PyTorchKR Papers

최신 논문

총 9,339편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2303.15960

ASCNet-ECG: Deep Autoencoder based Attention aware Skip Connection network for ECG filtering

Currently, the telehealth monitoring field has gained huge attention due to its noteworthy use in day-to-day life. This advancement has led to an increase in the data collection of electrophysiological signals. Due to this advancement, electrocardiogram (ECG) signal monitoring has become a leading task in the medical field. ECG plays an important role in the medical field by analysing cardiac physiology and abnormalities. However, these signals are affected due to numerous varieties of noises, such as electrode motion, baseline wander and white noise etc., which affects the diagnosis accuracy. Therefore, filtering ECG signals became an important task. Currently, deep learning schemes are widely employed in signal-filtering tasks due to their efficient architecture of feature learning. This work presents a deep learning-based scheme for ECG signal filtering, which is based on the deep autoencoder module. According to this scheme, the data is processed through the encoder and decoder layer to reconstruct by eliminating noises. The proposed deep learning architecture uses a modified ReLU function to improve the learning of attributes because standard ReLU cannot adapt to huge variations. Further, a skip connection is also incorporated in the proposed architecture, which retains the key feature of the encoder layer while mapping these features to the decoder layer. Similarly, an attention model is also included, which performs channel and spatial attention, which generates the robust map by using channel and average pooling operations, resulting in improving the learning performance. The proposed approach is tested on a publicly available MIT-BIH dataset where different types of noise, such as electrode motion, baseline water and motion artifacts, are added to the original signal at varied SNR levels.

arXiv:2303.15705

Translate the Beauty in Songs: Jointly Learning to Align Melody and Translate Lyrics

Song translation requires both translation of lyrics and alignment of music notes so that the resulting verse can be sung to the accompanying melody, which is a challenging problem that has attracted some interests in different aspects of the translation process. In this paper, we propose Lyrics-Melody Translation with Adaptive Grouping (LTAG), a holistic solution to automatic song translation by jointly modeling lyrics translation and lyrics-melody alignment. It is a novel encoder-decoder framework that can simultaneously translate the source lyrics and determine the number of aligned notes at each decoding step through an adaptive note grouping module. To address data scarcity, we commissioned a small amount of training data annotated specifically for this task and used large amounts of augmented data through back-translation. Experiments conducted on an English-Chinese song translation data set show the effectiveness of our model in both automatic and human evaluation.

arXiv:2303.15486

Unimodal Training-Multimodal Prediction: Cross-modal Federated Learning with Hierarchical Aggregation

Multimodal learning has seen great success mining data features from multiple modalities with remarkable model performance improvement. Meanwhile, federated learning (FL) addresses the data sharing problem, enabling privacy-preserved collaborative training to provide sufficient precious data. Great potential, therefore, arises with the confluence of them, known as multimodal federated learning. However, limitation lies in the predominant approaches as they often assume that each local dataset records samples from all modalities. In this paper, we aim to bridge this gap by proposing an Unimodal Training - Multimodal Prediction (UTMP) framework under the context of multimodal federated learning. We design HA-Fedformer, a novel transformer-based model that empowers unimodal training with only a unimodal dataset at the client and multimodal testing by aggregating multiple clients' knowledge for better accuracy. The key advantages are twofold. Firstly, to alleviate the impact of data non-IID, we develop an uncertainty-aware aggregation method for the local encoders with layer-wise Markov Chain Monte Carlo sampling. Secondly, to overcome the challenge of unaligned language sequence, we implement a cross-modal decoder aggregation to capture the hidden signal correlation between decoders trained by data from different modalities. Our experiments on popular sentiment analysis benchmarks, CMU-MOSI and CMU-MOSEI, demonstrate that HA-Fedformer significantly outperforms state-of-the-art multimodal models under the UTMP federated learning frameworks, with 15%-20% improvement on most attributes.

arXiv:2303.15973공식 코드 · Papers with Code

Do Neural Topic Models Really Need Dropout? Analysis of the Effect of Dropout in Topic Modeling

Dropout is a widely used regularization trick to resolve the overfitting issue in large feedforward neural networks trained on a small dataset, which performs poorly on the held-out test subset. Although the effectiveness of this regularization trick has been extensively studied for convolutional neural networks, there is a lack of analysis of it for unsupervised models and in particular, VAE-based neural topic models. In this paper, we have analyzed the consequences of dropout in the encoder as well as in the decoder of the VAE architecture in three widely used neural topic models, namely, contextualized topic model (CTM), ProdLDA, and embedded topic model (ETM) using four publicly available datasets. We characterize the dropout effect on these models in terms of the quality and predictive performance of the generated topics.

arXiv:2303.15576공식 코드 · Papers with Code

D-TrAttUnet: Dual-Decoder Transformer-Based Attention Unet Architecture for Binary and Multi-classes Covid-19 Infection Segmentation

In the last three years, the world has been facing a global crisis caused by Covid-19 pandemic. Medical imaging has been playing a crucial role in the fighting against this disease and saving the human lives. Indeed, CT-scans has proved their efficiency in diagnosing, detecting, and following-up the Covid-19 infection. In this paper, we propose a new Transformer-CNN based approach for Covid-19 infection segmentation from the CT slices. The proposed D-TrAttUnet architecture has an Encoder-Decoder structure, where compound Transformer-CNN encoder and Dual-Decoders are proposed. The Transformer-CNN encoder is built using Transformer layers, UpResBlocks, ResBlocks and max-pooling layers. The Dual-Decoder consists of two identical CNN decoders with attention gates. The two decoders are used to segment the infection and the lung regions simultaneously and the losses of the two tasks are joined. The proposed D-TrAttUnet architecture is evaluated for both Binary and Multi-classes Covid-19 infection segmentation. The experimental results prove the efficiency of the proposed approach to deal with the complexity of Covid-19 segmentation task from limited data. Furthermore, D-TrAttUnet architecture outperforms three baseline CNN segmentation architectures (Unet, AttUnet and Unet++) and three state-of-the-art architectures (AnamNet, SCOATNet and CopleNet), in both Binary and Mutli-classes segmentation tasks.

arXiv:2303.15555공식 코드 · Papers with Code

Object Discovery from Motion-Guided Tokens

Object discovery -- separating objects from the background without manual labels -- is a fundamental open challenge in computer vision. Previous methods struggle to go beyond clustering of low-level cues, whether handcrafted (e.g., color, texture) or learned (e.g., from auto-encoders). In this work, we augment the auto-encoder representation learning framework with two key components: motion-guidance and mid-level feature tokenization. Although both have been separately investigated, we introduce a new transformer decoder showing that their benefits can compound thanks to motion-guided vector quantization. We show that our architecture effectively leverages the synergy between motion and tokenization, improving upon the state of the art on both synthetic and real datasets. Our approach enables the emergence of interpretable object-specific mid-level features, demonstrating the benefits of motion-guidance (no labeling) and quantization (interpretability, memory efficiency).

arXiv:2303.15880공식 코드 · Papers with Code

Novel View Synthesis of Humans using Differentiable Rendering

We present a new approach for synthesizing novel views of people in new poses. Our novel differentiable renderer enables the synthesis of highly realistic images from any viewpoint. Rather than operating over mesh-based structures, our renderer makes use of diffuse Gaussian primitives that directly represent the underlying skeletal structure of a human. Rendering these primitives gives results in a high-dimensional latent image, which is then transformed into an RGB image by a decoder network. The formulation gives rise to a fully differentiable framework that can be trained end-to-end. We demonstrate the effectiveness of our approach to image reconstruction on both the Human3.6M and Panoptic Studio datasets. We show how our approach can be used for motion transfer between individuals; novel view synthesis of individuals captured from just a single camera; to synthesize individuals from any virtual viewpoint; and to re-render people in novel poses. Code and video results are available at https://github.com/GuillaumeRochette/HumanViewSynthesis.

arXiv:2303.15805

StarNet: Style-Aware 3D Point Cloud Generation

This paper investigates an open research task of reconstructing and generating 3D point clouds. Most existing works of 3D generative models directly take the Gaussian prior as input for the decoder to generate 3D point clouds, which fail to learn disentangled latent codes, leading noisy interpolated results. Most of the GAN-based models fail to discriminate the local geometries, resulting in the point clouds generated not evenly distributed at the object surface, hence degrading the point cloud generation quality. Moreover, prevailing methods adopt computation-intensive frameworks, such as flow-based models and Markov chains, which take plenty of time and resources in the training phase. To resolve these limitations, this paper proposes a unified style-aware network architecture combining both point-wise distance loss and adversarial loss, StarNet which is able to reconstruct and generate high-fidelity and even 3D point clouds using a mapping network that can effectively disentangle the Gaussian prior from input's high-level attributes in the mapped latent space to generate realistic interpolated objects. Experimental results demonstrate that our framework achieves comparable state-of-the-art performance on various metrics in the point cloud reconstruction and generation tasks, but is more lightweight in model size, requires much fewer parameters and less time for model training.

arXiv:2303.15786공식 코드 · Papers with Code

HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models

Human-Object Interaction (HOI) detection aims to localize human-object pairs and recognize their interactions. Recently, Contrastive Language-Image Pre-training (CLIP) has shown great potential in providing interaction prior for HOI detectors via knowledge distillation. However, such approaches often rely on large-scale training data and suffer from inferior performance under few/zero-shot scenarios. In this paper, we propose a novel HOI detection framework that efficiently extracts prior knowledge from CLIP and achieves better generalization. In detail, we first introduce a novel interaction decoder to extract informative regions in the visual feature map of CLIP via a cross-attention mechanism, which is then fused with the detection backbone by a knowledge integration block for more accurate human-object pair detection. In addition, prior knowledge in CLIP text encoder is leveraged to generate a classifier by embedding HOI descriptions. To distinguish fine-grained interactions, we build a verb classifier from training data via visual semantic arithmetic and a lightweight verb representation adapter. Furthermore, we propose a training-free enhancement to exploit global HOI predictions from CLIP. Extensive experiments demonstrate that our method outperforms the state of the art by a large margin on various settings, e.g. +4.04 mAP on HICO-Det. The source code is available in https://github.com/Artanic30/HOICLIP.

arXiv:2303.15782공식 코드 · Papers with Code

CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects

We present CARTO, a novel approach for reconstructing multiple articulated objects from a single stereo RGB observation. We use implicit object-centric representations and learn a single geometry and articulation decoder for multiple object categories. Despite training on multiple categories, our decoder achieves a comparable reconstruction accuracy to methods that train bespoke decoders separately for each category. Combined with our stereo image encoder we infer the 3D shape, 6D pose, size, joint type, and the joint state of multiple unknown objects in a single forward pass. Our method achieves a 20.4% absolute improvement in mAP 3D IOU50 for novel instances when compared to a two-stage pipeline. Inference time is fast and can run on a NVIDIA TITAN XP GPU at 1 HZ for eight or less objects present. While only trained on simulated data, CARTO transfers to real-world object instances. Code and evaluation data is available at: http://carto.cs.uni-freiburg.de

arXiv:2303.15699

Enhancing Breast Cancer Risk Prediction by Incorporating Prior Images

Recently, deep learning models have shown the potential to predict breast cancer risk and enable targeted screening strategies, but current models do not consider the change in the breast over time. In this paper, we present a new method, PRIME+, for breast cancer risk prediction that leverages prior mammograms using a transformer decoder, outperforming a state-of-the-art risk prediction method that only uses mammograms from a single time point. We validate our approach on a dataset with 16,113 exams and further demonstrate that it effectively captures patterns of changes from prior mammograms, such as changes in breast density, resulting in improved short-term and long-term breast cancer risk prediction. Experimental results show that our model achieves a statistically significant improvement in performance over the state-of-the-art based model, with a C-index increase from 0.68 to 0.73 (p < 0.05) on held-out test sets.

arXiv:2303.16160공식 코드 · Papers with Code

One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer

Whole-body mesh recovery aims to estimate the 3D human body, face, and hands parameters from a single image. It is challenging to perform this task with a single network due to resolution issues, i.e., the face and hands are usually located in extremely small regions. Existing works usually detect hands and faces, enlarge their resolution to feed in a specific network to predict the parameter, and finally fuse the results. While this copy-paste pipeline can capture the fine-grained details of the face and hands, the connections between different parts cannot be easily recovered in late fusion, leading to implausible 3D rotation and unnatural pose. In this work, we propose a one-stage pipeline for expressive whole-body mesh recovery, named OSX, without separate networks for each part. Specifically, we design a Component Aware Transformer (CAT) composed of a global body encoder and a local face/hand decoder. The encoder predicts the body parameters and provides a high-quality feature map for the decoder, which performs a feature-level upsample-crop scheme to extract high-resolution part-specific features and adopt keypoint-guided deformable attention to estimate hand and face precisely. The whole pipeline is simple yet effective without any manual post-processing and naturally avoids implausible prediction. Comprehensive experiments demonstrate the effectiveness of OSX. Lastly, we build a large-scale Upper-Body dataset (UBody) with high-quality 2D and 3D whole-body annotations. It contains persons with partially visible bodies in diverse real-life scenarios to bridge the gap between the basic task and downstream applications.

arXiv:2303.15293

A Deliberation-based Joint Acoustic and Text Decoder

We propose a new two-pass E2E speech recognition model that improves ASR performance by training on a combination of paired data and unpaired text data. Previously, the joint acoustic and text decoder (JATD) has shown promising results through the use of text data during model training and the recently introduced deliberation architecture has reduced recognition errors by leveraging first-pass decoding results. Our method, dubbed Deliberation-JATD, combines the spelling correcting abilities of deliberation with JATD's use of unpaired text data to further improve performance. The proposed model produces substantial gains across multiple test sets, especially those focused on rare words, where it reduces word error rate (WER) by between 12% and 22.5% relative. This is done without increasing model size or requiring multi-stage training, making Deliberation-JATD an efficient candidate for on-device applications.

arXiv:2303.15049

InterviewBot: Real-Time End-to-End Dialogue System to Interview Students for College Admission

We present the InterviewBot that dynamically integrates conversation history and customized topics into a coherent embedding space to conduct 10 mins hybrid-domain (open and closed) conversations with foreign students applying to U.S. colleges for assessing their academic and cultural readiness. To build a neural-based end-to-end dialogue model, 7,361 audio recordings of human-to-human interviews are automatically transcribed, where 440 are manually corrected for finetuning and evaluation. To overcome the input/output size limit of a transformer-based encoder-decoder model, two new methods are proposed, context attention and topic storing, allowing the model to make relevant and consistent interactions. Our final model is tested both statistically by comparing its responses to the interview data and dynamically by inviting professional interviewers and various students to interact with it in real-time, finding it highly satisfactory in fluency and context awareness.

arXiv:2303.15244공식 코드 · Papers with Code

Manifold Learning by Mixture Models of VAEs for Inverse Problems

Representing a manifold of very high-dimensional data with generative models has been shown to be computationally efficient in practice. However, this requires that the data manifold admits a global parameterization. In order to represent manifolds of arbitrary topology, we propose to learn a mixture model of variational autoencoders. Here, every encoder-decoder pair represents one chart of a manifold. We propose a loss function for maximum likelihood estimation of the model weights and choose an architecture that provides us the analytical expression of the charts and of their inverses. Once the manifold is learned, we use it for solving inverse problems by minimizing a data fidelity term restricted to the learned manifold. To solve the arising minimization problem we propose a Riemannian gradient descent algorithm on the learned manifold. We demonstrate the performance of our method for low-dimensional toy examples as well as for deblurring and electrical impedance tomography on certain image manifolds.

arXiv:2303.14302공식 코드 · Papers with Code

VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretraining

Assessing the aesthetics of an image is challenging, as it is influenced by multiple factors including composition, color, style, and high-level semantics. Existing image aesthetic assessment (IAA) methods primarily rely on human-labeled rating scores, which oversimplify the visual aesthetic information that humans perceive. Conversely, user comments offer more comprehensive information and are a more natural way to express human opinions and preferences regarding image aesthetics. In light of this, we propose learning image aesthetics from user comments, and exploring vision-language pretraining methods to learn multimodal aesthetic representations. Specifically, we pretrain an image-text encoder-decoder model with image-comment pairs, using contrastive and generative objectives to learn rich and generic aesthetic semantics without human labels. To efficiently adapt the pretrained model for downstream IAA tasks, we further propose a lightweight rank-based adapter that employs text as an anchor to learn the aesthetic ranking concept. Our results show that our pretrained aesthetic vision-language model outperforms prior works on image aesthetic captioning over the AVA-Captions dataset, and it has powerful zero-shot capability for aesthetic tasks such as zero-shot style classification and zero-shot IAA, surpassing many supervised baselines. With only minimal finetuning parameters using the proposed adapter module, our model achieves state-of-the-art IAA performance over the AVA dataset.

arXiv:2303.14816공식 코드 · Papers with Code

Feature Shrinkage Pyramid for Camouflaged Object Detection with Transformers

Vision transformers have recently shown strong global context modeling capabilities in camouflaged object detection. However, they suffer from two major limitations: less effective locality modeling and insufficient feature aggregation in decoders, which are not conducive to camouflaged object detection that explores subtle cues from indistinguishable backgrounds. To address these issues, in this paper, we propose a novel transformer-based Feature Shrinkage Pyramid Network (FSPNet), which aims to hierarchically decode locality-enhanced neighboring transformer features through progressive shrinking for camouflaged object detection. Specifically, we propose a nonlocal token enhancement module (NL-TEM) that employs the non-local mechanism to interact neighboring tokens and explore graph-based high-order relations within tokens to enhance local representations of transformers. Moreover, we design a feature shrinkage decoder (FSD) with adjacent interaction modules (AIM), which progressively aggregates adjacent transformer features through a layer-bylayer shrinkage pyramid to accumulate imperceptible but effective cues as much as possible for object information decoding. Extensive quantitative and qualitative experiments demonstrate that the proposed model significantly outperforms the existing 24 competitors on three challenging COD benchmark datasets under six widely-used evaluation metrics. Our code is publicly available at https://github.com/ZhouHuang23/FSPNet.

arXiv:2303.14739공식 코드 · Papers with Code

Geometry-Aware Attenuation Learning for Sparse-View CBCT Reconstruction

Cone Beam Computed Tomography (CBCT) plays a vital role in clinical imaging. Traditional methods typically require hundreds of 2D X-ray projections to reconstruct a high-quality 3D CBCT image, leading to considerable radiation exposure. This has led to a growing interest in sparse-view CBCT reconstruction to reduce radiation doses. While recent advances, including deep learning and neural rendering algorithms, have made strides in this area, these methods either produce unsatisfactory results or suffer from time inefficiency of individual optimization. In this paper, we introduce a novel geometry-aware encoder-decoder framework to solve this problem. Our framework starts by encoding multi-view 2D features from various 2D X-ray projections with a 2D CNN encoder. Leveraging the geometry of CBCT scanning, it then back-projects the multi-view 2D features into the 3D space to formulate a comprehensive volumetric feature map, followed by a 3D CNN decoder to recover 3D CBCT image. Importantly, our approach respects the geometric relationship between 3D CBCT image and its 2D X-ray projections during feature back projection stage, and enjoys the prior knowledge learned from the data population. This ensures its adaptability in dealing with extremly sparse view inputs without individual training, such as scenarios with only 5 or 10 X-ray projections. Extensive evaluations on two simulated datasets and one real-world dataset demonstrate exceptional reconstruction quality and time efficiency of our method.

arXiv:2303.14651공식 코드 · Papers with Code

You Only Segment Once: Towards Real-Time Panoptic Segmentation

In this paper, we propose YOSO, a real-time panoptic segmentation framework. YOSO predicts masks via dynamic convolutions between panoptic kernels and image feature maps, in which you only need to segment once for both instance and semantic segmentation tasks. To reduce the computational overhead, we design a feature pyramid aggregator for the feature map extraction, and a separable dynamic decoder for the panoptic kernel generation. The aggregator re-parameterizes interpolation-first modules in a convolution-first way, which significantly speeds up the pipeline without any additional costs. The decoder performs multi-head cross-attention via separable dynamic convolution for better efficiency and accuracy. To the best of our knowledge, YOSO is the first real-time panoptic segmentation framework that delivers competitive performance compared to state-of-the-art models. Specifically, YOSO achieves 46.4 PQ, 45.6 FPS on COCO; 52.5 PQ, 22.6 FPS on Cityscapes; 38.0 PQ, 35.4 FPS on ADE20K; and 34.1 PQ, 7.1 FPS on Mapillary Vistas. Code is available at https://github.com/hujiecpp/YOSO.

arXiv:2303.14644공식 코드 · Papers with Code

Affordance Grounding from Demonstration Video to Target Image

Humans excel at learning from expert demonstrations and solving their own problems. To equip intelligent robots and assistants, such as AR glasses, with this ability, it is essential to ground human hand interactions (i.e., affordances) from demonstration videos and apply them to a target image like a user's AR glass view. The video-to-image affordance grounding task is challenging due to (1) the need to predict fine-grained affordances, and (2) the limited training data, which inadequately covers video-image discrepancies and negatively impacts grounding. To tackle them, we propose Affordance Transformer (Afformer), which has a fine-grained transformer-based decoder that gradually refines affordance grounding. Moreover, we introduce Mask Affordance Hand (MaskAHand), a self-supervised pre-training technique for synthesizing video-image data and simulating context changes, enhancing affordance grounding across video-image discrepancies. Afformer with MaskAHand pre-training achieves state-of-the-art performance on multiple benchmarks, including a substantial 37% improvement on the OPRA dataset. Code is made available at https://github.com/showlab/afformer.