PyTorchKR Papers

최신 논문

총 3,484편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2107.12461공식 코드 · Papers with Code

Sharp U-Net: Depthwise Convolutional Network for Biomedical Image Segmentation

The U-Net architecture, built upon the fully convolutional network, has proven to be effective in biomedical image segmentation. However, U-Net applies skip connections to merge semantically different low- and high-level convolutional features, resulting in not only blurred feature maps, but also over- and under-segmented target regions. To address these limitations, we propose a simple, yet effective end-to-end depthwise encoder-decoder fully convolutional network architecture, called Sharp U-Net, for binary and multi-class biomedical image segmentation. The key rationale of Sharp U-Net is that instead of applying a plain skip connection, a depthwise convolution of the encoder feature map with a sharpening kernel filter is employed prior to merging the encoder and decoder features, thereby producing a sharpened intermediate feature map of the same size as the encoder map. Using this sharpening filter layer, we are able to not only fuse semantically less dissimilar features, but also to smooth out artifacts throughout the network layers during the early stages of training. Our extensive experiments on six datasets show that the proposed Sharp U-Net model consistently outperforms or matches the recent state-of-the-art baselines in both binary and multi-class segmentation tasks, while adding no extra learnable parameters. Furthermore, Sharp U-Net outperforms baselines that have more than three times the number of learnable parameters.

arXiv:2107.11945공식 코드 · Papers with Code

A Unified Hyper-GAN Model for Unpaired Multi-contrast MR Image Translation

Cross-contrast image translation is an important task for completing missing contrasts in clinical diagnosis. However, most existing methods learn separate translator for each pair of contrasts, which is inefficient due to many possible contrast pairs in real scenarios. In this work, we propose a unified Hyper-GAN model for effectively and efficiently translating between different contrast pairs. Hyper-GAN consists of a pair of hyper-encoder and hyper-decoder to first map from the source contrast to a common feature space, and then further map to the target contrast image. To facilitate the translation between different contrast pairs, contrast-modulators are designed to tune the hyper-encoder and hyper-decoder adaptive to different contrasts. We also design a common space loss to enforce that multi-contrast images of a subject share a common feature space, implicitly modeling the shared underlying anatomical structures. Experiments on two datasets of IXI and BraTS 2019 show that our Hyper-GAN achieves state-of-the-art results in both accuracy and efficiency, e.g., improving more than 1.47 and 1.09 dB in PSNR on two datasets with less than half the amount of parameters.

arXiv:2107.12309공식 코드 · Papers with Code

Spatial-Temporal Transformer for Dynamic Scene Graph Generation

Dynamic scene graph generation aims at generating a scene graph of the given video. Compared to the task of scene graph generation from images, it is more challenging because of the dynamic relationships between objects and the temporal dependencies between frames allowing for a richer semantic interpretation. In this paper, we propose Spatial-temporal Transformer (STTran), a neural network that consists of two core modules: (1) a spatial encoder that takes an input frame to extract spatial context and reason about the visual relationships within a frame, and (2) a temporal decoder which takes the output of the spatial encoder as input in order to capture the temporal dependencies between frames and infer the dynamic relationships. Furthermore, STTran is flexible to take varying lengths of videos as input without clipping, which is especially important for long videos. Our method is validated on the benchmark dataset Action Genome (AG). The experimental results demonstrate the superior performance of our method in terms of dynamic scene graphs. Moreover, a set of ablative studies is conducted and the effect of each proposed module is justified. Code available at: https://github.com/yrcong/STTran.

arXiv:2107.11517공식 코드 · Papers with Code

Crosslink-Net: Double-branch Encoder Segmentation Network via Fusing Vertical and Horizontal Convolutions

Accurate image segmentation plays a crucial role in medical image analysis, yet it faces great challenges of various shapes, diverse sizes, and blurry boundaries. To address these difficulties, square kernel-based encoder-decoder architecture has been proposed and widely used, but its performance remains still unsatisfactory. To further cope with these challenges, we present a novel double-branch encoder architecture. Our architecture is inspired by two observations: 1) Since the discrimination of features learned via square convolutional kernels needs to be further improved, we propose to utilize non-square vertical and horizontal convolutional kernels in the double-branch encoder, so features learned by the two branches can be expected to complement each other. 2) Considering that spatial attention can help models to better focus on the target region in a large-sized image, we develop an attention loss to further emphasize the segmentation on small-sized targets. Together, the above two schemes give rise to a novel double-branch encoder segmentation framework for medical image segmentation, namely Crosslink-Net. The experiments validate the effectiveness of our model on four datasets. The code is released at https://github.com/Qianyu1226/Crosslink-Net.

arXiv:2107.10834공식 코드 · Papers with Code

Query2Label: A Simple Transformer Way to Multi-Label Classification

This paper presents a simple and effective approach to solving the multi-label classification problem. The proposed approach leverages Transformer decoders to query the existence of a class label. The use of Transformer is rooted in the need of extracting local discriminative features adaptively for different labels, which is a strongly desired property due to the existence of multiple objects in one image. The built-in cross-attention module in the Transformer decoder offers an effective way to use label embeddings as queries to probe and pool class-related features from a feature map computed by a vision backbone for subsequent binary classifications. Compared with prior works, the new framework is simple, using standard Transformers and vision backbones, and effective, consistently outperforming all previous works on five multi-label classification data sets, including MS-COCO, PASCAL VOC, NUS-WIDE, and Visual Genome. Particularly, we establish $91.3\%$ mAP on MS-COCO. We hope its compact structure, simple implementation, and superior performance serve as a strong baseline for multi-label classification tasks and future studies. The code will be available soon at https://github.com/SlongLiu/query2labels.

arXiv:2107.09817공식 코드 · Papers with Code

Audio Captioning Transformer

Audio captioning aims to automatically generate a natural language description of an audio clip. Most captioning models follow an encoder-decoder architecture, where the decoder predicts words based on the audio features extracted by the encoder. Convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are often used as the audio encoder. However, CNNs can be limited in modelling temporal relationships among the time frames in an audio signal, while RNNs can be limited in modelling the long-range dependencies among the time frames. In this paper, we propose an Audio Captioning Transformer (ACT), which is a full Transformer network based on an encoder-decoder architecture and is totally convolution-free. The proposed method has a better ability to model the global information within an audio signal as well as capture temporal relationships between audio events. We evaluate our model on AudioCaps, which is the largest audio captioning dataset publicly available. Our model shows competitive performance compared to other state-of-the-art approaches.

arXiv:2107.09990공식 코드 · Papers with Code

CL4AC: A Contrastive Loss for Audio Captioning

Automated Audio captioning (AAC) is a cross-modal translation task that aims to use natural language to describe the content of an audio clip. As shown in the submissions received for Task 6 of the DCASE 2021 Challenges, this problem has received increasing interest in the community. The existing AAC systems are usually based on an encoder-decoder architecture, where the audio signal is encoded into a latent representation, and aligned with its corresponding text descriptions, then a decoder is used to generate the captions. However, training of an AAC system often encounters the problem of data scarcity, which may lead to inaccurate representation and audio-text alignment. To address this problem, we propose a novel encoder-decoder framework called Contrastive Loss for Audio Captioning (CL4AC). In CL4AC, the self-supervision signals derived from the original audio-text paired data are used to exploit the correspondences between audio and texts by contrasting samples, which can improve the quality of latent representation and the alignment between audio and texts, while trained with limited data. Experiments are performed on the Clotho dataset to show the effectiveness of our proposed approach.

arXiv:2107.08623공식 코드 · Papers with Code

LeViT-UNet: Make Faster Encoders with Transformer for Medical Image Segmentation

Medical image segmentation plays an essential role in developing computer-assisted diagnosis and therapy systems, yet still faces many challenges. In the past few years, the popular encoder-decoder architectures based on CNNs (e.g., U-Net) have been successfully applied in the task of medical image segmentation. However, due to the locality of convolution operations, they demonstrate limitations in learning global context and long-range spatial relations. Recently, several researchers try to introduce transformers to both the encoder and decoder components with promising results, but the efficiency requires further improvement due to the high computational complexity of transformers. In this paper, we propose LeViT-UNet, which integrates a LeViT Transformer module into the U-Net architecture, for fast and accurate medical image segmentation. Specifically, we use LeViT as the encoder of the LeViT-UNet, which better trades off the accuracy and efficiency of the Transformer block. Moreover, multi-scale feature maps from transformer blocks and convolutional blocks of LeViT are passed into the decoder via skip-connection, which can effectively reuse the spatial information of the feature maps. Our experiments indicate that the proposed LeViT-UNet achieves better performance comparing to various competing methods on several challenging medical image segmentation benchmarks including Synapse and ACDC. Code and models will be publicly available at https://github.com/apple1986/LeViT_UNet.

arXiv:2107.08037공식 코드 · Papers with Code

CCVS: Context-aware Controllable Video Synthesis

This presentation introduces a self-supervised learning approach to the synthesis of new video clips from old ones, with several new key elements for improved spatial resolution and realism: It conditions the synthesis process on contextual information for temporal continuity and ancillary information for fine control. The prediction model is doubly autoregressive, in the latent space of an autoencoder for forecasting, and in image space for updating contextual information, which is also used to enforce spatio-temporal consistency through a learnable optical flow module. Adversarial training of the autoencoder in the appearance and temporal domains is used to further improve the realism of its output. A quantizer inserted between the encoder and the transformer in charge of forecasting future frames in latent space (and its inverse inserted between the transformer and the decoder) adds even more flexibility by affording simple mechanisms for handling multimodal ancillary information for controlling the synthesis process (eg, a few sample frames, an audio track, a trajectory in image space) and taking into account the intrinsically uncertain nature of the future by allowing multiple predictions. Experiments with an implementation of the proposed approach give very good qualitative and quantitative results on multiple tasks and standard benchmarks.

arXiv:2107.07261공식 코드 · Papers with Code

Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills

Models pre-trained with a language modeling objective possess ample world knowledge and language skills, but are known to struggle in tasks that require reasoning. In this work, we propose to leverage semi-structured tables, and automatically generate at scale question-paragraph pairs, where answering the question requires reasoning over multiple facts in the paragraph. We add a pre-training step over this synthetic data, which includes examples that require 16 different reasoning skills such as number comparison, conjunction, and fact composition. To improve data efficiency, we propose sampling strategies that focus training on reasoning skills the model is currently lacking. We evaluate our approach on three reading comprehension datasets that are focused on reasoning, and show that our model, PReasM, substantially outperforms T5, a popular pre-trained encoder-decoder model. Moreover, sampling examples based on current model errors leads to faster training and higher overall performance.

arXiv:2107.06943공식 코드 · Papers with Code

FetalNet: Multi-task Deep Learning Framework for Fetal Ultrasound Biometric Measurements

In this paper, we propose an end-to-end multi-task neural network called FetalNet with an attention mechanism and stacked module for spatio-temporal fetal ultrasound scan video analysis. Fetal biometric measurement is a standard examination during pregnancy used for the fetus growth monitoring and estimation of gestational age and fetal weight. The main goal in fetal ultrasound scan video analysis is to find proper standard planes to measure the fetal head, abdomen and femur. Due to natural high speckle noise and shadows in ultrasound data, medical expertise and sonographic experience are required to find the appropriate acquisition plane and perform accurate measurements of the fetus. In addition, existing computer-aided methods for fetal US biometric measurement address only one single image frame without considering temporal features. To address these shortcomings, we propose an end-to-end multi-task neural network for spatio-temporal ultrasound scan video analysis to simultaneously localize, classify and measure the fetal body parts. We propose a new encoder-decoder segmentation architecture that incorporates a classification branch. Additionally, we employ an attention mechanism with a stacked module to learn salient maps to suppress irrelevant US regions and efficient scan plane localization. We trained on the fetal ultrasound video comes from routine examinations of 700 different patients. Our method called FetalNet outperforms existing state-of-the-art methods in both classification and segmentation in fetal ultrasound video recordings.

arXiv:2107.05790공식 코드 · Papers with Code

Visual Parser: Representing Part-whole Hierarchies with Transformers

Human vision is able to capture the part-whole hierarchical information from the entire scene. This paper presents the Visual Parser (ViP) that explicitly constructs such a hierarchy with transformers. ViP divides visual representations into two levels, the part level and the whole level. Information of each part represents a combination of several independent vectors within the whole. To model the representations of the two levels, we first encode the information from the whole into part vectors through an attention mechanism, then decode the global information within the part vectors back into the whole representation. By iteratively parsing the two levels with the proposed encoder-decoder interaction, the model can gradually refine the features on both levels. Experimental results demonstrate that ViP can achieve very competitive performance on three major tasks e.g. classification, detection and instance segmentation. In particular, it can surpass the previous state-of-the-art CNN backbones by a large margin on object detection. The tiny model of the ViP family with $7.2\times$ fewer parameters and $10.9\times$ fewer FLOPS can perform comparably with the largest model ResNeXt-101-64$\times$4d of ResNe(X)t family. Visualization results also demonstrate that the learnt parts are highly informative of the predicting class, making ViP more explainable than previous fundamental architectures. Code is available at https://github.com/kevin-ssy/ViP.

arXiv:2107.05944공식 코드 · Papers with Code

The Piano Inpainting Application

Autoregressive models are now capable of generating high-quality minute-long expressive MIDI piano performances. Even though this progress suggests new tools to assist music composition, we observe that generative algorithms are still not widely used by artists due to the limited control they offer, prohibitive inference times or the lack of integration within musicians' workflows. In this work, we present the Piano Inpainting Application (PIA), a generative model focused on inpainting piano performances, as we believe that this elementary operation (restoring missing parts of a piano performance) encourages human-machine interaction and opens up new ways to approach music composition. Our approach relies on an encoder-decoder Linear Transformer architecture trained on a novel representation for MIDI piano performances termed Structured MIDI Encoding. By uncovering an interesting synergy between Linear Transformers and our inpainting task, we are able to efficiently inpaint contiguous regions of a piano performance, which makes our model suitable for interactive and responsive A.I.-assisted composition. Finally, we introduce our freely-available Ableton Live PIA plugin, which allows musicians to smoothly generate or modify any MIDI clip using PIA within a widely-used professional Digital Audio Workstation.

arXiv:2107.05274공식 코드 · Papers with Code

TransAttUnet: Multi-level Attention-guided U-Net with Transformer for Medical Image Segmentation

Accurate segmentation of organs or lesions from medical images is crucial for reliable diagnosis of diseases and organ morphometry. In recent years, convolutional encoder-decoder solutions have achieved substantial progress in the field of automatic medical image segmentation. Due to the inherent bias in the convolution operations, prior models mainly focus on local visual cues formed by the neighboring pixels, but fail to fully model the long-range contextual dependencies. In this paper, we propose a novel Transformer-based Attention Guided Network called TransAttUnet, in which the multi-level guided attention and multi-scale skip connection are designed to jointly enhance the performance of the semantical segmentation architecture. Inspired by Transformer, the self-aware attention (SAA) module with Transformer Self Attention (TSA) and Global Spatial Attention (GSA) is incorporated into TransAttUnet to effectively learn the non-local interactions among encoder features. Moreover, we also use additional multi-scale skip connections between decoder blocks to aggregate the upsampled features with different semantic scales. In this way, the representation ability of multi-scale context information is strengthened to generate discriminative features. Benefitting from these complementary components, the proposed TransAttUnet can effectively alleviate the loss of fine details caused by the stacking of convolution layers and the consecutive sampling operations, finally improving the segmentation quality of medical images. Extensive experiments on multiple medical image segmentation datasets from different imaging modalities demonstrate that the proposed method consistently outperforms the state-of-the-art baselines. Our code and pre-trained models are available at: https://github.com/YishuLiu/TransAttUnet.

arXiv:2107.04396공식 코드 · Papers with Code

Multi-Modal Association based Grouping for Form Structure Extraction

Document structure extraction has been a widely researched area for decades. Recent work in this direction has been deep learning-based, mostly focusing on extracting structure using fully convolution NN through semantic segmentation. In this work, we present a novel multi-modal approach for form structure extraction. Given simple elements such as textruns and widgets, we extract higher-order structures such as TextBlocks, Text Fields, Choice Fields, and Choice Groups, which are essential for information collection in forms. To achieve this, we obtain a local image patch around each low-level element (reference) by identifying candidate elements closest to it. We process textual and spatial representation of candidates sequentially through a BiLSTM to obtain context-aware representations and fuse them with image patch features obtained by processing it through a CNN. Subsequently, the sequential decoder takes this fused feature vector to predict the association type between reference and candidates. These predicted associations are utilized to determine larger structures through connected components analysis. Experimental results show the effectiveness of our approach achieving a recall of 90.29%, 73.80%, 83.12%, and 52.72% for the above structures, respectively, outperforming semantic segmentation baselines significantly. We show the efficacy of our method through ablations, comparing it against using individual modalities. We also introduce our new rich human-annotated Forms Dataset.

arXiv:2107.04292공식 코드 · Papers with Code

UniRE: A Unified Label Space for Entity Relation Extraction

Many joint entity relation extraction models setup two separated label spaces for the two sub-tasks (i.e., entity detection and relation classification). We argue that this setting may hinder the information interaction between entities and relations. In this work, we propose to eliminate the different treatment on the two sub-tasks' label spaces. The input of our model is a table containing all word pairs from a sentence. Entities and relations are represented by squares and rectangles in the table. We apply a unified classifier to predict each cell's label, which unifies the learning of two sub-tasks. For testing, an effective (yet fast) approximate decoder is proposed for finding squares and rectangles from tables. Experiments on three benchmarks (ACE04, ACE05, SciERC) show that, using only half the number of parameters, our model achieves competitive accuracy with the best extractor, and is faster.

arXiv:2107.04152공식 코드 · Papers with Code

Levi Graph AMR Parser using Heterogeneous Attention

Coupled with biaffine decoders, transformers have been effectively adapted to text-to-graph transduction and achieved state-of-the-art performance on AMR parsing. Many prior works, however, rely on the biaffine decoder for either or both arc and label predictions although most features used by the decoder may be learned by the transformer already. This paper presents a novel approach to AMR parsing by combining heterogeneous data (tokens, concepts, labels) as one input to a transformer to learn attention, and use only attention matrices from the transformer to predict all elements in AMR graphs (concepts, arcs, labels). Although our models use significantly fewer parameters than the previous state-of-the-art graph parser, they show similar or better accuracy on AMR 2.0 and 3.0.

arXiv:2107.03377공식 코드 · Papers with Code

Long Short-Term Transformer for Online Action Detection

We present Long Short-term TRansformer (LSTR), a temporal modeling algorithm for online action detection, which employs a long- and short-term memory mechanism to model prolonged sequence data. It consists of an LSTR encoder that dynamically leverages coarse-scale historical information from an extended temporal window (e.g., 2048 frames spanning of up to 8 minutes), together with an LSTR decoder that focuses on a short time window (e.g., 32 frames spanning 8 seconds) to model the fine-scale characteristics of the data. Compared to prior work, LSTR provides an effective and efficient method to model long videos with fewer heuristics, which is validated by extensive empirical analysis. LSTR achieves state-of-the-art performance on three standard online action detection benchmarks, THUMOS'14, TVSeries, and HACS Segment. Code has been made available at: https://xumingze0308.github.io/projects/lstr

arXiv:2107.03172공식 코드 · Papers with Code

Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in the Real World

Common fully glazed facades and transparent objects present architectural barriers and impede the mobility of people with low vision or blindness, for instance, a path detected behind a glass door is inaccessible unless it is correctly perceived and reacted. However, segmenting these safety-critical objects is rarely covered by conventional assistive technologies. To tackle this issue, we construct a wearable system with a novel dual-head Transformer for Transparency (Trans4Trans) model, which is capable of segmenting general and transparent objects and performing real-time wayfinding to assist people walking alone more safely. Especially, both decoders created by our proposed Transformer Parsing Module (TPM) enable effective joint learning from different datasets. Besides, the efficient Trans4Trans model composed of symmetric transformer-based encoder and decoder, requires little computational expenses and is readily deployed on portable GPUs. Our Trans4Trans model outperforms state-of-the-art methods on the test sets of Stanford2D3D and Trans10K-v2 datasets and obtains mIoU of 45.13% and 75.14%, respectively. Through various pre-tests and a user study conducted in indoor and outdoor scenarios, the usability and reliability of our assistive system have been extensively verified.

arXiv:2107.02368공식 코드 · Papers with Code

UACANet: Uncertainty Augmented Context Attention for Polyp Segmentation

We propose Uncertainty Augmented Context Attention network (UACANet) for polyp segmentation which consider a uncertain area of the saliency map. We construct a modified version of U-Net shape network with additional encoder and decoder and compute a saliency map in each bottom-up stream prediction module and propagate to the next prediction module. In each prediction module, previously predicted saliency map is utilized to compute foreground, background and uncertain area map and we aggregate the feature map with three area maps for each representation. Then we compute the relation between each representation and each pixel in the feature map. We conduct experiments on five popular polyp segmentation benchmarks, Kvasir, CVC-ClinicDB, ETIS, CVC-ColonDB and CVC-300, and achieve state-of-the-art performance. Especially, we achieve 76.6% mean Dice on ETIS dataset which is 13.8% improvement compared to the previous state-of-the-art method. Source code is publicly available at https://github.com/plemeri/UACANet