PyTorchKR Papers

최신 논문

총 9,642편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2112.01044공식 코드 · Papers with Code

ShuttleNet: Position-aware Fusion of Rally Progress and Player Styles for Stroke Forecasting in Badminton

The increasing demand for analyzing the insights in sports has stimulated a line of productive studies from a variety of perspectives, e.g., health state monitoring, outcome prediction. In this paper, we focus on objectively judging what and where to return strokes, which is still unexplored in turn-based sports. By formulating stroke forecasting as a sequence prediction task, existing works can tackle the problem but fail to model information based on the characteristics of badminton. To address these limitations, we propose a novel Position-aware Fusion of Rally Progress and Player Styles framework (ShuttleNet) that incorporates rally progress and information of the players by two modified encoder-decoder extractors. Moreover, we design a fusion network to integrate rally contexts and contexts of the players by conditioning on information dependency and different positions. Extensive experiments on the badminton dataset demonstrate that ShuttleNet significantly outperforms the state-of-the-art methods and also empirically validates the feasibility of each component in ShuttleNet. On top of that, we provide an analysis scenario for the stroke forecasting problem.

arXiv:2112.01019

Unconstrained Face Sketch Synthesis via Perception-Adaptive Network and A New Benchmark

Face sketch generation has attracted much attention in the field of visual computing. However, existing methods either are limited to constrained conditions or heavily rely on various preprocessing steps to deal with in-the-wild cases. In this paper, we argue that accurately perceiving facial region and facial components is crucial for unconstrained sketch synthesis. To this end, we propose a novel Perception-Adaptive Network (PANet), which can generate high-quality face sketches under unconstrained conditions in an end-to-end scheme. Specifically, our PANet is composed of i) a Fully Convolutional Encoder for hierarchical feature extraction, ii) a Face-Adaptive Perceiving Decoder for extracting potential facial region and handling face variations, and iii) a Component-Adaptive Perceiving Module for facial component aware feature representation learning. To facilitate further researches of unconstrained face sketch synthesis, we introduce a new benchmark termed WildSketch, which contains 800 pairs of face photo-sketch with large variations in pose, expression, ethnic origin, background, and illumination. Extensive experiments demonstrate that the proposed method is capable of achieving state-of-the-art performance under both constrained and unconstrained conditions. Our source codes and the WildSketch benchmark are resealed on the project page http://lingboliu.com/unconstrained_face_sketch.html.

arXiv:2112.00989공식 코드 · Papers with Code

Embedding Decomposition for Artifacts Removal in EEG Signals

Electroencephalogram (EEG) recordings are often contaminated with artifacts. Various methods have been developed to eliminate or weaken the influence of artifacts. However, most of them rely on prior experience for analysis. Here, we propose an deep learning framework to separate neural signal and artifacts in the embedding space and reconstruct the denoised signal, which is called DeepSeparator. DeepSeparator employs an encoder to extract and amplify the features in the raw EEG, a module called decomposer to extract the trend, detect and suppress artifact and a decoder to reconstruct the denoised signal. Besides, DeepSeparator can extract the artifact, which largely increases the model interpretability. The proposed method is tested with a semi-synthetic EEG dataset and a real task-related EEG dataset, suggesting that DeepSeparator outperforms the conventional models in both EOG and EMG artifact removal. DeepSeparator can be extended to multi-channel EEG and data of any length. It may motivate future developments and application of deep learning-based EEG denoising. The code for DeepSeparator is available at https://github.com/ncclabsustech/DeepSeparator.

arXiv:2112.01030공식 코드 · Papers with Code

TransMEF: A Transformer-Based Multi-Exposure Image Fusion Framework using Self-Supervised Multi-Task Learning

In this paper, we propose TransMEF, a transformer-based multi-exposure image fusion framework that uses self-supervised multi-task learning. The framework is based on an encoder-decoder network, which can be trained on large natural image datasets and does not require ground truth fusion images. We design three self-supervised reconstruction tasks according to the characteristics of multi-exposure images and conduct these tasks simultaneously using multi-task learning; through this process, the network can learn the characteristics of multi-exposure images and extract more generalized features. In addition, to compensate for the defect in establishing long-range dependencies in CNN-based architectures, we design an encoder that combines a CNN module with a transformer module. This combination enables the network to focus on both local and global information. We evaluated our method and compared it to 11 competitive traditional and deep learning-based methods on the latest released multi-exposure image fusion benchmark dataset, and our method achieved the best performance in both subjective and objective evaluations.

arXiv:2112.00390공식 코드 · Papers with Code

SegDiff: Image Segmentation with Diffusion Probabilistic Models

Diffusion Probabilistic Methods are employed for state-of-the-art image generation. In this work, we present a method for extending such models for performing image segmentation. The method learns end-to-end, without relying on a pre-trained backbone. The information in the input image and in the current estimation of the segmentation map is merged by summing the output of two encoders. Additional encoding layers and a decoder are then used to iteratively refine the segmentation map, using a diffusion model. Since the diffusion model is probabilistic, it is applied multiple times, and the results are merged into a final segmentation map. The new method produces state-of-the-art results on the Cityscapes validation set, the Vaihingen building segmentation benchmark, and the MoNuSeg dataset.

arXiv:2112.00380

Deep Measurement Updates for Bayes Filters

Measurement update rules for Bayes filters often contain hand-crafted heuristics to compute observation probabilities for high-dimensional sensor data, like images. In this work, we propose the novel approach Deep Measurement Update (DMU) as a general update rule for a wide range of systems. DMU has a conditional encoder-decoder neural network structure to process depth images as raw inputs. Even though the network is trained only on synthetic data, the model shows good performance at evaluation time on real-world data. With our proposed training scheme primed data training , we demonstrate how the DMU models can be trained efficiently to be sensitive to condition variables without having to rely on a stochastic information bottleneck. We validate the proposed methods in multiple scenarios of increasing complexity, beginning with the pose estimation of a single object to the joint estimation of the pose and the internal state of an articulated system. Moreover, we provide a benchmark against Articulated Signed Distance Functions(A-SDF) on the RBO dataset as a baseline comparison for articulation state estimation.

arXiv:2112.00289

Point Cloud Segmentation Using Sparse Temporal Local Attention

Point clouds are a key modality used for perception in autonomous vehicles, providing the means for a robust geometric understanding of the surrounding environment. However despite the sensor outputs from autonomous vehicles being naturally temporal in nature, there is still limited exploration of exploiting point cloud sequences for 3D seman-tic segmentation. In this paper we propose a novel Sparse Temporal Local Attention (STELA) module which aggregates intermediate features from a local neighbourhood in previous point cloud frames to provide a rich temporal context to the decoder. Using the sparse local neighbourhood enables our approach to gather features more flexibly than those which directly match point features, and more efficiently than those which perform expensive global attention over the whole point cloud frame. We achieve a competitive mIoU of 64.3% on the SemanticKitti dataset, and demonstrate significant improvement over the single-frame baseline in our ablation studies.

arXiv:2112.00185

Light Field Implicit Representation for Flexible Resolution Reconstruction

Inspired by the recent advances in implicitly representing signals with trained neural networks, we aim to learn a continuous representation for narrow-baseline 4D light fields. We propose an implicit representation model for 4D light fields which is conditioned on a sparse set of input views. Our model is trained to output the light field values for a continuous range of query spatio-angular coordinates. Given a sparse set of input views, our scheme can super-resolve the input in both spatial and angular domains by flexible factors. consists of a feature extractor and a decoder which are trained on a dataset of light field patches. The feature extractor captures per-pixel features from the input views. These features can be resized to a desired spatial resolution and fed to the decoder along with the query coordinates. This formulation enables us to reconstruct light field views at any desired spatial and angular resolution. Additionally, our network can handle scenarios in which input views are either of low-resolution or with missing pixels. Experiments show that our method achieves state-of-the-art performance for the task of view synthesis while being computationally fast.

arXiv:2112.00180

SpaceEdit: Learning a Unified Editing Space for Open-Domain Image Editing

Recently, large pretrained models (e.g., BERT, StyleGAN, CLIP) have shown great knowledge transfer and generalization capability on various downstream tasks within their domains. Inspired by these efforts, in this paper we propose a unified model for open-domain image editing focusing on color and tone adjustment of open-domain images while keeping their original content and structure. Our model learns a unified editing space that is more semantic, intuitive, and easy to manipulate than the operation space (e.g., contrast, brightness, color curve) used in many existing photo editing softwares. Our model belongs to the image-to-image translation framework which consists of an image encoder and decoder, and is trained on pairs of before- and after-images to produce multimodal outputs. We show that by inverting image pairs into latent codes of the learned editing space, our model can be leveraged for various downstream editing tasks such as language-guided image editing, personalized editing, editing-style clustering, retrieval, etc. We extensively study the unique properties of the editing space in experiments and demonstrate superior performance on the aforementioned tasks.

arXiv:2111.15536

ViSTRA3: Video Coding with Deep Parameter Adaptation and Post Processing

This paper presents a deep learning-based video compression framework (ViSTRA3). The proposed framework intelligently adapts video format parameters of the input video before encoding, subsequently employing a CNN at the decoder to restore their original format and enhance reconstruction quality. ViSTRA3 has been integrated with the H.266/VVC Test Model VTM 14.0, and evaluated under the Joint Video Exploration Team Common Test Conditions. Bj{\o}negaard Delta (BD) measurement results show that the proposed framework consistently outperforms the original VVC VTM, with average BD-rate savings of 1.8% and 3.7% based on the assessment of PSNR and VMAF.

arXiv:2111.15473

New Approaches to Long Document Summarization: Fourier Transform Based Attention in a Transformer Model

In this work, we extensively redesign the newly introduced method of token mixing using Fourier Transforms (FNET) to replace the computationally expensive self-attention mechanism in a full transformer implementation on a long document summarization task (> 512 tokens). As a baseline, we also carried out long document summarization using established methods such as Longformer and Big Bird transformer models that are capable of processing over 8000 tokens and are currently the state of the art methods for these type of problems. The original FNET paper implemented this in an encoder only architecture while abstractive summarization requires both an encoder and a decoder. Since such a pretrained transformer model does not currently exist in the public domain, we decided to implement a full transformer based on this Fourier token mixing approach in an encoder/decoder architecture which we trained starting with Glove embeddings for the individual words in the corpus. We investigated a number of different extensions to the original FNET architecture and evaluated them on their Rouge F1-score performance on a summarization task. All modifications showed better performance on the summarization task than when using the original FNET encoder in a transformer architecture.

arXiv:2111.15640공식 코드 · Papers with Code

Diffusion Autoencoders: Toward a Meaningful and Decodable Representation

Diffusion probabilistic models (DPMs) have achieved remarkable quality in image generation that rivals GANs'. But unlike GANs, DPMs use a set of latent variables that lack semantic meaning and cannot serve as a useful representation for other tasks. This paper explores the possibility of using DPMs for representation learning and seeks to extract a meaningful and decodable representation of an input image via autoencoding. Our key idea is to use a learnable encoder for discovering the high-level semantics, and a DPM as the decoder for modeling the remaining stochastic variations. Our method can encode any image into a two-part latent code, where the first part is semantically meaningful and linear, and the second part captures stochastic details, allowing near-exact reconstruction. This capability enables challenging applications that currently foil GAN-based methods, such as attribute manipulation on real images. We also show that this two-level encoding improves denoising efficiency and naturally facilitates various downstream tasks including few-shot conditional sampling. Please visit our project page: https://Diff-AE.github.io/

arXiv:2111.15309

Deep Auto-encoder with Neural Response

Artificial neural network (ANN) is a versatile tool to study the neural representation in the ventral visual stream, and the knowledge in neuroscience in return inspires ANN models to improve performance in the task. However, it is still unclear how to merge these two directions into a unified framework. In this study, we propose an integrated framework called Deep Autoencoder with Neural Response (DAE-NR), which incorporates information from ANN and the visual cortex to achieve better image reconstruction performance and higher neural representation similarity between biological and artificial neurons. The same visual stimuli (i.e., natural images) are input to both the mice brain and DAE-NR. The encoder of DAE-NR jointly learns the dependencies from neural spike encoding and image reconstruction. For the neural spike encoding task, the features derived from a specific hidden layer of the encoder are transformed by a mapping function to predict the ground-truth neural response under the constraint of image reconstruction. Simultaneously, for the image reconstruction task, the latent representation obtained by the encoder is assigned to a decoder to restore the original image under the guidance of neural information. In DAE-NR, the learning process of encoder, mapping function and decoder are all implicitly constrained by these two tasks. Our experiments demonstrate that if and only if with the joint learning, DAE-NRs can improve the performance of visual image reconstruction and increase the representation similarity between biological neurons and artificial neurons. The DAE-NR offers a new perspective on the integration of computer vision and neuroscience.

arXiv:2111.15174공식 코드 · Papers with Code

CRIS: CLIP-Driven Referring Image Segmentation

Referring image segmentation aims to segment a referent via a natural linguistic expression.Due to the distinct data properties between text and image, it is challenging for a network to well align text and pixel-level features. Existing approaches use pretrained models to facilitate learning, yet separately transfer the language/vision knowledge from pretrained models, ignoring the multi-modal corresponding information. Inspired by the recent advance in Contrastive Language-Image Pretraining (CLIP), in this paper, we propose an end-to-end CLIP-Driven Referring Image Segmentation framework (CRIS). To transfer the multi-modal knowledge effectively, CRIS resorts to vision-language decoding and contrastive learning for achieving the text-to-pixel alignment. More specifically, we design a vision-language decoder to propagate fine-grained semantic information from textual representations to each pixel-level activation, which promotes consistency between the two modalities. In addition, we present text-to-pixel contrastive learning to explicitly enforce the text feature similar to the related pixel-level features and dissimilar to the irrelevances. The experimental results on three benchmark datasets demonstrate that our proposed framework significantly outperforms the state-of-the-art performance without any post-processing. The code will be released.

arXiv:2111.15257

ARTSeg: Employing Attention for Thermal images Semantic Segmentation

The research advancements have made the neural network algorithms deployed in the autonomous vehicle to perceive the surrounding. The standard exteroceptive sensors that are utilized for the perception of the environment are cameras and Lidar. Therefore, the neural network algorithms developed using these exteroceptive sensors have provided the necessary solution for the autonomous vehicle's perception. One major drawback of these exteroceptive sensors is their operability in adverse weather conditions, for instance, low illumination and night conditions. The useability and affordability of thermal cameras in the sensor suite of the autonomous vehicle provide the necessary improvement in the autonomous vehicle's perception in adverse weather conditions. The semantics of the environment benefits the robust perception, which can be achieved by segmenting different objects in the scene. In this work, we have employed the thermal camera for semantic segmentation. We have designed an attention-based Recurrent Convolution Network (RCNN) encoder-decoder architecture named ARTSeg for thermal semantic segmentation. The main contribution of this work is the design of encoder-decoder architecture, which employ units of RCNN for each encoder and decoder block. Furthermore, additive attention is employed in the decoder module to retain high-resolution features and improve the localization of features. The efficacy of the proposed method is evaluated on the available public dataset, showing better performance with other state-of-the-art methods in mean intersection over union (IoU).

arXiv:2111.15015

Neural Attention for Image Captioning: Review of Outstanding Methods

Image captioning is the task of automatically generating sentences that describe an input image in the best way possible. The most successful techniques for automatically generating image captions have recently used attentive deep learning models. There are variations in the way deep learning models with attention are designed. In this survey, we provide a review of literature related to attentive deep learning models for image captioning. Instead of offering a comprehensive review of all prior work on deep image captioning models, we explain various types of attention mechanisms used for the task of image captioning in deep learning models. The most successful deep learning models used for image captioning follow the encoder-decoder architecture, although there are differences in the way these models employ attention mechanisms. Via analysis on performance results from different attentive deep models for image captioning, we aim at finding the most successful types of attention mechanisms in deep models for image captioning. Soft attention, bottom-up attention, and multi-head attention are the types of attention mechanism widely used in state-of-the-art attentive deep learning models for image captioning. At the current time, the best results are achieved from variants of multi-head attention with bottom-up attention.

arXiv:2111.14803공식 코드 · Papers with Code

Computer Vision Aided Beam Tracking in A Real-World Millimeter Wave Deployment

Millimeter-wave (mmWave) and terahertz (THz) communications require beamforming to acquire adequate receive signal-to-noise ratio (SNR). To find the optimal beam, current beam management solutions perform beam training over a large number of beams in pre-defined codebooks. The beam training overhead increases the access latency and can become infeasible for high-mobility applications. To reduce or even eliminate this beam training overhead, we propose to utilize the visual data, captured for example by cameras at the base stations, to guide the beam tracking/refining process. We propose a machine learning (ML) framework, based on an encoder-decoder architecture, that can predict the future beams using the previously obtained visual sensing information. Our proposed approach is evaluated on a large-scale real-world dataset, where it achieves an accuracy of $64.47\%$ (and a normalized receive power of $97.66\%$) in predicting the future beam. This is achieved while requiring less than $1\%$ of the beam training overhead of a corresponding baseline solution that uses a sequence of previous beams to predict the future one. This high performance and low overhead obtained on the real-world dataset demonstrate the potential of the proposed vision-aided beam tracking approach in real-world applications.

arXiv:2111.14703

Question Answering for Complex Electronic Health Records Database using Unified Encoder-Decoder Architecture

An intelligent machine that can answer human questions based on electronic health records (EHR-QA) has a great practical value, such as supporting clinical decisions, managing hospital administration, and medical chatbots. Previous table-based QA studies focusing on translating natural questions into table queries (NLQ2SQL), however, suffer from the unique nature of EHR data due to complex and specialized medical terminology, hence increased decoding difficulty. In this paper, we design UniQA, a unified encoder-decoder architecture for EHR-QA where natural language questions are converted to queries such as SQL or SPARQL. We also propose input masking (IM), a simple and effective method to cope with complex medical terms and various typos and better learn the SQL/SPARQL syntax. Combining the unified architecture with an effective auxiliary training objective, UniQA demonstrated a significant performance improvement against the previous state-of-the-art model for MIMICSQL* (14.2% gain), the most complex NLQ2SQL dataset in the EHR domain, and its typo-ridden versions (approximately 28.8% gain). In addition, we confirmed consistent results for the graph-based EHR-QA dataset, MIMICSPARQL*.

arXiv:2111.14486

Just Least Squares: Binary Compressive Sampling with Low Generative Intrinsic Dimension

In this paper, we consider recovering $n$ dimensional signals from $m$ binary measurements corrupted by noises and sign flips under the assumption that the target signals have low generative intrinsic dimension, i.e., the target signals can be approximately generated via an $L$-Lipschitz generator $G: \mathbb{R}^k\rightarrow\mathbb{R}^{n}, k\ll n$. Although the binary measurements model is highly nonlinear, we propose a least square decoder and prove that, up to a constant $c$, with high probability, the least square decoder achieves a sharp estimation error $\mathcal{O} (\sqrt{\frac{k\log (Ln)}{m}})$ as long as $m\geq \mathcal{O}( k\log (Ln))$. Extensive numerical simulations and comparisons with state-of-the-art methods demonstrated the least square decoder is robust to noise and sign flips, as indicated by our theory. By constructing a ReLU network with properly chosen depth and width, we verify the (approximately) deep generative prior, which is of independent interest.

arXiv:2111.13884

Automated Antenna Testing Using Encoder-Decoder-based Anomaly Detection

We propose a new method for testing antenna arrays that records the radiating electromagnetic (EM) field using an absorbing material and evaluating the resulting thermal image series through an AI using a conditional encoder-decoder model. Given the power and phase of the signals fed into each array element, we are able to reconstruct normal sequences through our trained model and compare it to the real sequences observed by a thermal camera. These thermograms only contain low-level patterns such as blobs of various shapes. A contour-based anomaly detector can then map the reconstruction error matrix to an anomaly score to identify faulty antenna arrays and increase the classification F-measure (F-M) by up to 46%. We show our approach on the time series thermograms collected by our antenna testing system. Conventionally, a variational autoencoder (VAE) learning observation noise may yield better results than a VAE with a constant noise assumption. However, we demonstrate that this is not the case for anomaly detection on such low-level patterns for two reasons. First, the baseline metric reconstruction probability, which incorporates the learned observation noise, fails to differentiate anomalous patterns. Second, the area under the receiver operating characteristic (ROC) curve of a VAE with a lower observation noise assumption achieves 11.83% higher than that of a VAE with learned noise.