PyTorchKR Papers

최신 논문

총 9,642편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2007.09746

Beyond Single Stage Encoder-Decoder Networks: Deep Decoders for Semantic Image Segmentation

Single encoder-decoder methodologies for semantic segmentation are reaching their peak in terms of segmentation quality and efficiency per number of layers. To address these limitations, we propose a new architecture based on a decoder which uses a set of shallow networks for capturing more information content. The new decoder has a new topology of skip connections, namely backward and stacked residual connections. In order to further improve the architecture we introduce a weight function which aims to re-balance classes to increase the attention of the networks to under-represented objects. We carried out an extensive set of experiments that yielded state-of-the-art results for the CamVid, Gatech and Freiburg Forest datasets. Moreover, to further prove the effectiveness of our decoder, we conducted a set of experiments studying the impact of our decoder to state-of-the-art segmentation techniques. Additionally, we present a set of experiments augmenting semantic segmentation with optical flow information, showing that motion clues can boost pure image based semantic segmentation approaches.

arXiv:2007.09644

Semi Conditional Variational Auto-Encoder for Flow Reconstruction and Uncertainty Quantification from Limited Observations

We present a new data-driven model to reconstruct nonlinear flow from spatially sparse observations. The model is a version of a conditional variational auto-encoder (CVAE), which allows for probabilistic reconstruction and thus uncertainty quantification of the prediction. We show that in our model, conditioning on the measurements from the complete flow data leads to a CVAE where only the decoder depends on the measurements. For this reason we call the model as Semi-Conditional Variational Autoencoder (SCVAE). The method, reconstructions and associated uncertainty estimates are illustrated on the velocity data from simulations of 2D flow around a cylinder and bottom currents from the Bergen Ocean Model. The reconstruction errors are compared to those of the Gappy Proper Orthogonal Decomposition (GPOD) method.

arXiv:2007.09629

Character Region Attention For Text Spotting

A scene text spotter is composed of text detection and recognition modules. Many studies have been conducted to unify these modules into an end-to-end trainable model to achieve better performance. A typical architecture places detection and recognition modules into separate branches, and a RoI pooling is commonly used to let the branches share a visual feature. However, there still exists a chance of establishing a more complimentary connection between the modules when adopting recognizer that uses attention-based decoder and detector that represents spatial information of the character regions. This is possible since the two modules share a common sub-task which is to find the location of the character regions. Based on the insight, we construct a tightly coupled single pipeline model. This architecture is formed by utilizing detection outputs in the recognizer and propagating the recognition loss through the detection stage. The use of character score map helps the recognizer attend better to the character center points, and the recognition loss propagation to the detector module enhances the localization of the character regions. Also, a strengthened sharing stage allows feature rectification and boundary localization of arbitrary-shaped text regions. Extensive experiments demonstrate state-of-the-art performance in publicly available straight and curved benchmark dataset.

arXiv:2007.09580공식 코드 · Papers with Code

Length-Controllable Image Captioning

The last decade has witnessed remarkable progress in the image captioning task; however, most existing methods cannot control their captions, \emph{e.g.}, choosing to describe the image either roughly or in detail. In this paper, we propose to use a simple length level embedding to endow them with this ability. Moreover, due to their autoregressive nature, the computational complexity of existing models increases linearly as the length of the generated captions grows. Thus, we further devise a non-autoregressive image captioning approach that can generate captions in a length-irrelevant complexity. We verify the merit of the proposed length level embedding on three models: two state-of-the-art (SOTA) autoregressive models with different types of decoder, as well as our proposed non-autoregressive model, to show its generalization ability. In the experiments, our length-controllable image captioning models not only achieve SOTA performance on the challenging MS COCO dataset but also generate length-controllable and diverse image captions. Specifically, our non-autoregressive model outperforms the autoregressive baselines in terms of controllability and diversity, and also significantly improves the decoding efficiency for long captions. Our code and models are released at \textcolor{magenta}{\texttt{https://github.com/bearcatt/LaBERT}}.

arXiv:2007.10092

Improving Attention-Based Handwritten Mathematical Expression Recognition with Scale Augmentation and Drop Attention

Handwritten mathematical expression recognition (HMER) is an important research direction in handwriting recognition. The performance of HMER suffers from the two-dimensional structure of mathematical expressions (MEs). To address this issue, in this paper, we propose a high-performance HMER model with scale augmentation and drop attention. Specifically, tackling ME with unstable scale in both horizontal and vertical directions, scale augmentation improves the performance of the model on MEs of various scales. An attention-based encoder-decoder network is used for extracting features and generating predictions. In addition, drop attention is proposed to further improve performance when the attention distribution of the decoder is not precise. Compared with previous methods, our method achieves state-of-the-art performance on two public datasets of CROHME 2014 and CROHME 2016.

arXiv:2007.09903

Multimodal Dialogue State Tracking By QA Approach with Data Augmentation

Recently, a more challenging state tracking task, Audio-Video Scene-Aware Dialogue (AVSD), is catching an increasing amount of attention among researchers. Different from purely text-based dialogue state tracking, the dialogue in AVSD contains a sequence of question-answer pairs about a video and the final answer to the given question requires additional understanding of the video. This paper interprets the AVSD task from an open-domain Question Answering (QA) point of view and proposes a multimodal open-domain QA system to deal with the problem. The proposed QA system uses common encoder-decoder framework with multimodal fusion and attention. Teacher forcing is applied to train a natural language generator. We also propose a new data augmentation approach specifically under QA assumption. Our experiments show that our model and techniques bring significant improvements over the baseline model on the DSTC7-AVSD dataset and demonstrate the potentials of our data augmentation techniques.

arXiv:2007.09868

Attention Sequence to Sequence Model for Machine Remaining Useful Life Prediction

Accurate estimation of remaining useful life (RUL) of industrial equipment can enable advanced maintenance schedules, increase equipment availability and reduce operational costs. However, existing deep learning methods for RUL prediction are not completely successful due to the following two reasons. First, relying on a single objective function to estimate the RUL will limit the learned representations and thus affect the prediction accuracy. Second, while longer sequences are more informative for modelling the sensor dynamics of equipment, existing methods are less effective to deal with very long sequences, as they mainly focus on the latest information. To address these two problems, we develop a novel attention-based sequence to sequence with auxiliary task (ATS2S) model. In particular, our model jointly optimizes both reconstruction loss to empower our model with predictive capabilities (by predicting next input sequence given current input sequence) and RUL prediction loss to minimize the difference between the predicted RUL and actual RUL. Furthermore, to better handle longer sequence, we employ the attention mechanism to focus on all the important input information during training process. Finally, we propose a new dual-latent feature representation to integrate the encoder features and decoder hidden states, to capture rich semantic information in data. We conduct extensive experiments on four real datasets to evaluate the efficacy of the proposed method. Experimental results show that our proposed method can achieve superior performance over 13 state-of-the-art methods consistently.

arXiv:2007.08742공식 코드 · Papers with Code

A Novel Graph-based Multi-modal Fusion Encoder for Neural Machine Translation

Multi-modal neural machine translation (NMT) aims to translate source sentences into a target language paired with images. However, dominant multi-modal NMT models do not fully exploit fine-grained semantic correspondences between semantic units of different modalities, which have potential to refine multi-modal representation learning. To deal with this issue, in this paper, we propose a novel graph-based multi-modal fusion encoder for NMT. Specifically, we first represent the input sentence and image using a unified multi-modal graph, which captures various semantic relationships between multi-modal semantic units (words and visual objects). We then stack multiple graph-based multi-modal fusion layers that iteratively perform semantic interactions to learn node representations. Finally, these representations provide an attention-based context vector for the decoder. We evaluate our proposed encoder on the Multi30K datasets. Experimental results and in-depth analysis show the superiority of our multi-modal NMT model.

arXiv:2007.08864

Sparse Linear Networks with a Fixed Butterfly Structure: Theory and Practice

A butterfly network consists of logarithmically many layers, each with a linear number of non-zero weights (pre-specified). The fast Johnson-Lindenstrauss transform (FJLT) can be represented as a butterfly network followed by a projection onto a random subset of the coordinates. Moreover, a random matrix based on FJLT with high probability approximates the action of any matrix on a vector. Motivated by these facts, we propose to replace a dense linear layer in any neural network by an architecture based on the butterfly network. The proposed architecture significantly improves upon the quadratic number of weights required in a standard dense layer to nearly linear with little compromise in expressibility of the resulting operator. In a collection of wide variety of experiments, including supervised prediction on both the NLP and vision data, we show that this not only produces results that match and at times outperform existing well-known architectures, but it also offers faster training and prediction in deployment. To understand the optimization problems posed by neural networks with a butterfly network, we also study the optimization landscape of the encoder-decoder network, where the encoder is replaced by a butterfly network followed by a dense linear layer in smaller dimension. Theoretical result presented in the paper explains why the training speed and outcome are not compromised by our proposed approach.

arXiv:2007.09062공식 코드 · Papers with Code

Multi-scale Interactive Network for Salient Object Detection

Deep-learning based salient object detection methods achieve great progress. However, the variable scale and unknown category of salient objects are great challenges all the time. These are closely related to the utilization of multi-level and multi-scale features. In this paper, we propose the aggregate interaction modules to integrate the features from adjacent levels, in which less noise is introduced because of only using small up-/down-sampling rates. To obtain more efficient multi-scale features from the integrated features, the self-interaction modules are embedded in each decoder unit. Besides, the class imbalance issue caused by the scale variation weakens the effect of the binary cross entropy loss and results in the spatial inconsistency of the predictions. Therefore, we exploit the consistency-enhanced loss to highlight the fore-/back-ground difference and preserve the intra-class consistency. Experimental results on five benchmark datasets demonstrate that the proposed method without any post-processing performs favorably against 23 state-of-the-art approaches. The source code will be publicly available at https://github.com/lartpang/MINet.

arXiv:2007.09049공식 코드 · Papers with Code

Learning to Discretely Compose Reasoning Module Networks for Video Captioning

Generating natural language descriptions for videos, i.e., video captioning, essentially requires step-by-step reasoning along the generation process. For example, to generate the sentence "a man is shooting a basketball", we need to first locate and describe the subject "man", next reason out the man is "shooting", then describe the object "basketball" of shooting. However, existing visual reasoning methods designed for visual question answering are not appropriate to video captioning, for it requires more complex visual reasoning on videos over both space and time, and dynamic module composition along the generation process. In this paper, we propose a novel visual reasoning approach for video captioning, named Reasoning Module Networks (RMN), to equip the existing encoder-decoder framework with the above reasoning capacity. Specifically, our RMN employs 1) three sophisticated spatio-temporal reasoning modules, and 2) a dynamic and discrete module selector trained by a linguistic loss with a Gumbel approximation. Extensive experiments on MSVD and MSR-VTT datasets demonstrate the proposed RMN outperforms the state-of-the-art methods while providing an explicit and explainable generation process. Our code is available at https://github.com/tgc1997/RMN.

arXiv:2007.08304

Dual Graph Embedding for Object-Tag LinkPrediction on the Knowledge Graph

Knowledge graphs (KGs) composed of users, objects, and tags are widely used in web applications ranging from E-commerce, social media sites to news portals. This paper concentrates on an attractive application which aims to predict the object-tag links in the KG for better tag recommendation and object explanation. When predicting the object-tag links, both the first-order and high-order proximities between entities in the KG propagate essential similarity information for better prediction. Most existing methods focus on preserving the first-order proximity between entities in the KG. However, they cannot capture the high-order proximities in an explicit way, and the adopted margin-based criterion cannot measure the first-order proximity on the global structure accurately. In this paper, we propose a novel approach named Dual Graph Embedding (DGE) that models both the first-order and high-order proximities in the KG via an auto-encoding architecture to facilitate better object-tag relation inference. Here the dual graphs contain an object graph and a tag graph that explicitly depict the high-order object-object and tag-tag proximities in the KG. The dual graph encoder in DGE then encodes these high-order proximities in the dual graphs into entity embeddings. The decoder formulates a skip-gram objective that maximizes the first-order proximity between observed object-tag pairs over the global proximity structure. With the supervision of the decoder, the embeddings derived by the encoder will be refined to capture both the first-order and high-order proximities in the KG for better link prediction. Extensive experiments on three real-world datasets demonstrate that DGE outperforms the state-of-the-art methods.

arXiv:2007.08139공식 코드 · Papers with Code

Interactive Video Object Segmentation Using Global and Local Transfer Modules

An interactive video object segmentation algorithm, which takes scribble annotations on query objects as input, is proposed in this paper. We develop a deep neural network, which consists of the annotation network (A-Net) and the transfer network (T-Net). First, given user scribbles on a frame, A-Net yields a segmentation result based on the encoder-decoder architecture. Second, T-Net transfers the segmentation result bidirectionally to the other frames, by employing the global and local transfer modules. The global transfer module conveys the segmentation information in an annotated frame to a target frame, while the local transfer module propagates the segmentation information in a temporally adjacent frame to the target frame. By applying A-Net and T-Net alternately, a user can obtain desired segmentation results with minimal efforts. We train the entire network in two stages, by emulating user scribbles and employing an auxiliary loss. Experimental results demonstrate that the proposed interactive video object segmentation algorithm outperforms the state-of-the-art conventional algorithms. Codes and models are available at https://github.com/yuk6heo/IVOS-ATNet.

arXiv:2007.08113공식 코드 · Papers with Code

Defocus Blur Detection via Depth Distillation

Defocus Blur Detection(DBD) aims to separate in-focus and out-of-focus regions from a single image pixel-wisely. This task has been paid much attention since bokeh effects are widely used in digital cameras and smartphone photography. However, identifying obscure homogeneous regions and borderline transitions in partially defocus images is still challenging. To solve these problems, we introduce depth information into DBD for the first time. When the camera parameters are fixed, we argue that the accuracy of DBD is highly related to scene depth. Hence, we consider the depth information as the approximate soft label of DBD and propose a joint learning framework inspired by knowledge distillation. In detail, we learn the defocus blur from ground truth and the depth distilled from a well-trained depth estimation network at the same time. Thus, the sharp region will provide a strong prior for depth estimation while the blur detection also gains benefits from the distilled depth. Besides, we propose a novel decoder in the fully convolutional network(FCN) as our network structure. In each level of the decoder, we design the Selective Reception Field Block(SRFB) for merging multi-scale features efficiently and reuse the side outputs as Supervision-guided Attention Block(SAB). Unlike previous methods, the proposed decoder builds reception field pyramids and emphasizes salient regions simply and efficiently. Experiments show that our approach outperforms 11 other state-of-the-art methods on two popular datasets. Our method also runs at over 30 fps on a single GPU, which is 2x faster than previous works. The code is available at: https://github.com/vinthony/depth-distillation

arXiv:2007.08074공식 코드 · Papers with Code

Suppress and Balance: A Simple Gated Network for Salient Object Detection

Most salient object detection approaches use U-Net or feature pyramid networks (FPN) as their basic structures. These methods ignore two key problems when the encoder exchanges information with the decoder: one is the lack of interference control between them, the other is without considering the disparity of the contributions of different encoder blocks. In this work, we propose a simple gated network (GateNet) to solve both issues at once. With the help of multilevel gate units, the valuable context information from the encoder can be optimally transmitted to the decoder. We design a novel gated dual branch structure to build the cooperation among different levels of features and improve the discriminability of the whole network. Through the dual branch design, more details of the saliency map can be further restored. In addition, we adopt the atrous spatial pyramid pooling based on the proposed "Fold" operation (Fold-ASPP) to accurately localize salient objects of various scales. Extensive experiments on five challenging datasets demonstrate that the proposed model performs favorably against most state-of-the-art methods under different evaluation metrics.

arXiv:2007.07542공식 코드 · Papers with Code

RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition

The attention-based encoder-decoder framework has recently achieved impressive results for scene text recognition, and many variants have emerged with improvements in recognition quality. However, it performs poorly on contextless texts (e.g., random character sequences) which is unacceptable in most of real application scenarios. In this paper, we first deeply investigate the decoding process of the decoder. We empirically find that a representative character-level sequence decoder utilizes not only context information but also positional information. Contextual information, which the existing approaches heavily rely on, causes the problem of attention drift. To suppress such side-effect, we propose a novel position enhancement branch, and dynamically fuse its outputs with those of the decoder attention module for scene text recognition. Specifically, it contains a position aware module to enable the encoder to output feature vectors encoding their own spatial positions, and an attention module to estimate glimpses using the positional clue (i.e., the current decoding time step) only. The dynamic fusion is conducted for more robust feature via an element-wise gate mechanism. Theoretically, our proposed method, dubbed \emph{RobustScanner}, decodes individual characters with dynamic ratio between context and positional clues, and utilizes more positional ones when the decoding sequences with scarce context, and thus is robust and practical. Empirically, it has achieved new state-of-the-art results on popular regular and irregular text recognition benchmarks while without much performance drop on contextless benchmarks, validating its robustness in both contextual and contextless application scenarios.

arXiv:2007.07524

Learning with Privileged Information for Efficient Image Super-Resolution

Convolutional neural networks (CNNs) have allowed remarkable advances in single image super-resolution (SISR) over the last decade. Most SR methods based on CNNs have focused on achieving performance gains in terms of quality metrics, such as PSNR and SSIM, over classical approaches. They typically require a large amount of memory and computational units. FSRCNN, consisting of few numbers of convolutional layers, has shown promising results, while using an extremely small number of network parameters. We introduce in this paper a novel distillation framework, consisting of teacher and student networks, that allows to boost the performance of FSRCNN drastically. To this end, we propose to use ground-truth high-resolution (HR) images as privileged information. The encoder in the teacher learns the degradation process, subsampling of HR images, using an imitation loss. The student and the decoder in the teacher, having the same network architecture as FSRCNN, try to reconstruct HR images. Intermediate features in the decoder, affordable for the student to learn, are transferred to the student through feature distillation. Experimental results on standard benchmarks demonstrate the effectiveness and the generalization ability of our framework, which significantly boosts the performance of FSRCNN as well as other SR methods. Our code and model are available online: https://cvlab.yonsei.ac.kr/projects/PISR.

arXiv:2007.06712공식 코드 · Papers with Code

Embedded Encoder-Decoder in Convolutional Networks Towards Explainable AI

Understanding intermediate layers of a deep learning model and discovering the driving features of stimuli have attracted much interest, recently. Explainable artificial intelligence (XAI) provides a new way to open an AI black box and makes a transparent and interpretable decision. This paper proposes a new explainable convolutional neural network (XCNN) which represents important and driving visual features of stimuli in an end-to-end model architecture. This network employs encoder-decoder neural networks in a CNN architecture to represent regions of interest in an image based on its category. The proposed model is trained without localization labels and generates a heat-map as part of the network architecture without extra post-processing steps. The experimental results on the CIFAR-10, Tiny ImageNet, and MNIST datasets showed the success of our algorithm (XCNN) to make CNNs explainable. Based on visual assessment, the proposed model outperforms the current algorithms in class-specific feature representation and interpretable heatmap generation while providing a simple and flexible network architecture. The initial success of this approach warrants further study to enhance weakly supervised localization and semantic segmentation in explainable frameworks.

arXiv:2007.06620

AUTO3D: Novel view synthesis through unsupervisely learned variational viewpoint and global 3D representation

This paper targets on learning-based novel view synthesis from a single or limited 2D images without the pose supervision. In the viewer-centered coordinates, we construct an end-to-end trainable conditional variational framework to disentangle the unsupervisely learned relative-pose/rotation and implicit global 3D representation (shape, texture and the origin of viewer-centered coordinates, etc.). The global appearance of the 3D object is given by several appearance-describing images taken from any number of viewpoints. Our spatial correlation module extracts a global 3D representation from the appearance-describing images in a permutation invariant manner. Our system can achieve implicitly 3D understanding without explicitly 3D reconstruction. With an unsupervisely learned viewer-centered relative-pose/rotation code, the decoder can hallucinate the novel view continuously by sampling the relative-pose in a prior distribution. In various applications, we demonstrate that our model can achieve comparable or even better results than pose/3D model-supervised learning-based novel view synthesis (NVS) methods with any number of input views.

arXiv:2007.06963

P-KDGAN: Progressive Knowledge Distillation with GANs for One-class Novelty Detection

One-class novelty detection is to identify anomalous instances that do not conform to the expected normal instances. In this paper, the Generative Adversarial Networks (GANs) based on encoder-decoder-encoder pipeline are used for detection and achieve state-of-the-art performance. However, deep neural networks are too over-parameterized to deploy on resource-limited devices. Therefore, Progressive Knowledge Distillation with GANs (PKDGAN) is proposed to learn compact and fast novelty detection networks. The P-KDGAN is a novel attempt to connect two standard GANs by the designed distillation loss for transferring knowledge from the teacher to the student. The progressive learning of knowledge distillation is a two-step approach that continuously improves the performance of the student GAN and achieves better performance than single step methods. In the first step, the student GAN learns the basic knowledge totally from the teacher via guiding of the pretrained teacher GAN with fixed weights. In the second step, joint fine-training is adopted for the knowledgeable teacher and student GANs to further improve the performance and stability. The experimental results on CIFAR-10, MNIST, and FMNIST show that our method improves the performance of the student GAN by 2.44%, 1.77%, and 1.73% when compressing the computation at ratios of 24.45:1, 311.11:1, and 700:1, respectively.