PyTorchKR Papers

최신 논문

총 5,576편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2205.00847공식 코드 · Papers with Code

APP-Net: Auxiliary-point-based Push and Pull Operations for Efficient Point Cloud Classification

Aggregating neighbor features is essential for point cloud classification. In the existing work, each point in the cloud may inevitably be selected as the neighbors of multiple aggregation centers, as all centers will gather neighbor features from the whole point cloud independently. Thus each point has to participate in the calculation repeatedly and generates redundant duplicates in the memory, leading to intensive computation costs and memory consumption. Meanwhile, to pursue higher accuracy, previous methods often rely on a complex local aggregator to extract fine geometric representation, which further slows down the classification pipeline. To address these issues, we propose a new local aggregator of linear complexity for point cloud classification, coined as APP. Specifically, we introduce an auxiliary container as an anchor to exchange features between the source point and the aggregating center. Each source point pushes its feature to only one auxiliary container, and each center point pulls features from only one auxiliary container. This avoids the re-computation issue of each source point. To facilitate the learning of the local structure of cloud point, we use an online normal estimation module to provide the explainable geometric information to enhance our APP modeling capability. Our built network is more efficient than all the previous baselines with a clear margin while still consuming a lower memory. Experiments on both synthetic and real datasets demonstrate that APP-Net reaches comparable accuracies to other networks. It can process more than 10,000 samples per second with less than 10GB of memory on a single GPU. We will release the code in https://github.com/MCG-NJU/APP-Net.

arXiv:2205.00841

GPUNet: Searching the Deployable Convolution Neural Networks for GPUs

Customizing Convolution Neural Networks (CNN) for production use has been a challenging task for DL practitioners. This paper intends to expedite the model customization with a model hub that contains the optimized models tiered by their inference latency using Neural Architecture Search (NAS). To achieve this goal, we build a distributed NAS system to search on a novel search space that consists of prominent factors to impact latency and accuracy. Since we target GPU, we name the NAS optimized models as GPUNet, which establishes a new SOTA Pareto frontier in inference latency and accuracy. Within 1$ms$, GPUNet is 2x faster than EfficientNet-X and FBNetV3 with even better accuracy. We also validate GPUNet on detection tasks, and GPUNet consistently outperforms EfficientNet-X and FBNetV3 on COCO detection tasks in both latency and accuracy. All of these data validate that our NAS system is effective and generic to handle different design tasks. With this NAS system, we expand GPUNet to cover a wide range of latency targets such that DL practitioners can deploy our models directly in different scenarios.

arXiv:2205.00630

Design equivariant neural networks for 3D point cloud

This work seeks to improve the generalization and robustness of existing neural networks for 3D point clouds by inducing group equivariance under general group transformations. The main challenge when designing equivariant models for point clouds is how to trade-off the performance of the model and the complexity. Existing equivariant models are either too complicate to implement or very high complexity. The main aim of this study is to build a general procedure to introduce group equivariant property to SOTA models for 3D point clouds. The group equivariant models built form our procedure are simple to implement, less complexity in comparison with the existing ones, and they preserve the strengths of the original SOTA backbone. From the results of the experiments on object classification, it is shown that our methods are superior to other group equivariant models in performance and complexity. Moreover, our method also helps to improve the mIoU of semantic segmentation models. Overall, by using a combination of only-finite-rotation equivariance and augmentation, our models can outperform existing full $SO(3)$-equivariance models with much cheaper complexity and GPU memory. The proposed procedure is general and forms a fundamental approach to group equivariant neural networks. We believe that it can be easily adapted to other SOTA models in the future.

arXiv:2204.13902공식 코드 · Papers with Code

Fast Sampling of Diffusion Models with Exponential Integrator

The past few years have witnessed the great success of Diffusion models~(DMs) in generating high-fidelity samples in generative modeling tasks. A major limitation of the DM is its notoriously slow sampling procedure which normally requires hundreds to thousands of time discretization steps of the learned diffusion process to reach the desired accuracy. Our goal is to develop a fast sampling method for DMs with a much less number of steps while retaining high sample quality. To this end, we systematically analyze the sampling procedure in DMs and identify key factors that affect the sample quality, among which the method of discretization is most crucial. By carefully examining the learned diffusion process, we propose Diffusion Exponential Integrator Sampler~(DEIS). It is based on the Exponential Integrator designed for discretizing ordinary differential equations (ODEs) and leverages a semilinear structure of the learned diffusion process to reduce the discretization error. The proposed method can be applied to any DMs and can generate high-fidelity samples in as few as 10 steps. In our experiments, it takes about 3 minutes on one A6000 GPU to generate $50k$ images from CIFAR10. Moreover, by directly using pre-trained DMs, we achieve the state-of-art sampling performance when the number of score function evaluation~(NFE) is limited, e.g., 4.17 FID with 10 NFEs, 3.37 FID, and 9.74 IS with only 15 NFEs on CIFAR10. Code is available at https://github.com/qsh-zh/deis

arXiv:2204.13791

Depth Estimation with Simplified Transformer

Transformer and its variants have shown state-of-the-art results in many vision tasks recently, ranging from image classification to dense prediction. Despite of their success, limited work has been reported on improving the model efficiency for deployment in latency-critical applications, such as autonomous driving and robotic navigation. In this paper, we aim at improving upon the existing transformers in vision, and propose a method for self-supervised monocular Depth Estimation with Simplified Transformer (DEST), which is efficient and particularly suitable for deployment on GPU-based platforms. Through strategic design choices, our model leads to significant reduction in model size, complexity, as well as inference latency, while achieving superior accuracy as compared to state-of-the-art. We also show that our design generalize well to other dense prediction task without bells and whistles.

arXiv:2204.13596공식 코드 · Papers with Code

Generative Multi-hop Retrieval

A common practice for text retrieval is to use an encoder to map the documents and the query to a common vector space and perform a nearest neighbor search (NNS); multi-hop retrieval also often adopts the same paradigm, usually with a modification of iteratively reformulating the query vector so that it can retrieve different documents at each hop. However, such a bi-encoder approach has limitations in multi-hop settings; (1) the reformulated query gets longer as the number of hops increases, which further tightens the embedding bottleneck of the query vector, and (2) it is prone to error propagation. In this paper, we focus on alleviating these limitations in multi-hop settings by formulating the problem in a fully generative way. We propose an encoder-decoder model that performs multi-hop retrieval by simply generating the entire text sequences of the retrieval targets, which means the query and the documents interact in the language model's parametric space rather than L2 or inner product space as in the bi-encoder approach. Our approach, Generative Multi-hop Retrieval(GMR), consistently achieves comparable or higher performance than bi-encoder models in five datasets while demonstrating superior GPU memory and storage footprint.

arXiv:2204.13132공식 코드 · Papers with Code

HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation

Unsupervised domain adaptation (UDA) aims to adapt a model trained on the source domain (e.g. synthetic data) to the target domain (e.g. real-world data) without requiring further annotations on the target domain. This work focuses on UDA for semantic segmentation as real-world pixel-wise annotations are particularly expensive to acquire. As UDA methods for semantic segmentation are usually GPU memory intensive, most previous methods operate only on downscaled images. We question this design as low-resolution predictions often fail to preserve fine details. The alternative of training with random crops of high-resolution images alleviates this problem but falls short in capturing long-range, domain-robust context information. Therefore, we propose HRDA, a multi-resolution training approach for UDA, that combines the strengths of small high-resolution crops to preserve fine segmentation details and large low-resolution crops to capture long-range context dependencies with a learned scale attention, while maintaining a manageable GPU memory footprint. HRDA enables adapting small objects and preserving fine segmentation details. It significantly improves the state-of-the-art performance by 5.5 mIoU for GTA-to-Cityscapes and 4.9 mIoU for Synthia-to-Cityscapes, resulting in unprecedented 73.8 and 65.8 mIoU, respectively. The implementation is available at https://github.com/lhoyer/HRDA.

arXiv:2204.13307공식 코드 · Papers with Code

AlphaZero-Inspired Game Learning: Faster Training by Using MCTS Only at Test Time

Recently, the seminal algorithms AlphaGo and AlphaZero have started a new era in game learning and deep reinforcement learning. While the achievements of AlphaGo and AlphaZero - playing Go and other complex games at super human level - are truly impressive, these architectures have the drawback that they require high computational resources. Many researchers are looking for methods that are similar to AlphaZero, but have lower computational demands and are thus more easily reproducible. In this paper, we pick an important element of AlphaZero - the Monte Carlo Tree Search (MCTS) planning stage - and combine it with temporal difference (TD) learning agents. We wrap MCTS for the first time around TD n-tuple networks and we use this wrapping only at test time to create versatile agents that keep at the same time the computational demands low. We apply this new architecture to several complex games (Othello, ConnectFour, Rubik's Cube) and show the advantages achieved with this AlphaZero-inspired MCTS wrapper. In particular, we present results that this agent is the first one trained on standard hardware (no GPU or TPU) to beat the very strong Othello program Edax up to and including level 7 (where most other learning-from-scratch algorithms could only defeat Edax up to level 2).

arXiv:2204.13103공식 코드 · Papers with Code

FlowGNN: A Dataflow Architecture for Real-Time Workload-Agnostic Graph Neural Network Inference

Graph neural networks (GNNs) have recently exploded in popularity thanks to their broad applicability to graph-related problems such as quantum chemistry, drug discovery, and high energy physics. However, meeting demand for novel GNN models and fast inference simultaneously is challenging due to the gap between developing efficient accelerators and the rapid creation of new GNN models. Prior art focuses on accelerating specific classes of GNNs, such as Graph Convolutional Networks (GCN), but lacks generality to support a wide range of existing or new GNN models. Furthermore, most works rely on graph pre-processing to exploit data locality, making them unsuitable for real-time applications. To address these limitations, in this work, we propose a generic dataflow architecture for GNN acceleration, named FlowGNN, which is generalizable to the majority of message-passing GNNs. The contributions are three-fold. First, we propose a novel and scalable dataflow architecture, which generally supports a wide range of GNN models with message-passing mechanism. The architecture features a configurable dataflow optimized for simultaneous computation of node embedding, edge embedding, and message passing, which is generally applicable to all models. We also propose a rich library of model-specific components. Second, we deliver ultra-fast real-time GNN inference without any graph pre-processing, making it agnostic to dynamically changing graph structures. Third, we verify our architecture on the Xilinx Alveo U50 FPGA board and measure the on-board end-to-end performance. We achieve a speed-up of up to 24-254x against CPU (6226R) and 1.3-477x against GPU (A6000) (with batch sizes 1 through 1024); we also outperform the SOTA GNN accelerator I-GCN by 1.26x speedup and 1.55x energy efficiency over four datasets. Our implementation code and on-board measurement are publicly available on GitHub.

arXiv:2204.12726

PRE-NAS: Predictor-assisted Evolutionary Neural Architecture Search

Neural architecture search (NAS) aims to automate architecture engineering in neural networks. This often requires a high computational overhead to evaluate a number of candidate networks from the set of all possible networks in the search space during the search. Prediction of the networks' performance can alleviate this high computational overhead by mitigating the need for evaluating every candidate network. Developing such a predictor typically requires a large number of evaluated architectures which may be difficult to obtain. We address this challenge by proposing a novel evolutionary-based NAS strategy, Predictor-assisted E-NAS (PRE-NAS), which can perform well even with an extremely small number of evaluated architectures. PRE-NAS leverages new evolutionary search strategies and integrates high-fidelity weight inheritance over generations. Unlike one-shot strategies, which may suffer from bias in the evaluation due to weight sharing, offspring candidates in PRE-NAS are topologically homogeneous, which circumvents bias and leads to more accurate predictions. Extensive experiments on NAS-Bench-201 and DARTS search spaces show that PRE-NAS can outperform state-of-the-art NAS methods. With only a single GPU searching for 0.6 days, competitive architecture can be found by PRE-NAS which achieves 2.40% and 24% test error rates on CIFAR-10 and ImageNet respectively.

arXiv:2204.11838

Automating Neural Architecture Design without Search

Neural structure search (NAS), as the mainstream approach to automate deep neural architecture design, has achieved much success in recent years. However, the performance estimation component adhering to NAS is often prohibitively costly, which leads to the enormous computational demand. Though a large number of efforts have been dedicated to alleviating this pain point, no consensus has been made yet on which is optimal. In this paper, we study the automated architecture design from a new perspective that eliminates the need to sequentially evaluate each neural architecture generated during algorithm execution. Specifically, the proposed approach is built by learning the knowledge of high-level experts in designing state-of-the-art architectures, and then the new architecture is directly generated upon the knowledge learned. We implemented the proposed approach by using a graph neural network for link prediction and acquired the knowledge from NAS-Bench-101. Compared to existing peer competitors, we found a competitive network with minimal cost. In addition, we also utilized the learned knowledge from NAS-Bench-101 to automate architecture design in the DARTS search space, and achieved 97.82% accuracy on CIFAR10, and 76.51% top-1 accuracy on ImageNet consuming only $2\times10^{-4}$ GPU days. This also demonstrates the high transferability of the proposed approach, and can potentially lead to a new, more computationally efficient paradigm in this research direction.

arXiv:2204.12346

On automatic calibration of the SIRD epidemiological model for COVID-19 data in Poland

We propose a novel methodology for estimating the epidemiological parameters of a modified SIRD model (acronym of Susceptible, Infected, Recovered and Deceased individuals) and perform a short-term forecast of SARS-CoV-2 virus spread. We mainly focus on forecasting number of deceased. The procedure was tested on reported data for Poland. For some short-time intervals we performed numerical test investigating stability of parameter estimates in the proposed approach. Numerical experiments confirm the effectiveness of short-term forecasts (up to 2 weeks) and stability of the method. To improve their performance (i.e. computation time) GPU architecture was used in computations.

arXiv:2204.11850

Memory Efficient Invertible Neural Networks for 3D Photoacoustic Imaging

Photoacoustic imaging (PAI) can image high-resolution structures of clinical interest such as vascularity in cancerous tumor monitoring. When imaging human subjects, geometric restrictions force limited-view data retrieval causing imaging artifacts. Iterative physical model based approaches reduce artifacts but require prohibitively time consuming PDE solves. Machine learning (ML) has accelerated PAI by combining physical models and learned networks. However, the depth and overall power of ML methods is limited by memory intensive training. We propose using invertible neural networks (INNs) to alleviate memory pressure. We demonstrate INNs can image 3D photoacoustic volumes in the setting of limited-view, noisy, and subsampled data. The frugal constant memory usage of INNs enables us to train an arbitrary depth of learned layers on a consumer GPU with 16GB RAM.

arXiv:2204.10586

Efficient Training of Neural Transducer for Speech Recognition

As one of the most popular sequence-to-sequence modeling approaches for speech recognition, the RNN-Transducer has achieved evolving performance with more and more sophisticated neural network models of growing size and increasing training epochs. While strong computation resources seem to be the prerequisite of training superior models, we try to overcome it by carefully designing a more efficient training pipeline. In this work, we propose an efficient 3-stage progressive training pipeline to build highly-performing neural transducer models from scratch with very limited computation resources in a reasonable short time period. The effectiveness of each stage is experimentally verified on both Librispeech and Switchboard corpora. The proposed pipeline is able to train transducer models approaching state-of-the-art performance with a single GPU in just 2-3 weeks. Our best conformer transducer achieves 4.1% WER on Librispeech test-other with only 35 epochs of training.

arXiv:2204.10356공식 코드 · Papers with Code

Interactive Segmentation and Visualization for Tiny Objects in Multi-megapixel Images

We introduce an interactive image segmentation and visualization framework for identifying, inspecting, and editing tiny objects (just a few pixels wide) in large multi-megapixel high-dynamic-range (HDR) images. Detecting cosmic rays (CRs) in astronomical observations is a cumbersome workflow that requires multiple tools, so we developed an interactive toolkit that unifies model inference, HDR image visualization, segmentation mask inspection and editing into a single graphical user interface. The feature set, initially designed for astronomical data, makes this work a useful research-supporting tool for human-in-the-loop tiny-object segmentation in scientific areas like biomedicine, materials science, remote sensing, etc., as well as computer vision. Our interface features mouse-controlled, synchronized, dual-window visualization of the image and the segmentation mask, a critical feature for locating tiny objects in multi-megapixel images. The browser-based tool can be readily hosted on the web to provide multi-user access and GPU acceleration for any device. The toolkit can also be used as a high-precision annotation tool, or adapted as the frontend for an interactive machine learning framework. Our open-source dataset, CR detection model, and visualization toolkit are available at https://github.com/cy-xu/cosmic-conn.

arXiv:2204.09934공식 코드 · Papers with Code

FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis

Denoising diffusion probabilistic models (DDPMs) have recently achieved leading performances in many generative tasks. However, the inherited iterative sampling process costs hindered their applications to speech synthesis. This paper proposes FastDiff, a fast conditional diffusion model for high-quality speech synthesis. FastDiff employs a stack of time-aware location-variable convolutions of diverse receptive field patterns to efficiently model long-term time dependencies with adaptive conditions. A noise schedule predictor is also adopted to reduce the sampling steps without sacrificing the generation quality. Based on FastDiff, we design an end-to-end text-to-speech synthesizer, FastDiff-TTS, which generates high-fidelity speech waveforms without any intermediate feature (e.g., Mel-spectrogram). Our evaluation of FastDiff demonstrates the state-of-the-art results with higher-quality (MOS 4.28) speech samples. Also, FastDiff enables a sampling speed of 58x faster than real-time on a V100 GPU, making diffusion models practically applicable to speech synthesis deployment for the first time. We further show that FastDiff generalized well to the mel-spectrogram inversion of unseen speakers, and FastDiff-TTS outperformed other competing methods in end-to-end text-to-speech synthesis. Audio samples are available at \url{https://FastDiff.github.io/}.

arXiv:2204.09656공식 코드 · Papers with Code

A Fast Post-Training Pruning Framework for Transformers

Pruning is an effective way to reduce the huge inference cost of Transformer models. However, prior work on pruning Transformers requires retraining the models. This can add high training cost and high complexity to model deployment, making it difficult to use in many practical situations. To address this, we propose a fast post-training pruning framework for Transformers that does not require any retraining. Given a resource constraint and a sample dataset, our framework automatically prunes the Transformer model using structured sparsity methods. To retain high accuracy without retraining, we introduce three novel techniques: (i) a lightweight mask search algorithm that finds which heads and filters to prune based on the Fisher information; (ii) mask rearrangement that complements the search algorithm; and (iii) mask tuning that reconstructs the output activations for each layer. We apply our method to BERT-base and DistilBERT, and we evaluate its effectiveness on GLUE and SQuAD benchmarks. Our framework achieves up to 2.0x reduction in FLOPs and 1.56x speedup in inference latency, while maintaining < 1% loss in accuracy. Importantly, our framework prunes Transformers in less than 3 minutes on a single GPU, which is over two orders of magnitude faster than existing pruning approaches that retrain the models.

arXiv:2204.09227

Cross-stitched Multi-modal Encoders

In this paper, we propose a novel architecture for multi-modal speech and text input. We combine pretrained speech and text encoders using multi-headed cross-modal attention and jointly fine-tune on the target problem. The resultant architecture can be used for continuous token-level classification or utterance-level prediction acting on simultaneous text and speech. The resultant encoder efficiently captures both acoustic-prosodic and lexical information. We compare the benefits of multi-headed attention-based fusion for multi-modal utterance-level classification against a simple concatenation of pre-pooled, modality-specific representations. Our model architecture is compact, resource efficient, and can be trained on a single consumer GPU card.

arXiv:2204.08988공식 코드 · Papers with Code

CPU- and GPU-based Distributed Sampling in Dirichlet Process Mixtures for Large-scale Analysis

In the realm of unsupervised learning, Bayesian nonparametric mixture models, exemplified by the Dirichlet Process Mixture Model (DPMM), provide a principled approach for adapting the complexity of the model to the data. Such models are particularly useful in clustering tasks where the number of clusters is unknown. Despite their potential and mathematical elegance, however, DPMMs have yet to become a mainstream tool widely adopted by practitioners. This is arguably due to a misconception that these models scale poorly as well as the lack of high-performance (and user-friendly) software tools that can handle large datasets efficiently. In this paper we bridge this practical gap by proposing a new, easy-to-use, statistical software package for scalable DPMM inference. More concretely, we provide efficient and easily-modifiable implementations for high-performance distributed sampling-based inference in DPMMs where the user is free to choose between either a multiple-machine, multiple-core, CPU implementation (written in Julia) and a multiple-stream GPU implementation (written in CUDA/C++). Both the CPU and GPU implementations come with a common (and optional) python wrapper, providing the user with a single point of entry with the same interface. On the algorithmic side, our implementations leverage a leading DPMM sampler from (Chang and Fisher III, 2013). While Chang and Fisher III's implementation (written in MATLAB/C++) used only CPU and was designed for a single multi-core machine, the packages we proposed here distribute the computations efficiently across either multiple multi-core machines or across mutiple GPU streams. This leads to speedups, alleviates memory and storage limitations, and lets us fit DPMMs to significantly larger datasets and of higher dimensionality than was possible previously by either (Chang and Fisher III, 2013) or other DPMM methods.

arXiv:2204.08269공식 코드 · Papers with Code

Differentiable Time-Frequency Scattering on GPU

Joint time-frequency scattering (JTFS) is a convolutional operator in the time-frequency domain which extracts spectrotemporal modulations at various rates and scales. It offers an idealized model of spectrotemporal receptive fields (STRF) in the primary auditory cortex, and thus may serve as a biological plausible surrogate for human perceptual judgments at the scale of isolated audio events. Yet, prior implementations of JTFS and STRF have remained outside of the standard toolkit of perceptual similarity measures and evaluation methods for audio generation. We trace this issue down to three limitations: differentiability, speed, and flexibility. In this paper, we present an implementation of time-frequency scattering in Python. Unlike prior implementations, ours accommodates NumPy, PyTorch, and TensorFlow as backends and is thus portable on both CPU and GPU. We demonstrate the usefulness of JTFS via three applications: unsupervised manifold learning of spectrotemporal modulations, supervised classification of musical instruments, and texture resynthesis of bioacoustic sounds.