PyTorchKR Papers

최신 논문

총 3,484편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2012.02097공식 코드 · Papers with Code

Recursive Tree Grammar Autoencoders

Machine learning on trees has been mostly focused on trees as input to algorithms. Much less research has investigated trees as output, which has many applications, such as molecule optimization for drug discovery, or hint generation for intelligent tutoring systems. In this work, we propose a novel autoencoder approach, called recursive tree grammar autoencoder (RTG-AE), which encodes trees via a bottom-up parser and decodes trees via a tree grammar, both learned via recursive neural networks that minimize the variational autoencoder loss. The resulting encoder and decoder can then be utilized in subsequent tasks, such as optimization and time series prediction. RTG-AEs are the first model to combine variational autoencoders, grammatical knowledge, and recursive processing. Our key message is that this unique combination of all three elements outperforms models which combine any two of the three. In particular, we perform an ablation study to show that our proposed method improves the autoencoding error, training time, and optimization score on synthetic as well as real datasets compared to four baselines. We further prove that RTG-AEs parse and generate trees in linear time and are expressive enough to handle all regular tree grammars.

arXiv:2012.01747공식 코드 · Papers with Code

Bengali Abstractive News Summarization(BANS): A Neural Attention Approach

Abstractive summarization is the process of generating novel sentences based on the information extracted from the original text document while retaining the context. Due to abstractive summarization's underlying complexities, most of the past research work has been done on the extractive summarization approach. Nevertheless, with the triumph of the sequence-to-sequence (seq2seq) model, abstractive summarization becomes more viable. Although a significant number of notable research has been done in the English language based on abstractive summarization, only a couple of works have been done on Bengali abstractive news summarization (BANS). In this article, we presented a seq2seq based Long Short-Term Memory (LSTM) network model with attention at encoder-decoder. Our proposed system deploys a local attention-based model that produces a long sequence of words with lucid and human-like generated sentences with noteworthy information of the original document. We also prepared a dataset of more than 19k articles and corresponding human-written summaries collected from bangla.bdnews24.com1 which is till now the most extensive dataset for Bengali news document summarization and publicly published in Kaggle2. We evaluated our model qualitatively and quantitatively and compared it with other published results. It showed significant improvement in terms of human evaluation scores with state-of-the-art approaches for BANS.

arXiv:1910.08721공식 코드 · Papers with Code

Learning to Reconstruct Crack Profiles for Eddy Current Nondestructive Testing

Eddy current testing (ECT) is one of the most popular Nondestructive Testing (NDT) techniques, especially for conductive materials. Reconstructing the crack profile from measured EC signals is one of the main goals of ECT. This task is highly challenging, as the EC signals are nonlinear responses resulted from the presence of cracks, and reconstructing the crack profile requires establishing the forward model of the nonlinear electromagnetic dynamics and solving its inverse problem, which is an ill-posed numerical optimization problem. Instead of solving the inverse problem numerically, we propose to directly learn the inverse mapping from EC signals to crack profiles with a deep encoder-decoder convolutional neural network named EddyNet. EddyNet is trained on a set of randomly generated crack profiles and the corresponding simulated EC responses generated from a realistic forward model. On the held-out test data, EddyNet achieved a mean absolute error of 0.198 between predicted profiles and ground truth ones. Qualitatively, the geometries of predicted profiles are visually similar to the ground truth profiles. Our method greatly reduces the usual reliance on domain experts, and the reconstruction is extremely fast both on GPUs and on CPUs. The source code of EddyNet is released on https://github.com/askerlee/EddyNet.

arXiv:1905.04628공식 코드 · Papers with Code

Improving Opus Low Bit Rate Quality with Neural Speech Synthesis

The voice mode of the Opus audio coder can compress wideband speech at bit rates ranging from 6 kb/s to 40 kb/s. However, Opus is at its core a waveform matching coder, and as the rate drops below 10 kb/s, quality degrades quickly. As the rate reduces even further, parametric coders tend to perform better than waveform coders. In this paper we propose a backward-compatible way of improving low bit rate Opus quality by re-synthesizing speech from the decoded parameters. We compare two different neural generative models, WaveNet and LPCNet. WaveNet is a powerful, high-complexity, and high-latency architecture that is not feasible for a practical system, yet provides a best known achievable quality with generative models. LPCNet is a low-complexity, low-latency RNN-based generative model, and practically implementable on mobile phones. We apply these systems with parameters from Opus coded at 6 kb/s as conditioning features for the generative models. A listening test shows that for the same 6 kb/s Opus bit stream, synthesized speech using LPCNet clearly outperforms the output of the standard Opus decoder. This opens up ways to improve the decoding quality of existing speech and audio waveform coders without breaking compatibility.

arXiv:2012.00945공식 코드 · Papers with Code

Two-Stage Single Image Reflection Removal with Reflection-Aware Guidance

Removing undesired reflection from an image captured through a glass surface is a very challenging problem with many practical application scenarios. For improving reflection removal, cascaded deep models have been usually adopted to estimate the transmission in a progressive manner. However, most existing methods are still limited in exploiting the result in prior stage for guiding transmission estimation. In this paper, we present a novel two-stage network with reflection-aware guidance (RAGNet) for single image reflection removal (SIRR). To be specific, the reflection layer is firstly estimated due to that it generally is much simpler and is relatively easier to estimate. Reflectionaware guidance (RAG) module is then elaborated for better exploiting the estimated reflection in predicting transmission layer. By incorporating feature maps from the estimated reflection and observation, RAG can be used (i) to mitigate the effect of reflection from the observation, and (ii) to generate mask in partial convolution for mitigating the effect of deviating from linear combination hypothesis. A dedicated mask loss is further presented for reconciling the contributions of encoder and decoder features. Experiments on five commonly used datasets demonstrate the quantitative and qualitative superiority of our RAGNet in comparison to the state-of-the-art SIRR methods. The source code and pre-trained model are available at https://github.com/liyucs/RAGNet.

arXiv:2011.13922공식 코드 · Papers with Code

A Recurrent Vision-and-Language BERT for Navigation

Accuracy of many visiolinguistic tasks has benefited significantly from the application of vision-and-language(V&L) BERT. However, its application for the task of vision-and-language navigation (VLN) remains limited. One reason for this is the difficulty adapting the BERT architecture to the partially observable Markov decision process present in VLN, requiring history-dependent attention and decision making. In this paper we propose a recurrent BERT model that is time-aware for use in VLN. Specifically, we equip the BERT model with a recurrent function that maintains cross-modal state information for the agent. Through extensive experiments on R2R and REVERIE we demonstrate that our model can replace more complex encoder-decoder models to achieve state-of-the-art results. Moreover, our approach can be generalised to other transformer-based architectures, supports pre-training, and is capable of solving navigation and referring expression tasks simultaneously.

arXiv:2011.14284공식 코드 · Papers with Code

UVid-Net: Enhanced Semantic Segmentation of UAV Aerial Videos by Embedding Temporal Information

Semantic segmentation of aerial videos has been extensively used for decision making in monitoring environmental changes, urban planning, and disaster management. The reliability of these decision support systems is dependent on the accuracy of the video semantic segmentation algorithms. The existing CNN based video semantic segmentation methods have enhanced the image semantic segmentation methods by incorporating an additional module such as LSTM or optical flow for computing temporal dynamics of the video which is a computational overhead. The proposed research work modifies the CNN architecture by incorporating temporal information to improve the efficiency of video semantic segmentation. In this work, an enhanced encoder-decoder based CNN architecture (UVid-Net) is proposed for UAV video semantic segmentation. The encoder of the proposed architecture embeds temporal information for temporally consistent labelling. The decoder is enhanced by introducing the feature-refiner module, which aids in accurate localization of the class labels. The proposed UVid-Net architecture for UAV video semantic segmentation is quantitatively evaluated on extended ManipalUAVid dataset. The performance metric mIoU of 0.79 has been observed which is significantly greater than the other state-of-the-art algorithms. Further, the proposed work produced promising results even for the pre-trained model of UVid-Net on urban street scene with fine tuning the final layer on UAV aerial videos.

arXiv:2011.14244공식 코드 · Papers with Code

Latent Template Induction with Gumbel-CRFs

Learning to control the structure of sentences is a challenging problem in text generation. Existing work either relies on simple deterministic approaches or RL-based hard structures. We explore the use of structured variational autoencoders to infer latent templates for sentence generation using a soft, continuous relaxation in order to utilize reparameterization for training. Specifically, we propose a Gumbel-CRF, a continuous relaxation of the CRF sampling algorithm using a relaxed Forward-Filtering Backward-Sampling (FFBS) approach. As a reparameterized gradient estimator, the Gumbel-CRF gives more stable gradients than score-function based estimators. As a structured inference network, we show that it learns interpretable templates during training, which allows us to control the decoder during testing. We demonstrate the effectiveness of our methods with experiments on data-to-text generation and unsupervised paraphrase generation.

arXiv:2011.14141공식 코드 · Papers with Code

AdaBins: Depth Estimation using Adaptive Bins

We address the problem of estimating a high quality dense depth map from a single RGB input image. We start out with a baseline encoder-decoder convolutional neural network architecture and pose the question of how the global processing of information can help improve overall depth estimation. To this end, we propose a transformer-based architecture block that divides the depth range into bins whose center value is estimated adaptively per image. The final depth values are estimated as linear combinations of the bin centers. We call our new building block AdaBins. Our results show a decisive improvement over the state-of-the-art on several popular depth datasets across all metrics. We also validate the effectiveness of the proposed block with an ablation study and provide the code and corresponding pre-trained weights of the new state-of-the-art model.

arXiv:2011.12643공식 코드 · Papers with Code

The Unreasonable Effectiveness of Encoder-Decoder Networks for Retinal Vessel Segmentation

We propose an encoder-decoder framework for the segmentation of blood vessels in retinal images that relies on the extraction of large-scale patches at multiple image-scales during training. Experiments on three fundus image datasets demonstrate that this approach achieves state-of-the-art results and can be implemented using a simple and efficient fully-convolutional network with a parameter count of less than 0.8M. Furthermore, we show that this framework - called VLight - avoids overfitting to specific training images and generalizes well across different datasets, which makes it highly suitable for real-world applications where robustness, accuracy as well as low inference time on high-resolution fundus images is required.

arXiv:2011.12022공식 코드 · Papers with Code

Multi-Decoder DPRNN: High Accuracy Source Counting and Separation

We propose an end-to-end trainable approach to single-channel speech separation with unknown number of speakers. Our approach extends the MulCat source separation backbone with additional output heads: a count-head to infer the number of speakers, and decoder-heads for reconstructing the original signals. Beyond the model, we also propose a metric on how to evaluate source separation with variable number of speakers. Specifically, we cleared up the issue on how to evaluate the quality when the ground-truth hasmore or less speakers than the ones predicted by the model. We evaluate our approach on the WSJ0-mix datasets, with mixtures up to five speakers. We demonstrate that our approach outperforms state-of-the-art in counting the number of speakers and remains competitive in quality of reconstructed signals.

arXiv:2011.11377공식 코드 · Papers with Code

SCGAN: Saliency Map-guided Colorization with Generative Adversarial Network

Given a grayscale photograph, the colorization system estimates a visually plausible colorful image. Conventional methods often use semantics to colorize grayscale images. However, in these methods, only classification semantic information is embedded, resulting in semantic confusion and color bleeding in the final colorized image. To address these issues, we propose a fully automatic Saliency Map-guided Colorization with Generative Adversarial Network (SCGAN) framework. It jointly predicts the colorization and saliency map to minimize semantic confusion and color bleeding in the colorized image. Since the global features from pre-trained VGG-16-Gray network are embedded to the colorization encoder, the proposed SCGAN can be trained with much less data than state-of-the-art methods to achieve perceptually reasonable colorization. In addition, we propose a novel saliency map-based guidance method. Branches of the colorization decoder are used to predict the saliency map as a proxy target. Moreover, two hierarchical discriminators are utilized for the generated colorization and saliency map, respectively, in order to strengthen visual perception performance. The proposed system is evaluated on ImageNet validation set. Experimental results show that SCGAN can generate more reasonable colorized images than state-of-the-art techniques.

arXiv:2011.11314공식 코드 · Papers with Code

Synthesizing Optical and SAR Imagery From Land Cover Maps and Auxiliary Raster Data

We synthesize both optical RGB and synthetic aperture radar (SAR) remote sensing images from land cover maps and auxiliary raster data using generative adversarial networks (GANs). In remote sensing, many types of data, such as digital elevation models (DEMs) or precipitation maps, are often not reflected in land cover maps but still influence image content or structure. Including such data in the synthesis process increases the quality of the generated images and exerts more control on their characteristics. Spatially adaptive normalization layers fuse both inputs and are applied to a full-blown generator architecture consisting of encoder and decoder to take full advantage of the information content in the auxiliary raster data. Our method successfully synthesizes medium (10 m) and high (1 m) resolution images when trained with the corresponding data set. We show the advantage of data fusion of land cover maps and auxiliary information using mean intersection over unions (mIoUs), pixel accuracy, and Fr\'echet inception distances (FIDs) using pretrained U-Net segmentation models. Handpicked images exemplify how fusing information avoids ambiguities in the synthesized images. By slightly editing the input, our method can be used to synthesize realistic changes, i.e., raising the water levels. The source code is available at https://github.com/gbaier/rs_img_synth and we published the newly created high-resolution dataset at https://ieee-dataport.org/open-access/geonrw.

arXiv:2011.10867공식 코드 · Papers with Code

A Neuro-Inspired Autoencoding Defense Against Adversarial Perturbations

Deep Neural Networks (DNNs) are vulnerable to adversarial attacks: carefully constructed perturbations to an image can seriously impair classification accuracy, while being imperceptible to humans. While there has been a significant amount of research on defending against such attacks, most defenses based on systematic design principles have been defeated by appropriately modified attacks. For a fixed set of data, the most effective current defense is to train the network using adversarially perturbed examples. In this paper, we investigate a radically different, neuro-inspired defense mechanism, starting from the observation that human vision is virtually unaffected by adversarial examples designed for machines. We aim to reject L^inf bounded adversarial perturbations before they reach a classifier DNN, using an encoder with characteristics commonly observed in biological vision: sparse overcomplete representations, randomness due to synaptic noise, and drastic nonlinearities. Encoder training is unsupervised, using standard dictionary learning. A CNN-based decoder restores the size of the encoder output to that of the original image, enabling the use of a standard CNN for classification. Our nominal design is to train the decoder and classifier together in standard supervised fashion, but we also consider unsupervised decoder training based on a regression objective (as in a conventional autoencoder) with separate supervised training of the classifier. Unlike adversarial training, all training is based on clean images. Our experiments on the CIFAR-10 show performance competitive with state-of-the-art defenses based on adversarial training, and point to the promise of neuro-inspired techniques for the design of robust neural networks. In addition, we provide results for a subset of the Imagenet dataset to verify that our approach scales to larger images.

arXiv:2011.09553공식 코드 · Papers with Code

A Sequence-to-Sequence Approach to Dialogue State Tracking

This paper is concerned with dialogue state tracking (DST) in a task-oriented dialogue system. Building a DST module that is highly effective is still a challenging issue, although significant progresses have been made recently. This paper proposes a new approach to dialogue state tracking, referred to as Seq2Seq-DU, which formalizes DST as a sequence-to-sequence problem. Seq2Seq-DU employs two BERT-based encoders to respectively encode the utterances in the dialogue and the descriptions of schemas, an attender to calculate attentions between the utterance embeddings and the schema embeddings, and a decoder to generate pointers to represent the current state of dialogue. Seq2Seq-DU has the following advantages. It can jointly model intents, slots, and slot values; it can leverage the rich representations of utterances and schemas based on BERT; it can effectively deal with categorical and non-categorical slots, and unseen schemas. In addition, Seq2Seq-DU can also be used in the NLU (natural language understanding) module of a dialogue system. Experimental results on benchmark datasets in different settings (SGD, MultiWOZ2.2, MultiWOZ2.1, WOZ2.0, DSTC2, M2M, SNIPS, and ATIS) show that Seq2Seq-DU outperforms the existing methods.

arXiv:2011.09390공식 코드 · Papers with Code

Diverse Plausible Shape Completions from Ambiguous Depth Images

We propose PSSNet, a network architecture for generating diverse plausible 3D reconstructions from a single 2.5D depth image. Existing methods tend to produce only small variations on a single shape, even when multiple shapes are consistent with an observation. To obtain diversity we alter a Variational Auto Encoder by providing a learned shape bounding box feature as side information during training. Since these features are known during training, we are able to add a supervised loss to the encoder and noiseless values to the decoder. To evaluate, we sample a set of completions from a network, construct a set of plausible shape matches for each test observation, and compare using our plausible diversity metric defined over sets of shapes. We perform experiments using Shapenet mugs and partially-occluded YCB objects and find that our method performs comparably in datasets with little ambiguity, and outperforms existing methods when many shapes plausibly fit an observed depth image. We demonstrate one use for PSSNet on a physical robot when grasping objects in occlusion and clutter.

arXiv:2011.09094공식 코드 · Papers with Code

UP-DETR: Unsupervised Pre-training for Object Detection with Transformers

DEtection TRansformer (DETR) for object detection reaches competitive performance compared with Faster R-CNN via a transformer encoder-decoder architecture. However, trained with scratch transformers, DETR needs large-scale training data and an extreme long training schedule even on COCO dataset. Inspired by the great success of pre-training transformers in natural language processing, we propose a novel pretext task named random query patch detection in Unsupervised Pre-training DETR (UP-DETR). Specifically, we randomly crop patches from the given image and then feed them as queries to the decoder. The model is pre-trained to detect these query patches from the input image. During the pre-training, we address two critical issues: multi-task learning and multi-query localization. (1) To trade off classification and localization preferences in the pretext task, we find that freezing the CNN backbone is the prerequisite for the success of pre-training transformers. (2) To perform multi-query localization, we develop UP-DETR with multi-query patch detection with attention mask. Besides, UP-DETR also provides a unified perspective for fine-tuning object detection and one-shot detection tasks. In our experiments, UP-DETR significantly boosts the performance of DETR with faster convergence and higher average precision on object detection, one-shot detection and panoptic segmentation. Code and pre-training models: https://github.com/dddzg/up-detr.

arXiv:2011.08102공식 코드 · Papers with Code

Combining GANs and AutoEncoders for Efficient Anomaly Detection

In this work, we propose CBiGAN -- a novel method for anomaly detection in images, where a consistency constraint is introduced as a regularization term in both the encoder and decoder of a BiGAN. Our model exhibits fairly good modeling power and reconstruction consistency capability. We evaluate the proposed method on MVTec AD -- a real-world benchmark for unsupervised anomaly detection on high-resolution images -- and compare against standard baselines and state-of-the-art approaches. Experiments show that the proposed method improves the performance of BiGAN formulations by a large margin and performs comparably to expensive state-of-the-art iterative methods while reducing the computational cost. We also observe that our model is particularly effective in texture-type anomaly detection, as it sets a new state of the art in this category. Our code is available at https://github.com/fabiocarrara/cbigan-ad/.

arXiv:2011.06125공식 코드 · Papers with Code

Hurricane Forecasting: A Novel Multimodal Machine Learning Framework

This paper describes a novel machine learning (ML) framework for tropical cyclone intensity and track forecasting, combining multiple ML techniques and utilizing diverse data sources. Our multimodal framework, called Hurricast, efficiently combines spatial-temporal data with statistical data by extracting features with deep-learning encoder-decoder architectures and predicting with gradient-boosted trees. We evaluate our models in the North Atlantic and Eastern Pacific basins on 2016-2019 for 24-hour lead time track and intensity forecasts and show they achieve comparable mean absolute error and skill to current operational forecast models while computing in seconds. Furthermore, the inclusion of Hurricast into an operational forecast consensus model could improve over the National Hurricane Center's official forecast, thus highlighting the complementary properties with existing approaches. In summary, our work demonstrates that utilizing machine learning techniques to combine different data sources can lead to new opportunities in tropical cyclone forecasting.

arXiv:2011.05680공식 코드 · Papers with Code

Zero-Pair Image to Image Translation using Domain Conditional Normalization

In this paper, we propose an approach based on domain conditional normalization (DCN) for zero-pair image-to-image translation, i.e., translating between two domains which have no paired training data available but each have paired training data with a third domain. We employ a single generator which has an encoder-decoder structure and analyze different implementations of domain conditional normalization to obtain the desired target domain output. The validation benchmark uses RGB-depth pairs and RGB-semantic pairs for training and compares performance for the depth-semantic translation task. The proposed approaches improve in qualitative and quantitative terms over the compared methods, while using much fewer parameters. Code available at https://github.com/samarthshukla/dcn