PyTorchKR Papers

최신 논문

총 9,642편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2110.04257

VieSum: How Robust Are Transformer-based Models on Vietnamese Summarization?

Text summarization is a challenging task within natural language processing that involves text generation from lengthy input sequences. While this task has been widely studied in English, there is very limited research on summarization for Vietnamese text. In this paper, we investigate the robustness of transformer-based encoder-decoder architectures for Vietnamese abstractive summarization. Leveraging transfer learning and self-supervised learning, we validate the performance of the methods on two Vietnamese datasets.

arXiv:2110.04076공식 코드 · Papers with Code

Self-supervised Point Cloud Prediction Using 3D Spatio-temporal Convolutional Networks

Exploiting past 3D LiDAR scans to predict future point clouds is a promising method for autonomous mobile systems to realize foresighted state estimation, collision avoidance, and planning. In this paper, we address the problem of predicting future 3D LiDAR point clouds given a sequence of past LiDAR scans. Estimating the future scene on the sensor level does not require any preceding steps as in localization or tracking systems and can be trained self-supervised. We propose an end-to-end approach that exploits a 2D range image representation of each 3D LiDAR scan and concatenates a sequence of range images to obtain a 3D tensor. Based on such tensors, we develop an encoder-decoder architecture using 3D convolutions to jointly aggregate spatial and temporal information of the scene and to predict the future 3D point clouds. We evaluate our method on multiple datasets and the experimental results suggest that our method outperforms existing point cloud prediction architectures and generalizes well to new, unseen environments without additional fine-tuning. Our method operates online and is faster than the common LiDAR frame rate of 10 Hz.

arXiv:2110.03879

Explaining the Attention Mechanism of End-to-End Speech Recognition Using Decision Trees

The attention mechanism has largely improved the performance of end-to-end speech recognition systems. However, the underlying behaviours of attention is not yet clearer. In this study, we use decision trees to explain how the attention mechanism impact itself in speech recognition. The results indicate that attention levels are largely impacted by their previous states rather than the encoder and decoder patterns. Additionally, the default attention mechanism seems to put more weights on closer states, but behaves poorly on modelling long-term dependencies of attention states.

arXiv:2110.04079

A Hybrid Spatial-temporal Deep Learning Architecture for Lane Detection

Accurate and reliable lane detection is vital for the safe performance of lane-keeping assistance and lane departure warning systems. However, under certain challenging circumstances, it is difficult to get satisfactory performance in accurately detecting the lanes from one single image as mostly done in current literature. Since lane markings are continuous lines, the lanes that are difficult to be accurately detected in the current single image can potentially be better deduced if information from previous frames is incorporated. This study proposes a novel hybrid spatial-temporal (ST) sequence-to-one deep learning architecture. This architecture makes full use of the ST information in multiple continuous image frames to detect the lane markings in the very last frame. Specifically, the hybrid model integrates the following aspects: (a) the single image feature extraction module equipped with the spatial convolutional neural network; (b) the ST feature integration module constructed by ST recurrent neural network; (c) the encoder-decoder structure, which makes this image segmentation problem work in an end-to-end supervised learning format. Extensive experiments reveal that the proposed model architecture can effectively handle challenging driving scenes and outperforms available state-of-the-art methods.

arXiv:2110.03921공식 코드 · Papers with Code

ViDT: An Efficient and Effective Fully Transformer-based Object Detector

Transformers are transforming the landscape of computer vision, especially for recognition tasks. Detection transformers are the first fully end-to-end learning systems for object detection, while vision transformers are the first fully transformer-based architecture for image classification. In this paper, we integrate Vision and Detection Transformers (ViDT) to build an effective and efficient object detector. ViDT introduces a reconfigured attention module to extend the recent Swin Transformer to be a standalone object detector, followed by a computationally efficient transformer decoder that exploits multi-scale features and auxiliary techniques essential to boost the detection performance without much increase in computational load. Extensive evaluation results on the Microsoft COCO benchmark dataset demonstrate that ViDT obtains the best AP and latency trade-off among existing fully transformer-based object detectors, and achieves 49.2AP owing to its high scalability for large models. We will release the code and trained models at https://github.com/naver-ai/vidt

arXiv:2110.03452공식 코드 · Papers with Code

Inter-Domain Alignment for Predicting High-Resolution Brain Networks Using Teacher-Student Learning

Accurate and automated super-resolution image synthesis is highly desired since it has the great potential to circumvent the need for acquiring high-cost medical scans and a time-consuming preprocessing pipeline of neuroimaging data. However, existing deep learning frameworks are solely designed to predict high-resolution (HR) image from a low-resolution (LR) one, which limits their generalization ability to brain graphs (i.e., connectomes). A small body of works has focused on superresolving brain graphs where the goal is to predict a HR graph from a single LR graph. Although promising, existing works mainly focus on superresolving graphs belonging to the same domain (e.g., functional), overlooking the domain fracture existing between multimodal brain data distributions (e.g., morphological and structural). To this aim, we propose a novel inter-domain adaptation framework namely, Learn to SuperResolve Brain Graphs with Knowledge Distillation Network (L2S-KDnet), which adopts a teacher-student paradigm to superresolve brain graphs. Our teacher network is a graph encoder-decoder that firstly learns the LR brain graph embeddings, and secondly learns how to align the resulting latent representations to the HR ground truth data distribution using an adversarial regularization. Ultimately, it decodes the HR graphs from the aligned embeddings. Next, our student network learns the knowledge of the aligned brain graphs as well as the topological structure of the predicted HR graphs transferred from the teacher. We further leverage the decoder of the teacher to optimize the student network. L2S-KDnet presents the first TS architecture tailored for brain graph super-resolution synthesis that is based on inter-domain alignment. Our experimental results demonstrate substantial performance gains over benchmark methods.

arXiv:2110.03674공식 코드 · Papers with Code

Dense Gaussian Processes for Few-Shot Segmentation

Few-shot segmentation is a challenging dense prediction task, which entails segmenting a novel query image given only a small annotated support set. The key problem is thus to design a method that aggregates detailed information from the support set, while being robust to large variations in appearance and context. To this end, we propose a few-shot segmentation method based on dense Gaussian process (GP) regression. Given the support set, our dense GP learns the mapping from local deep image features to mask values, capable of capturing complex appearance distributions. Furthermore, it provides a principled means of capturing uncertainty, which serves as another powerful cue for the final segmentation, obtained by a CNN decoder. Instead of a one-dimensional mask output, we further exploit the end-to-end learning capabilities of our approach to learn a high-dimensional output space for the GP. Our approach sets a new state-of-the-art on the PASCAL-5$^i$ and COCO-20$^i$ benchmarks, achieving an absolute gain of $+8.4$ mIoU in the COCO-20$^i$ 5-shot setting. Furthermore, the segmentation quality of our approach scales gracefully when increasing the support set size, while achieving robust cross-dataset transfer. Code and trained models are available at \url{https://github.com/joakimjohnander/dgpnet}.

arXiv:2110.03352공식 코드 · Papers with Code

Optimized U-Net for Brain Tumor Segmentation

We propose an optimized U-Net architecture for a brain tumor segmentation task in the BraTS21 challenge. To find the optimal model architecture and the learning schedule, we have run an extensive ablation study to test: deep supervision loss, Focal loss, decoder attention, drop block, and residual connections. Additionally, we have searched for the optimal depth of the U-Net encoder, number of convolutional channels and post-processing strategy. Our method won the validation phase and took third place in the test phase. We have open-sourced the code to reproduce our BraTS21 submission at the NVIDIA Deep Learning Examples GitHub Repository.

arXiv:2110.03298공식 코드 · Papers with Code

End-to-End Supermask Pruning: Learning to Prune Image Captioning Models

With the advancement of deep models, research work on image captioning has led to a remarkable gain in raw performance over the last decade, along with increasing model complexity and computational cost. However, surprisingly works on compression of deep networks for image captioning task has received little to no attention. For the first time in image captioning research, we provide an extensive comparison of various unstructured weight pruning methods on three different popular image captioning architectures, namely Soft-Attention, Up-Down and Object Relation Transformer. Following this, we propose a novel end-to-end weight pruning method that performs gradual sparsification based on weight sensitivity to the training loss. The pruning schemes are then extended with encoder pruning, where we show that conducting both decoder pruning and training simultaneously prior to the encoder pruning provides good overall performance. Empirically, we show that an 80% to 95% sparse network (up to 75% reduction in model size) can either match or outperform its dense counterpart. The code and pre-trained models for Up-Down and Object Relation Transformer that are capable of achieving CIDEr scores >120 on the MS-COCO dataset but with only 8.7 MB and 14.5 MB in model size (size reduction of 96% and 94% respectively against dense versions) are publicly available at https://github.com/jiahuei/sparse-image-captioning.

arXiv:2110.03027

Dynamically Decoding Source Domain Knowledge for Domain Generalization

Optimizing the performance of classifiers on samples from unseen domains remains a challenging problem. While most existing studies on domain generalization focus on learning domain-invariant feature representations, multi-expert frameworks have been proposed as a possible solution and have demonstrated promising performance. However, current multi-expert learning frameworks fail to fully exploit source domain knowledge during inference, resulting in sub-optimal performance. In this work, we propose to adapt Transformers for the purpose of dynamically decoding source domain knowledge for domain generalization. Specifically, we build one domain-specific local expert per source domain and one domain-agnostic feature branch as query. A Transformer encoder encodes all domain-specific features as source domain knowledge in memory. In the Transformer decoder, the domain-agnostic query interacts with the memory in the cross-attention module, and domains that are similar to the input will contribute more to the attention output. Thus, source domain knowledge gets dynamically decoded for inference of the current input from unseen domain. This mechanism enables the proposed method to generalize well to unseen domains. The proposed method has been evaluated on three benchmarks in the domain generalization field and shown to have the best performance compared to state-of-the-art methods.

arXiv:2110.03389

Beam Search with Bidirectional Strategies for Neural Response Generation

Sequence-to-sequence neural networks have been widely used in language-based applications as they have flexible capabilities to learn various language models. However, when seeking for the optimal language response through trained neural networks, current existing approaches such as beam-search decoder strategies are still not able reaching to promising performances. Instead of developing various decoder strategies based on a "regular sentence order" neural network (a trained model by outputting sentences from left-to-right order), we leveraged "reverse" order as additional language model (a trained model by outputting sentences from right-to-left order) which can provide different perspectives for the path finding problems. In this paper, we propose bidirectional strategies in searching paths by combining two networks (left-to-right and right-to-left language models) making a bidirectional beam search possible. Besides, our solution allows us using any similarity measure in our sentence selection criterion. Our approaches demonstrate better performance compared to the unidirectional beam search strategy.

arXiv:2110.03318

On the Latent Holes of VAEs for Text Generation

In this paper, we provide the first focused study on the discontinuities (aka. holes) in the latent space of Variational Auto-Encoders (VAEs), a phenomenon which has been shown to have a detrimental effect on model capacity. When investigating latent holes, existing works are exclusively centred around the encoder network and they merely explore the existence of holes. We tackle these limitations by proposing a highly efficient Tree-based Decoder-Centric (TDC) algorithm for latent hole identification, with a focal point on the text domain. In contrast to past studies, our approach pays attention to the decoder network, as a decoder has a direct impact on the model's output quality. Furthermore, we provide, for the first time, in-depth empirical analysis of the latent hole phenomenon, investigating several important aspects such as how the holes impact VAE algorithms' performance on text generation, and how the holes are distributed in the latent space.

arXiv:2110.03278공식 코드 · Papers with Code

Virtual Multi-Modality Self-Supervised Foreground Matting for Human-Object Interaction

Most existing human matting algorithms tried to separate pure human-only foreground from the background. In this paper, we propose a Virtual Multi-modality Foreground Matting (VMFM) method to learn human-object interactive foreground (human and objects interacted with him or her) from a raw RGB image. The VMFM method requires no additional inputs, e.g. trimap or known background. We reformulate foreground matting as a self-supervised multi-modality problem: factor each input image into estimated depth map, segmentation mask, and interaction heatmap using three auto-encoders. In order to fully utilize the characteristics of each modality, we first train a dual encoder-to-decoder network to estimate the same alpha matte. Then we introduce a self-supervised method: Complementary Learning(CL) to predict deviation probability map and exchange reliable gradients across modalities without label. We conducted extensive experiments to analyze the effectiveness of each modality and the significance of different components in complementary learning. We demonstrate that our model outperforms the state-of-the-art methods.

arXiv:2110.03223

Goal-Directed Design Agents: Integrating Visual Imitation with One-Step Lookahead Optimization for Generative Design

Engineering design problems often involve large state and action spaces along with highly sparse rewards. Since an exhaustive search of those spaces is not feasible, humans utilize relevant domain knowledge to condense the search space. Previously, deep learning agents (DLAgents) were introduced to use visual imitation learning to model design domain knowledge. This note builds on DLAgents and integrates them with one-step lookahead search to develop goal-directed agents capable of enhancing learned strategies for sequentially generating designs. Goal-directed DLAgents can employ human strategies learned from data along with optimizing an objective function. The visual imitation network from DLAgents is composed of a convolutional encoder-decoder network, acting as a rough planning step that is agnostic to feedback. Meanwhile, the lookahead search identifies the fine-tuned design action guided by an objective. These design agents are trained on an unconstrained truss design problem that is modeled as a sequential, action-based configuration design problem. The agents are then evaluated on two versions of the problem: the original version used for training and an unseen constrained version with an obstructed construction space. The goal-directed agents outperform the human designers used to train the network as well as the previous objective-agnostic versions of the agent in both scenarios. This illustrates a design agent framework that can efficiently use feedback to not only enhance learned design strategies but also adapt to unseen design problems.

arXiv:2110.03183

Attention is All You Need? Good Embeddings with Statistics are enough:Large Scale Audio Understanding without Transformers/ Convolutions/ BERTs/ Mixers/ Attention/ RNNs or ....

This paper presents a way of doing large scale audio understanding without traditional state of the art neural architectures. Ever since the introduction of deep learning for understanding audio signals in the past decade, convolutional architectures have been able to achieve state of the art results surpassing traditional hand-crafted features. In the recent past, there has been a similar shift away from traditional convolutional and recurrent neural networks towards purely end-to-end Transformer architectures. We, in this work, explore an approach, based on Bag-of-Words model. Our approach does not have any convolutions, recurrence, attention, transformers or other approaches such as BERT. We utilize micro and macro level clustered vanilla embeddings, and use a MLP head for classification. We only use feed-forward encoder-decoder models to get the bottlenecks of spectral envelops, spectral patches and slices as well as multi-resolution spectra. A classification head (a feed-forward layer), similar to the approach in SimCLR is trained on a learned representation. Using simple codes learned on latent representations, we show how we surpass traditional convolutional neural network architectures, and come strikingly close to outperforming powerful Transformer architectures. This work hopefully would pave way for exciting advancements in the field of representation learning without massive, end-to-end neural architectures.

arXiv:2110.02519공식 코드 · Papers with Code

E1D3 U-Net for Brain Tumor Segmentation: Submission to the RSNA-ASNR-MICCAI BraTS 2021 Challenge

Convolutional Neural Networks (CNNs) have demonstrated state-of-the-art performance in medical image segmentation tasks. A common feature in most top-performing CNNs is an encoder-decoder architecture inspired by the U-Net. For multi-region brain tumor segmentation, 3D U-Net architecture and its variants provide the most competitive segmentation performances. In this work, we propose an interesting extension of the standard 3D U-Net architecture, specialized for brain tumor segmentation. The proposed network, called E1D3 U-Net, is a one-encoder, three-decoder fully-convolutional neural network architecture where each decoder segments one of the hierarchical regions of interest: whole tumor, tumor core, and enhancing core. On the BraTS 2018 validation (unseen) dataset, E1D3 U-Net demonstrates single-prediction performance comparable with most state-of-the-art networks in brain tumor segmentation, with reasonable computational requirements and without ensembling. As a submission to the RSNA-ASNR-MICCAI BraTS 2021 challenge, we also evaluate our proposal on the BraTS 2021 dataset. E1D3 U-Net showcases the flexibility in the standard 3D U-Net architecture which we exploit for the task of brain tumor segmentation.

arXiv:2110.02329공식 코드 · Papers with Code

Task-aware Privacy Preservation for Multi-dimensional Data

Local differential privacy (LDP) can be adopted to anonymize richer user data attributes that will be input to sophisticated machine learning (ML) tasks. However, today's LDP approaches are largely task-agnostic and often lead to severe performance loss -- they simply inject noise to all data attributes according to a given privacy budget, regardless of what features are most relevant for the ultimate task. In this paper, we address how to significantly improve the ultimate task performance with multi-dimensional user data by considering a task-aware privacy preservation problem. The key idea is to use an encoder-decoder framework to learn (and anonymize) a task-relevant latent representation of user data. We obtain an analytical near-optimal solution for the linear setting with mean-squared error (MSE) task loss. We also provide an approximate solution through a gradient-based learning algorithm for general nonlinear cases. Extensive experiments demonstrate that our task-aware approach significantly improves ultimate task accuracy compared to standard benchmark LDP approaches with the same level of privacy guarantee.

arXiv:2110.02629공식 코드 · Papers with Code

Deep Reinforcement Learning for Solving the Heterogeneous Capacitated Vehicle Routing Problem

Existing deep reinforcement learning (DRL) based methods for solving the capacitated vehicle routing problem (CVRP) intrinsically cope with homogeneous vehicle fleet, in which the fleet is assumed as repetitions of a single vehicle. Hence, their key to construct a solution solely lies in the selection of the next node (customer) to visit excluding the selection of vehicle. However, vehicles in real-world scenarios are likely to be heterogeneous with different characteristics that affect their capacity (or travel speed), rendering existing DRL methods less effective. In this paper, we tackle heterogeneous CVRP (HCVRP), where vehicles are mainly characterized by different capacities. We consider both min-max and min-sum objectives for HCVRP, which aim to minimize the longest or total travel time of the vehicle(s) in the fleet. To solve those problems, we propose a DRL method based on the attention mechanism with a vehicle selection decoder accounting for the heterogeneous fleet constraint and a node selection decoder accounting for the route construction, which learns to construct a solution by automatically selecting both a vehicle and a node for this vehicle at each step. Experimental results based on randomly generated instances show that, with desirable generalization to various problem sizes, our method outperforms the state-of-the-art DRL method and most of the conventional heuristics, and also delivers competitive performance against the state-of-the-art heuristic method, i.e., SISR. Additionally, the results of extended experiments demonstrate that our method is also able to solve CVRPLib instances with satisfactory performance.

arXiv:2110.02220

Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognition

Fast contextual adaptation has shown to be effective in improving Automatic Speech Recognition (ASR) of rare words and when combined with an on-device personalized training, it can yield an even better recognition result. However, the traditional re-scoring approaches based on an external language model is prone to diverge during the personalized training. In this work, we introduce a model-based end-to-end contextual adaptation approach that is decoder-agnostic and amenable to on-device personalization. Our on-device simulation experiments demonstrate that the proposed approach outperforms the traditional re-scoring technique by 12% relative WER and 15.7% entity mention specific F1-score in a continues personalization scenario.

arXiv:2110.02144

Late reverberation suppression using U-nets

In real-world settings, speech signals are almost always affected by reverberation produced by the working environment; these corrupted signals need to be \emph{dereverberated} prior to performing, e.g., speech recognition, speech-to-text conversion, compression, or general audio enhancement. In this paper, we propose a supervised dereverberation technique using \emph{U-nets with skip connections}, which are fully-convolutional encoder-decoder networks with layers arranged in the form of an "U" and connections that "skip" some layers. Building on this architecture, we address speech dereverberation through the lens of Late Reverberation Suppression (LS). Via experiments on synthetic and real-world data with different noise levels and reverberation settings, we show that our proposed method termed "LS U-net" improves quality, intelligibility and other performance metrics compared to the original U-net method and it is on par with the state-of-the-art GAN-based approaches.