PyTorchKR Papers

최신 논문

총 9,339편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2305.06321공식 코드 · Papers with Code

SepMark: Deep Separable Watermarking for Unified Source Tracing and Deepfake Detection

Malicious Deepfakes have led to a sharp conflict over distinguishing between genuine and forged faces. Although many countermeasures have been developed to detect Deepfakes ex-post, undoubtedly, passive forensics has not considered any preventive measures for the pristine face before foreseeable manipulations. To complete this forensics ecosystem, we thus put forward the proactive solution dubbed SepMark, which provides a unified framework for source tracing and Deepfake detection. SepMark originates from encoder-decoder-based deep watermarking but with two separable decoders. For the first time the deep separable watermarking, SepMark brings a new paradigm to the established study of deep watermarking, where a single encoder embeds one watermark elegantly, while two decoders can extract the watermark separately at different levels of robustness. The robust decoder termed Tracer that resists various distortions may have an overly high level of robustness, allowing the watermark to survive both before and after Deepfake. The semi-robust one termed Detector is selectively sensitive to malicious distortions, making the watermark disappear after Deepfake. Only SepMark comprising of Tracer and Detector can reliably trace the trusted source of the marked face and detect whether it has been altered since being marked; neither of the two alone can achieve this. Extensive experiments demonstrate the effectiveness of the proposed SepMark on typical Deepfakes, including face swapping, expression reenactment, and attribute editing.

arXiv:2305.06242공식 코드 · Papers with Code

Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving

End-to-end autonomous driving has made impressive progress in recent years. Existing methods usually adopt the decoupled encoder-decoder paradigm, where the encoder extracts hidden features from raw sensor data, and the decoder outputs the ego-vehicle's future trajectories or actions. Under such a paradigm, the encoder does not have access to the intended behavior of the ego agent, leaving the burden of finding out safety-critical regions from the massive receptive field and inferring about future situations to the decoder. Even worse, the decoder is usually composed of several simple multi-layer perceptrons (MLP) or GRUs while the encoder is delicately designed (e.g., a combination of heavy ResNets or Transformer). Such an imbalanced resource-task division hampers the learning process. In this work, we aim to alleviate the aforementioned problem by two principles: (1) fully utilizing the capacity of the encoder; (2) increasing the capacity of the decoder. Concretely, we first predict a coarse-grained future position and action based on the encoder features. Then, conditioned on the position and action, the future scene is imagined to check the ramification if we drive accordingly. We also retrieve the encoder features around the predicted coordinate to obtain fine-grained information about the safety-critical region. Finally, based on the predicted future and the retrieved salient feature, we refine the coarse-grained position and action by predicting its offset from ground-truth. The above refinement module could be stacked in a cascaded fashion, which extends the capacity of the decoder with spatial-temporal prior knowledge about the conditioned future. We conduct experiments on the CARLA simulator and achieve state-of-the-art performance in closed-loop benchmarks. Extensive ablation studies demonstrate the effectiveness of each proposed module.

arXiv:2305.06203

Multiclass MRI Brain Tumor Segmentation using 3D Attention-based U-Net

This paper proposes a 3D attention-based U-Net architecture for multi-region segmentation of brain tumors using a single stacked multi-modal volume created by combining three non-native MRI volumes. The attention mechanism added to the decoder side of the U-Net helps to improve segmentation accuracy by de-emphasizing healthy tissues and accentuating malignant tissues, resulting in better generalization power and reduced computational resources. The method is trained and evaluated on the BraTS 2021 Task 1 dataset, and demonstrates improvement of accuracy over other approaches. My findings suggest that the proposed approach has potential to enhance brain tumor segmentation using multi-modal MRI data, contributing to better understanding and diagnosis of brain diseases. This work highlights the importance of combining multiple imaging modalities and incorporating attention mechanisms for improved accuracy in brain tumor segmentation.

arXiv:2305.06158

EdgeNet : Encoder-decoder generative Network for Auction Design in E-commerce Online Advertising

We present a new encoder-decoder generative network dubbed EdgeNet, which introduces a novel encoder-decoder framework for data-driven auction design in online e-commerce advertising. We break the neural auction paradigm of Generalized-Second-Price(GSP), and improve the utilization efficiency of data while ensuring the economic characteristics of the auction mechanism. Specifically, EdgeNet introduces a transformer-based encoder to better capture the mutual influence among different candidate advertisements. In contrast to GSP based neural auction model, we design an autoregressive decoder to better utilize the rich context information in online advertising auctions. EdgeNet is conceptually simple and easy to extend to the existing end-to-end neural auction framework. We validate the efficiency of EdgeNet on a wide range of e-commercial advertising auction, demonstrating its potential in improving user experience and platform revenue.

arXiv:2305.05873공식 코드 · Papers with Code

Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation

We propose a novel method called SHS-Net for oriented normal estimation of point clouds by learning signed hyper surfaces, which can accurately predict normals with global consistent orientation from various point clouds. Almost all existing methods estimate oriented normals through a two-stage pipeline, i.e., unoriented normal estimation and normal orientation, and each step is implemented by a separate algorithm. However, previous methods are sensitive to parameter settings, resulting in poor results from point clouds with noise, density variations and complex geometries. In this work, we introduce signed hyper surfaces (SHS), which are parameterized by multi-layer perceptron (MLP) layers, to learn to estimate oriented normals from point clouds in an end-to-end manner. The signed hyper surfaces are implicitly learned in a high-dimensional feature space where the local and global information is aggregated. Specifically, we introduce a patch encoding module and a shape encoding module to encode a 3D point cloud into a local latent code and a global latent code, respectively. Then, an attention-weighted normal prediction module is proposed as a decoder, which takes the local and global latent codes as input to predict oriented normals. Experimental results show that our SHS-Net outperforms the state-of-the-art methods in both unoriented and oriented normal estimation on the widely used benchmarks.

arXiv:2305.05425공식 코드 · Papers with Code

3DInvNet: A Deep Learning-Based 3D Ground-Penetrating Radar Data Inversion

The reconstruction of the 3D permittivity map from ground-penetrating radar (GPR) data is of great importance for mapping subsurface environments and inspecting underground structural integrity. Traditional iterative 3D reconstruction algorithms suffer from strong non-linearity, ill-posedness, and high computational cost. To tackle these issues, a 3D deep learning scheme, called 3DInvNet, is proposed to reconstruct 3D permittivity maps from GPR C-scans. The proposed scheme leverages a prior 3D convolutional neural network with a feature attention mechanism to suppress the noise in the C-scans due to subsurface heterogeneous soil environments. Then a 3D U-shaped encoder-decoder network with multi-scale feature aggregation modules is designed to establish the optimal inverse mapping from the denoised C-scans to 3D permittivity maps. Furthermore, a three-step separate learning strategy is employed to pre-train and fine-tune the networks. The proposed scheme is applied to numerical simulation as well as real measurement data. The quantitative and qualitative results show the network capability, generalizability, and robustness in denoising GPR C-scans and reconstructing 3D permittivity maps of subsurface objects.

arXiv:2305.05166공식 코드 · Papers with Code

E2TIMT: Efficient and Effective Modal Adapter for Text Image Machine Translation

Text image machine translation (TIMT) aims to translate texts embedded in images from one source language to another target language. Existing methods, both two-stage cascade and one-stage end-to-end architectures, suffer from different issues. The cascade models can benefit from the large-scale optical character recognition (OCR) and MT datasets but the two-stage architecture is redundant. The end-to-end models are efficient but suffer from training data deficiency. To this end, in our paper, we propose an end-to-end TIMT model fully making use of the knowledge from existing OCR and MT datasets to pursue both an effective and efficient framework. More specifically, we build a novel modal adapter effectively bridging the OCR encoder and MT decoder. End-to-end TIMT loss and cross-modal contrastive loss are utilized jointly to align the feature distribution of the OCR and MT tasks. Extensive experiments show that the proposed method outperforms the existing two-stage cascade models and one-stage end-to-end models with a lighter and faster architecture. Furthermore, the ablation studies verify the generalization of our method, where the proposed modal adapter is effective to bridge various OCR and MT models.

arXiv:2305.05084

Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition

Conformer-based models have become the dominant end-to-end architecture for speech processing tasks. With the objective of enhancing the conformer architecture for efficient training and inference, we carefully redesigned Conformer with a novel downsampling schema. The proposed model, named Fast Conformer(FC), is 2.8x faster than the original Conformer, supports scaling to Billion parameters without any changes to the core architecture and also achieves state-of-the-art accuracy on Automatic Speech Recognition benchmarks. To enable transcription of long-form speech up to 11 hours, we replaced global attention with limited context attention post-training, while also improving accuracy through fine-tuning with the addition of a global token. Fast Conformer, when combined with a Transformer decoder also outperforms the original Conformer in accuracy and in speed for Speech Translation and Spoken Language Understanding.

arXiv:2305.05627공식 코드 · Papers with Code

An Exploration of Encoder-Decoder Approaches to Multi-Label Classification for Legal and Biomedical Text

Standard methods for multi-label text classification largely rely on encoder-only pre-trained language models, whereas encoder-decoder models have proven more effective in other classification tasks. In this study, we compare four methods for multi-label classification, two based on an encoder only, and two based on an encoder-decoder. We carry out experiments on four datasets -two in the legal domain and two in the biomedical domain, each with two levels of label granularity- and always depart from the same pre-trained model, T5. Our results show that encoder-decoder methods outperform encoder-only methods, with a growing advantage on more complex datasets and labeling schemes of finer granularity. Using encoder-decoder models in a non-autoregressive fashion, in particular, yields the best performance overall, so we further study this approach through ablations to better understand its strengths.

arXiv:2305.05146공식 코드 · Papers with Code

A Mountain-Shaped Single-Stage Network for Accurate Image Restoration

Image restoration is the task of aiming to obtain a high-quality image from a corrupt input image, such as deblurring and deraining. In image restoration, it is typically necessary to maintain a complex balance between spatial details and contextual information. Although a multi-stage network can optimally balance these competing goals and achieve significant performance, this also increases the system's complexity. In this paper, we propose a mountain-shaped single-stage design base on a simple U-Net architecture, which removes or replaces unnecessary nonlinear activation functions to achieve the above balance with low system complexity. Specifically, we propose a feature fusion middleware (FFM) mechanism as an information exchange component between the encoder-decoder architectural levels. It seamlessly integrates upper-layer information into the adjacent lower layer, sequentially down to the lowest layer. Finally, all information is fused into the original image resolution manipulation level. This preserves spatial details and integrates contextual information, ensuring high-quality image restoration. In addition, we propose a multi-head attention middle block (MHAMB) as a bridge between the encoder and decoder to capture more global information and surpass the limitations of the receptive field of CNNs. Extensive experiments demonstrate that our approach, named as M3SNet, outperforms previous state-of-the-art models while using less than half the computational costs, for several image restoration tasks, such as image deraining and deblurring.

arXiv:2305.05082공식 코드 · Papers with Code

A Unifying Framework of Attention-based Neural Load Forecasting

Accurate load forecasting is critical for reliable and efficient planning and operation of electric power grids. In this paper, we propose a unifying deep learning framework for load forecasting, which includes time-varying feature weighting, hierarchical temporal attention, and feature-reinforced error correction. Our framework adopts a modular design with good generalization capability. First, the feature-weighting mechanism assigns input features with temporal weights. Second, a recurrent encoder-decoder structure with hierarchical attention is developed as a load predictor. The hierarchical attention enables a similar day selection, which re-evaluates the importance of historical information at each time step. Third, we develop an error correction module that explores the errors and learned feature hidden information to further improve the model's forecasting performance. Experimental results demonstrate that our proposed framework outperforms existing methods on two public datasets and performance metrics, with the feature weighting mechanism and error correction module being critical to achieving superior performance. Our framework provides an effective solution to the electric load forecasting problem, which can be further adapted to many other forecasting tasks.

arXiv:2305.05006

Synthesis of Annotated Colorectal Cancer Tissue Images from Gland Layout

Generating realistic tissue images with annotations is a challenging task that is important in many computational histopathology applications. Synthetically generated images and annotations are valuable for training and evaluating algorithms in this domain. To address this, we propose an interactive framework generating pairs of realistic colorectal cancer histology images with corresponding glandular masks from glandular structure layouts. The framework accurately captures vital features like stroma, goblet cells, and glandular lumen. Users can control gland appearance by adjusting parameters such as the number of glands, their locations, and sizes. The generated images exhibit good Frechet Inception Distance (FID) scores compared to the state-of-the-art image-to-image translation model. Additionally, we demonstrate the utility of our synthetic annotations for evaluating gland segmentation algorithms. Furthermore, we present a methodology for constructing glandular masks using advanced deep generative models, such as latent diffusion models. These masks enable tissue image generation through a residual encoder-decoder network.

arXiv:2305.04961공식 코드 · Papers with Code

Joint Moment Retrieval and Highlight Detection Via Natural Language Queries

Video summarization has become an increasingly important task in the field of computer vision due to the vast amount of video content available on the internet. In this project, we propose a new method for natural language query based joint video summarization and highlight detection using multi-modal transformers. This approach will use both visual and audio cues to match a user's natural language query to retrieve the most relevant and interesting moments from a video. Our approach employs multiple recent techniques used in Vision Transformers (ViTs) to create a transformer-like encoder-decoder model. We evaluated our approach on multiple datasets such as YouTube Highlights and TVSum to demonstrate the flexibility of our proposed method.

arXiv:2305.05610공식 코드 · Papers with Code

Can point cloud networks learn statistical shape models of anatomies?

Statistical Shape Modeling (SSM) is a valuable tool for investigating and quantifying anatomical variations within populations of anatomies. However, traditional correspondence-based SSM generation methods have a prohibitive inference process and require complete geometric proxies (e.g., high-resolution binary volumes or surface meshes) as input shapes to construct the SSM. Unordered 3D point cloud representations of shapes are more easily acquired from various medical imaging practices (e.g., thresholded images and surface scanning). Point cloud deep networks have recently achieved remarkable success in learning permutation-invariant features for different point cloud tasks (e.g., completion, semantic segmentation, classification). However, their application to learning SSM from point clouds is to-date unexplored. In this work, we demonstrate that existing point cloud encoder-decoder-based completion networks can provide an untapped potential for SSM, capturing population-level statistical representations of shapes while reducing the inference burden and relaxing the input requirement. We discuss the limitations of these techniques to the SSM application and suggest future improvements. Our work paves the way for further exploration of point cloud deep learning for SSM, a promising avenue for advancing shape analysis literature and broadening SSM to diverse use cases.

arXiv:2305.05591

AudioSlots: A slot-centric generative model for audio separation

In a range of recent works, object-centric architectures have been shown to be suitable for unsupervised scene decomposition in the vision domain. Inspired by these methods we present AudioSlots, a slot-centric generative model for blind source separation in the audio domain. AudioSlots is built using permutation-equivariant encoder and decoder networks. The encoder network based on the Transformer architecture learns to map a mixed audio spectrogram to an unordered set of independent source embeddings. The spatial broadcast decoder network learns to generate the source spectrograms from the source embeddings. We train the model in an end-to-end manner using a permutation invariant loss function. Our results on Libri2Mix speech separation constitute a proof of concept that this approach shows promise. We discuss the results and limitations of our approach in detail, and further outline potential ways to overcome the limitations and directions for future work.

arXiv:2305.05226공식 코드 · Papers with Code

Multi-Teacher Knowledge Distillation For Text Image Machine Translation

Text image machine translation (TIMT) has been widely used in various real-world applications, which translates source language texts in images into another target language sentence. Existing methods on TIMT are mainly divided into two categories: the recognition-then-translation pipeline model and the end-to-end model. However, how to transfer knowledge from the pipeline model into the end-to-end model remains an unsolved problem. In this paper, we propose a novel Multi-Teacher Knowledge Distillation (MTKD) method to effectively distillate knowledge into the end-to-end TIMT model from the pipeline model. Specifically, three teachers are utilized to improve the performance of the end-to-end TIMT model. The image encoder in the end-to-end TIMT model is optimized with the knowledge distillation guidance from the recognition teacher encoder, while the sequential encoder and decoder are improved by transferring knowledge from the translation sequential and decoder teacher models. Furthermore, both token and sentence-level knowledge distillations are incorporated to better boost the translation performance. Extensive experimental results show that our proposed MTKD effectively improves the text image translation performance and outperforms existing end-to-end and pipeline models with fewer parameters and less decoding time, illustrating that MTKD can take advantage of both pipeline and end-to-end models.

arXiv:2305.05159

Latent Interactive A2C for Improved RL in Open Many-Agent Systems

There is a prevalence of multiagent reinforcement learning (MARL) methods that engage in centralized training. But, these methods involve obtaining various types of information from the other agents, which may not be feasible in competitive or adversarial settings. A recent method, the interactive advantage actor critic (IA2C), engages in decentralized training coupled with decentralized execution, aiming to predict the other agents' actions from possibly noisy observations. In this paper, we present the latent IA2C that utilizes an encoder-decoder architecture to learn a latent representation of the hidden state and other agents' actions. Our experiments in two domains -- each populated by many agents -- reveal that the latent IA2C significantly improves sample efficiency by reducing variance and converging faster. Additionally, we introduce open versions of these domains where the agent population may change over time, and evaluate on these instances as well.

arXiv:2305.04612

Can graph neural network-based detection mitigate the impact of hardware imperfections?

Until recently, researchers used machine learning methods to compensate for hardware imperfections at the symbol level, indicating that optimum radio-frequency transceiver performance is possible. Nevertheless, such approaches neglect the error correcting codes used in wireless networks, which inspires machine learning (ML)-approaches that learn and minimise hardware imperfections at the bit level. In the present work, we evaluate a graph neural network (GNN)-based intelligent detector's in-phase and quadrature imbalance (IQI) mitigation capabilities. We focus on a high-frequency, high-directional wireless system where IQI affects both the transmitter (TX) and the receiver (RX). The TX uses a GNN-based decoder, whilst the RX uses a linear error correcting algorithm. The bit error rate (BER) is computed using appropriate Monte Carlo simulations to quantify performance. Finally, the outcomes are compared to both traditional systems using conventional detectors and wireless systems using belief propagation based detectors. Due to the utilization of graph neural networks, the proposed algorithm is highly scalable with few training parameters and is able to adapt to various code parameters.

arXiv:2305.04490공식 코드 · Papers with Code

PromptRank: Unsupervised Keyphrase Extraction Using Prompt

The keyphrase extraction task refers to the automatic selection of phrases from a given document to summarize its core content. State-of-the-art (SOTA) performance has recently been achieved by embedding-based algorithms, which rank candidates according to how similar their embeddings are to document embeddings. However, such solutions either struggle with the document and candidate length discrepancies or fail to fully utilize the pre-trained language model (PLM) without further fine-tuning. To this end, in this paper, we propose a simple yet effective unsupervised approach, PromptRank, based on the PLM with an encoder-decoder architecture. Specifically, PromptRank feeds the document into the encoder and calculates the probability of generating the candidate with a designed prompt by the decoder. We extensively evaluate the proposed PromptRank on six widely used benchmarks. PromptRank outperforms the SOTA approach MDERank, improving the F1 score relatively by 34.18%, 24.87%, and 17.57% for 5, 10, and 15 returned results, respectively. This demonstrates the great potential of using prompt for unsupervised keyphrase extraction. We release our code at https://github.com/HLT-NLP/PromptRank.

arXiv:2305.04414

Untrained Neural Network based Bayesian Detector for OTFS Modulation Systems

The orthogonal time frequency space (OTFS) symbol detector design for high mobility communication scenarios has received numerous attention lately. Current state-of-the-art OTFS detectors mainly can be divided into two categories; iterative and training-based deep neural network (DNN) detectors. Many practical iterative detectors rely on minimum-mean-square-error (MMSE) denoiser to get the initial symbol estimates. However, their computational complexity increases exponentially with the number of detected symbols. Training-based DNN detectors typically suffer from dependency on the availability of large computation resources and the fidelity of synthetic datasets for the training phase, which are both costly. In this paper, we propose an untrained DNN based on the deep image prior (DIP) and decoder architecture, referred to as D-DIP that replaces the MMSE denoiser in the iterative detector. DIP is a type of DNN that requires no training, which makes it beneficial in OTFS detector design. Then we propose to combine the D-DIP denoiser with the Bayesian parallel interference cancellation (BPIC) detector to perform iterative symbol detection, referred to as D-DIP-BPIC. Our simulation results show that the symbol error rate (SER) performance of the proposed D-DIP-BPIC detector outperforms practical state-of-the-art detectors by 0.5 dB and retains low computational complexity.