PyTorchKR Papers

최신 논문

총 3,484편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2105.04281공식 코드 · Papers with Code

Visual Grounding with Transformers

In this paper, we propose a transformer based approach for visual grounding. Unlike previous proposal-and-rank frameworks that rely heavily on pretrained object detectors or proposal-free frameworks that upgrade an off-the-shelf one-stage detector by fusing textual embeddings, our approach is built on top of a transformer encoder-decoder and is independent of any pretrained detectors or word embedding models. Termed VGTR -- Visual Grounding with TRansformers, our approach is designed to learn semantic-discriminative visual features under the guidance of the textual description without harming their location ability. This information flow enables our VGTR to have a strong capability in capturing context-level semantics of both vision and language modalities, rendering us to aggregate accurate visual clues implied by the description to locate the interested object instance. Experiments show that our method outperforms state-of-the-art proposal-free approaches by a considerable margin on five benchmarks while maintaining fast inference speed.

arXiv:2105.02412공식 코드 · Papers with Code

Handwritten Mathematical Expression Recognition with Bidirectionally Trained Transformer

Encoder-decoder models have made great progress on handwritten mathematical expression recognition recently. However, it is still a challenge for existing methods to assign attention to image features accurately. Moreover, those encoder-decoder models usually adopt RNN-based models in their decoder part, which makes them inefficient in processing long $\LaTeX{}$ sequences. In this paper, a transformer-based decoder is employed to replace RNN-based ones, which makes the whole model architecture very concise. Furthermore, a novel training strategy is introduced to fully exploit the potential of the transformer in bidirectional language modeling. Compared to several methods that do not use data augmentation, experiments demonstrate that our model improves the ExpRate of current state-of-the-art methods on CROHME 2014 by 2.23%. Similarly, on CROHME 2016 and CROHME 2019, we improve the ExpRate by 1.92% and 2.28% respectively.

arXiv:2105.02340공식 코드 · Papers with Code

DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Data

Despite over two decades of progress, imbalanced data is still considered a significant challenge for contemporary machine learning models. Modern advances in deep learning have magnified the importance of the imbalanced data problem. The two main approaches to address this issue are based on loss function modifications and instance resampling. Instance sampling is typically based on Generative Adversarial Networks (GANs), which may suffer from mode collapse. Therefore, there is a need for an oversampling method that is specifically tailored to deep learning models, can work on raw images while preserving their properties, and is capable of generating high quality, artificial images that can enhance minority classes and balance the training set. We propose DeepSMOTE - a novel oversampling algorithm for deep learning models. It is simple, yet effective in its design. It consists of three major components: (i) an encoder/decoder framework; (ii) SMOTE-based oversampling; and (iii) a dedicated loss function that is enhanced with a penalty term. An important advantage of DeepSMOTE over GAN-based oversampling is that DeepSMOTE does not require a discriminator, and it generates high-quality artificial images that are both information-rich and suitable for visual inspection. DeepSMOTE code is publicly available at: https://github.com/dd1github/DeepSMOTE

arXiv:2105.02216공식 코드 · Papers with Code

Self-Supervised Multi-Frame Monocular Scene Flow

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

arXiv:2105.00999공식 코드 · Papers with Code

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

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

arXiv:2105.00967공식 코드 · Papers with Code

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

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

arXiv:2105.00690공식 코드 · Papers with Code

Multi-modal Bifurcated Network for Depth Guided Image Relighting

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

arXiv:2105.00681공식 코드 · Papers with Code

S3Net: A Single Stream Structure for Depth Guided Image Relighting

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

arXiv:2105.00273공식 코드 · Papers with Code

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

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

arXiv:2105.00171공식 코드 · Papers with Code

AlloST: Low-resource Speech Translation without Source Transcription

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

arXiv:2105.00079공식 코드 · Papers with Code

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

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

arXiv:2105.00997공식 코드 · Papers with Code

Recovering Barabási-Albert Parameters of Graphs through Disentanglement

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

arXiv:2105.00250공식 코드 · Papers with Code

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

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

arXiv:2104.14079공식 코드 · Papers with Code

Maneuver-Aware Pooling for Vehicle Trajectory Prediction

Autonomous vehicles should be able to predict the future states of its environment and respond appropriately. Specifically, predicting the behavior of surrounding human drivers is vital for such platforms to share the same road with humans. Behavior of each of the surrounding vehicles is governed by the motion of its neighbor vehicles. This paper focuses on predicting the behavior of the surrounding vehicles of an autonomous vehicle on highways. We are motivated by improving the prediction accuracy when a surrounding vehicle performs lane change and highway merging maneuvers. We propose a novel pooling strategy to capture the inter-dependencies between the neighbor vehicles. Depending solely on Euclidean trajectory representation, the existing pooling strategies do not model the context information of the maneuvers intended by a surrounding vehicle. In contrast, our pooling mechanism employs polar trajectory representation, vehicles orientation and radial velocity. This results in an implicitly maneuver-aware pooling operation. We incorporated the proposed pooling mechanism into a generative encoder-decoder model, and evaluated our method on the public NGSIM dataset. The results of maneuver-based trajectory predictions demonstrate the effectiveness of the proposed method compared with the state-of-the-art approaches. Our "Pooling Toolbox" code is available at https://github.com/m-hasan-n/pooling.

arXiv:2104.13743공식 코드 · Papers with Code

Image Inpainting by End-to-End Cascaded Refinement with Mask Awareness

Inpainting arbitrary missing regions is challenging because learning valid features for various masked regions is nontrivial. Though U-shaped encoder-decoder frameworks have been witnessed to be successful, most of them share a common drawback of mask unawareness in feature extraction because all convolution windows (or regions), including those with various shapes of missing pixels, are treated equally and filtered with fixed learned kernels. To this end, we propose our novel mask-aware inpainting solution. Firstly, a Mask-Aware Dynamic Filtering (MADF) module is designed to effectively learn multi-scale features for missing regions in the encoding phase. Specifically, filters for each convolution window are generated from features of the corresponding region of the mask. The second fold of mask awareness is achieved by adopting Point-wise Normalization (PN) in our decoding phase, considering that statistical natures of features at masked points differentiate from those of unmasked points. The proposed PN can tackle this issue by dynamically assigning point-wise scaling factor and bias. Lastly, our model is designed to be an end-to-end cascaded refinement one. Supervision information such as reconstruction loss, perceptual loss and total variation loss is incrementally leveraged to boost the inpainting results from coarse to fine. Effectiveness of the proposed framework is validated both quantitatively and qualitatively via extensive experiments on three public datasets including Places2, CelebA and Paris StreetView.

arXiv:2104.13682공식 코드 · Papers with Code

HOTR: End-to-End Human-Object Interaction Detection with Transformers

Human-Object Interaction (HOI) detection is a task of identifying "a set of interactions" in an image, which involves the i) localization of the subject (i.e., humans) and target (i.e., objects) of interaction, and ii) the classification of the interaction labels. Most existing methods have indirectly addressed this task by detecting human and object instances and individually inferring every pair of the detected instances. In this paper, we present a novel framework, referred to by HOTR, which directly predicts a set of <human, object, interaction> triplets from an image based on a transformer encoder-decoder architecture. Through the set prediction, our method effectively exploits the inherent semantic relationships in an image and does not require time-consuming post-processing which is the main bottleneck of existing methods. Our proposed algorithm achieves the state-of-the-art performance in two HOI detection benchmarks with an inference time under 1 ms after object detection.

arXiv:2104.13188공식 코드 · Papers with Code

Rethinking BiSeNet For Real-time Semantic Segmentation

BiSeNet has been proved to be a popular two-stream network for real-time segmentation. However, its principle of adding an extra path to encode spatial information is time-consuming, and the backbones borrowed from pretrained tasks, e.g., image classification, may be inefficient for image segmentation due to the deficiency of task-specific design. To handle these problems, we propose a novel and efficient structure named Short-Term Dense Concatenate network (STDC network) by removing structure redundancy. Specifically, we gradually reduce the dimension of feature maps and use the aggregation of them for image representation, which forms the basic module of STDC network. In the decoder, we propose a Detail Aggregation module by integrating the learning of spatial information into low-level layers in single-stream manner. Finally, the low-level features and deep features are fused to predict the final segmentation results. Extensive experiments on Cityscapes and CamVid dataset demonstrate the effectiveness of our method by achieving promising trade-off between segmentation accuracy and inference speed. On Cityscapes, we achieve 71.9% mIoU on the test set with a speed of 250.4 FPS on NVIDIA GTX 1080Ti, which is 45.2% faster than the latest methods, and achieve 76.8% mIoU with 97.0 FPS while inferring on higher resolution images.

arXiv:2104.12714공식 코드 · Papers with Code

Focused Attention Improves Document-Grounded Generation

Document grounded generation is the task of using the information provided in a document to improve text generation. This work focuses on two different document grounded generation tasks: Wikipedia Update Generation task and Dialogue response generation. Our work introduces two novel adaptations of large scale pre-trained encoder-decoder models focusing on building context driven representation of the document and enabling specific attention to the information in the document. Additionally, we provide a stronger BART baseline for these tasks. Our proposed techniques outperform existing methods on both automated (at least 48% increase in BLEU-4 points) and human evaluation for closeness to reference and relevance to the document. Furthermore, we perform comprehensive manual inspection of the generated output and categorize errors to provide insights into future directions in modeling these tasks.

arXiv:2104.11984공식 코드 · Papers with Code

MusCaps: Generating Captions for Music Audio

Content-based music information retrieval has seen rapid progress with the adoption of deep learning. Current approaches to high-level music description typically make use of classification models, such as in auto-tagging or genre and mood classification. In this work, we propose to address music description via audio captioning, defined as the task of generating a natural language description of music audio content in a human-like manner. To this end, we present the first music audio captioning model, MusCaps, consisting of an encoder-decoder with temporal attention. Our method combines convolutional and recurrent neural network architectures to jointly process audio-text inputs through a multimodal encoder and leverages pre-training on audio data to obtain representations that effectively capture and summarise musical features in the input. Evaluation of the generated captions through automatic metrics shows that our method outperforms a baseline designed for non-music audio captioning. Through an ablation study, we unveil that this performance boost can be mainly attributed to pre-training of the audio encoder, while other design choices - modality fusion, decoding strategy and the use of attention - contribute only marginally. Our model represents a shift away from classification-based music description and combines tasks requiring both auditory and linguistic understanding to bridge the semantic gap in music information retrieval.

arXiv:2104.12137공식 코드 · Papers with Code

A Novel Transformer Based Semantic Segmentation Scheme for Fine-Resolution Remote Sensing Images

The fully convolutional network (FCN) with an encoder-decoder architecture has been the standard paradigm for semantic segmentation. The encoder-decoder architecture utilizes an encoder to capture multilevel feature maps, which are incorporated into the final prediction by a decoder. As the context is crucial for precise segmentation, tremendous effort has been made to extract such information in an intelligent fashion, including employing dilated/atrous convolutions or inserting attention modules. However, these endeavors are all based on the FCN architecture with ResNet or other backbones, which cannot fully exploit the context from the theoretical concept. By contrast, we introduce the Swin Transformer as the backbone to extract the context information and design a novel decoder of densely connected feature aggregation module (DCFAM) to restore the resolution and produce the segmentation map. The experimental results on two remotely sensed semantic segmentation datasets demonstrate the effectiveness of the proposed scheme.Code is available at https://github.com/WangLibo1995/GeoSeg