundtruth.

arXiv:2203.01017공식 코드 · Papers with Code

TableFormer: Table Structure Understanding with Transformers

Tables organize valuable content in a concise and compact representation. This content is extremely valuable for systems such as search engines, Knowledge Graph's, etc, since they enhance their predictive capabilities. Unfortunately, tables come in a large variety of shapes and sizes. Furthermore, they can have complex column/row-header configurations, multiline rows, different variety of separation lines, missing entries, etc. As such, the correct identification of the table-structure from an image is a non-trivial task. In this paper, we present a new table-structure identification model. The latter improves the latest end-to-end deep learning model (i.e. encoder-dual-decoder from PubTabNet) in two significant ways. First, we introduce a new object detection decoder for table-cells. In this way, we can obtain the content of the table-cells from programmatic PDF's directly from the PDF source and avoid the training of the custom OCR decoders. This architectural change leads to more accurate table-content extraction and allows us to tackle non-english tables. Second, we replace the LSTM decoders with transformer based decoders. This upgrade improves significantly the previous state-of-the-art tree-editing-distance-score (TEDS) from 91% to 98.5% on simple tables and from 88.7% to 95% on complex tables.

arXiv:2203.00960

Aggregated Pyramid Vision Transformer: Split-transform-merge Strategy for Image Recognition without Convolutions

With the achievements of Transformer in the field of natural language processing, the encoder-decoder and the attention mechanism in Transformer have been applied to computer vision. Recently, in multiple tasks of computer vision (image classification, object detection, semantic segmentation, etc.), state-of-the-art convolutional neural networks have introduced some concepts of Transformer. This proves that Transformer has a good prospect in the field of image recognition. After Vision Transformer was proposed, more and more works began to use self-attention to completely replace the convolutional layer. This work is based on Vision Transformer, combined with the pyramid architecture, using Split-transform-merge to propose the group encoder and name the network architecture Aggregated Pyramid Vision Transformer (APVT). We perform image classification tasks on the CIFAR-10 dataset and object detection tasks on the COCO 2017 dataset. Compared with other network architectures that use Transformer as the backbone, APVT has excellent results while reducing the computational cost. We hope this improved strategy can provide a reference for future Transformer research in computer vision.

arXiv:2203.00860

D^2ETR: Decoder-Only DETR with Computationally Efficient Cross-Scale Attention

DETR is the first fully end-to-end detector that predicts a final set of predictions without post-processing. However, it suffers from problems such as low performance and slow convergence. A series of works aim to tackle these issues in different ways, but the computational cost is yet expensive due to the sophisticated encoder-decoder architecture. To alleviate this issue, we propose a decoder-only detector called D^2ETR. In the absence of encoder, the decoder directly attends to the fine-fused feature maps generated by the Transformer backbone with a novel computationally efficient cross-scale attention module. D^2ETR demonstrates low computational complexity and high detection accuracy in evaluations on the COCO benchmark, outperforming DETR and its variants.

arXiv:2203.01305공식 코드 · Papers with Code

DN-DETR: Accelerate DETR Training by Introducing Query DeNoising

We present in this paper a novel denoising training method to speedup DETR (DEtection TRansformer) training and offer a deepened understanding of the slow convergence issue of DETR-like methods. We show that the slow convergence results from the instability of bipartite graph matching which causes inconsistent optimization goals in early training stages. To address this issue, except for the Hungarian loss, our method additionally feeds ground-truth bounding boxes with noises into Transformer decoder and trains the model to reconstruct the original boxes, which effectively reduces the bipartite graph matching difficulty and leads to a faster convergence. Our method is universal and can be easily plugged into any DETR-like methods by adding dozens of lines of code to achieve a remarkable improvement. As a result, our DN-DETR results in a remarkable improvement ($+1.9$AP) under the same setting and achieves the best result (AP $43.4$ and $48.6$ with $12$ and $50$ epochs of training respectively) among DETR-like methods with ResNet-$50$ backbone. Compared with the baseline under the same setting, DN-DETR achieves comparable performance with $50\%$ training epochs. Code is available at \url{https://github.com/FengLi-ust/DN-DETR}.

논문 ID: document/9684717

TR-MISR: Multiimage Super-Resolution Based on Feature Fusion With Transformers

Multiimage super-resolution (MISR), as one of the most promising directions in remote sensing, has become a needy technique in the satellite market. A sequence of images collected by satellites often has plenty of views and a long time span, so integrating multiple low-resolution views into a high-resolution image with details emerges as a challenging problem. However, most MISR methods based on deep learning cannot make full use of multiple images. Their fusion modules are incapable of adapting to an image sequence with weak temporal correlations well. To cope with these problems, we propose a novel end-to-end framework called TR-MISR. It consists of three parts: An encoder based on residual blocks, a transformer-based fusion module, and a decoder based on subpixel convolution. Specifically, by rearranging multiple feature maps into vectors, the fusion module can assign dynamic attention to the same area of different satellite images simultaneously. In addition, TR-MISR adopts an additional learnable embedding vector that fuses these vectors to restore the details to the greatest extent.TR-MISR has successfully applied the transformer to MISR tasks for the first time, notably reducing the difficulty of training the transformer by ignoring the spatial relations of image patches. Extensive experiments performed on the PROBA-V Kelvin dataset demonstrate the superiority of the proposed model that provides an effective method for transformers in other low-level vision tasks.

arXiv:2203.00360

Non-linear manifold ROM with Convolutional Autoencoders and Reduced Over-Collocation method

Non-affine parametric dependencies, nonlinearities and advection-dominated regimes of the model of interest can result in a slow Kolmogorov n-width decay, which precludes the realization of efficient reduced-order models based on linear subspace approximations. Among the possible solutions, there are purely data-driven methods that leverage autoencoders and their variants to learn a latent representation of the dynamical system, and then evolve it in time with another architecture. Despite their success in many applications where standard linear techniques fail, more has to be done to increase the interpretability of the results, especially outside the training range and not in regimes characterized by an abundance of data. Not to mention that none of the knowledge on the physics of the model is exploited during the predictive phase. In order to overcome these weaknesses, we implement the non-linear manifold method introduced by Carlberg et al [37] with hyper-reduction achieved through reduced over-collocation and teacher-student training of a reduced decoder. We test the methodology on a 2d non-linear conservation law and a 2d shallow water models, and compare the results obtained with a purely data-driven method for which the dynamics is evolved in time with a long-short term memory network.

arXiv:2203.00595공식 코드 · Papers with Code

Parameter estimation for WMTI-Watson model of white matter using encoder-decoder recurrent neural network

Biophysical modelling of the diffusion MRI signal provides estimates of specific microstructural tissue properties. Although nonlinear optimization such as non-linear least squares (NLLS) is the most widespread method for model estimation, it suffers from local minima and high computational cost. Deep Learning approaches are steadily replacing NL fitting, but come with the limitation that the model needs to be retrained for each acquisition protocol and noise level. The White Matter Tract Integrity (WMTI)-Watson model was proposed as an implementation of the Standard Model of diffusion in white matter that estimates model parameters from the diffusion and kurtosis tensors (DKI). Here we proposed a deep learning approach based on the encoder-decoder recurrent neural network (RNN) to increase the robustness and accelerate the parameter estimation of WMTI-Watson. We use an embedding approach to render the model insensitive to potential differences in distributions between training data and experimental data. This RNN-based solver thus has the advantage of being highly efficient in computation and more readily translatable to other datasets, irrespective of acquisition protocol and underlying parameter distributions as long as DKI was pre-computed from the data. In this study, we evaluated the performance of NLLS, the RNN-based method and a multilayer perceptron (MLP) on synthetic and in vivo datasets of rat and human brain. We showed that the proposed RNN-based fitting approach had the advantage of highly reduced computation time over NLLS (from hours to seconds), with similar accuracy and precision but improved robustness, and superior translatability to new datasets over MLP.