PyTorchKR Papers

최신 논문

총 5,576편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2203.04074공식 코드 · Papers with Code

E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation

Contour-based instance segmentation methods have developed rapidly recently but feature rough and hand-crafted front-end contour initialization, which restricts the model performance, and an empirical and fixed backend predicted-label vertex pairing, which contributes to the learning difficulty. In this paper, we introduce a novel contour-based method, named E2EC, for high-quality instance segmentation. Firstly, E2EC applies a novel learnable contour initialization architecture instead of hand-crafted contour initialization. This consists of a contour initialization module for constructing more explicit learning goals and a global contour deformation module for taking advantage of all of the vertices' features better. Secondly, we propose a novel label sampling scheme, named multi-direction alignment, to reduce the learning difficulty. Thirdly, to improve the quality of the boundary details, we dynamically match the most appropriate predicted-ground truth vertex pairs and propose the corresponding loss function named dynamic matching loss. The experiments showed that E2EC can achieve a state-of-the-art performance on the KITTI INStance (KINS) dataset, the Semantic Boundaries Dataset (SBD), the Cityscapes and the COCO dataset. E2EC is also efficient for use in real-time applications, with an inference speed of 36 fps for 512*512 images on an NVIDIA A6000 GPU. Code will be released at https://github.com/zhang-tao-whu/e2ec.

arXiv:2203.03689공식 코드 · Papers with Code

WaveMix: Resource-efficient Token Mixing for Images

Although certain vision transformer (ViT) and CNN architectures generalize well on vision tasks, it is often impractical to use them on green, edge, or desktop computing due to their computational requirements for training and even testing. We present WaveMix as an alternative neural architecture that uses a multi-scale 2D discrete wavelet transform (DWT) for spatial token mixing. Unlike ViTs, WaveMix neither unrolls the image nor requires self-attention of quadratic complexity. Additionally, DWT introduces another inductive bias -- besides convolutional filtering -- to utilize the 2D structure of an image to improve generalization. The multi-scale nature of the DWT also reduces the requirement for a deeper architecture compared to the CNNs, as the latter relies on pooling for partial spatial mixing. WaveMix models show generalization that is competitive with ViTs, CNNs, and token mixers on several datasets while requiring lower GPU RAM (training and testing), number of computations, and storage. WaveMix have achieved State-of-the-art (SOTA) results in EMNIST Byclass and EMNIST Balanced datasets.

arXiv:2203.02530

Machine Learning for CUDA+MPI Design Rules

We present a new strategy for automatically exploring the design space of key CUDA+MPI programs and providing design rules that discriminate slow from fast implementations. In such programs, the order of operations (e.g., GPU kernels, MPI communication) and assignment of operations to resources (e.g., GPU streams) makes the space of possible designs enormous. Systems experts have the task of redesigning and reoptimizing these programs to effectively utilize each new platform. This work provides a prototype tool to reduce that burden. In our approach, a directed acyclic graph of CUDA and MPI operations defines the design space for the program. Monte-Carlo tree search discovers regions of the design space that have large impact on the program's performance. A sequence-to-vector transformation defines features for each explored implementation, and each implementation is assigned a class label according to its relative performance. A decision tree is trained on the features and labels to produce design rules for each class; these rules can be used by systems experts to guide their implementations. We demonstrate our strategy using a key kernel from scientific computing -- sparse-matrix vector multiplication -- on a platform with multiple MPI ranks and GPU streams.

arXiv:2203.03226공식 코드 · Papers with Code

Signature and Log-signature for the Study of Empirical Distributions Generated with GANs

In this paper, we bring forward the use of the recently developed Signature Transform as a way to measure the similarity between image distributions and provide detailed acquaintance and extensive evaluations. We are the first to pioneer RMSE and MAE Signature, along with log-signature as an alternative to measure GAN convergence, a problem that has been extensively studied. We are also forerunners to introduce analytical measures based on statistics to study the goodness of fit of the GAN sample distribution that are both efficient and effective. Current GAN measures involve lots of computation normally done at the GPU and are very time consuming. In contrast, we diminish the computation time to the order of seconds and computation is done at the CPU achieving the same level of goodness. Lastly, a PCA adaptive t-SNE approach, which is novel in this context, is also proposed for data visualization.

arXiv:2203.02651공식 코드 · Papers with Code

Ensemble Knowledge Guided Sub-network Search and Fine-tuning for Filter Pruning

Conventional NAS-based pruning algorithms aim to find the sub-network with the best validation performance. However, validation performance does not successfully represent test performance, i.e., potential performance. Also, although fine-tuning the pruned network to restore the performance drop is an inevitable process, few studies have handled this issue. This paper provides a novel Ensemble Knowledge Guidance (EKG) to solve both problems at once. First, we experimentally prove that the fluctuation of loss landscape can be an effective metric to evaluate the potential performance. In order to search a sub-network with the smoothest loss landscape at a low cost, we employ EKG as a search reward. EKG utilized for the following search iteration is composed of the ensemble knowledge of interim sub-networks, i.e., the by-products of the sub-network evaluation. Next, we reuse EKG to provide a gentle and informative guidance to the pruned network while fine-tuning the pruned network. Since EKG is implemented as a memory bank in both phases, it requires a negligible cost. For example, when pruning and training ResNet-50, just 315 GPU hours are required to remove around 45.04% of FLOPS without any performance degradation, which can operate even on a low-spec workstation. the implemented code is available at https://github.com/sseung0703/EKG.

arXiv:2203.02094공식 코드 · Papers with Code

LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models

The Transformer architecture is ubiquitously used as the building block of large-scale autoregressive language models. However, finding architectures with the optimal trade-off between task performance (perplexity) and hardware constraints like peak memory utilization and latency is non-trivial. This is exacerbated by the proliferation of various hardware. We leverage the somewhat surprising empirical observation that the number of decoder parameters in autoregressive Transformers has a high rank correlation with task performance, irrespective of the architecture topology. This observation organically induces a simple Neural Architecture Search (NAS) algorithm that uses decoder parameters as a proxy for perplexity without need for any model training. The search phase of our training-free algorithm, dubbed Lightweight Transformer Search (LTS), can be run directly on target devices since it does not require GPUs. Using on-target-device measurements, LTS extracts the Pareto-frontier of perplexity versus any hardware performance cost. We evaluate LTS on diverse devices from ARM CPUs to NVIDIA GPUs and two popular autoregressive Transformer backbones: GPT-2 and Transformer-XL. Results show that the perplexity of 16-layer GPT-2 and Transformer-XL can be achieved with up to 1.5x, 2.5x faster runtime and 1.2x, 2.0x lower peak memory utilization. When evaluated in zero and one-shot settings, LTS Pareto-frontier models achieve higher average accuracy compared to the 350M parameter OPT across 14 tasks, with up to 1.6x lower latency. LTS extracts the Pareto-frontier in under 3 hours while running on a commodity laptop. We effectively remove the carbon footprint of hundreds of GPU hours of training during search, offering a strong simple baseline for future NAS methods in autoregressive language modeling.

arXiv:2203.02300

Mixed Reality Depth Contour Occlusion Using Binocular Similarity Matching and Three-dimensional Contour Optimisation

Mixed reality applications often require virtual objects that are partly occluded by real objects. However, previous research and commercial products have limitations in terms of performance and efficiency. To address these challenges, we propose a novel depth contour occlusion (DCO) algorithm. The proposed method is based on the sensitivity of contour occlusion and a binocular stereoscopic vision device. In this method, a depth contour map is combined with a sparse depth map obtained from a two-stage adaptive filter area stereo matching algorithm and the depth contour information of the objects extracted by a digital image stabilisation optical flow method. We also propose a quadratic optimisation model with three constraints to generate an accurate dense map of the depth contour for high-quality real-virtual occlusion. The whole process is accelerated by GPU. To evaluate the effectiveness of the algorithm, we demonstrate a time con-sumption statistical analysis for each stage of the DCO algorithm execution. To verify the relia-bility of the real-virtual occlusion effect, we conduct an experimental analysis on single-sided, enclosed, and complex occlusions; subsequently, we compare it with the occlusion method without quadratic optimisation. With our GPU implementation for real-time DCO, the evaluation indicates that applying the presented DCO algorithm can enhance the real-time performance and the visual quality of real-virtual occlusion.

arXiv:2203.02281

A Comprehensive Review of Computer Vision in Sports: Open Issues, Future Trends and Research Directions

Recent developments in video analysis of sports and computer vision techniques have achieved significant improvements to enable a variety of critical operations. To provide enhanced information, such as detailed complex analysis in sports like soccer, basketball, cricket, badminton, etc., studies have focused mainly on computer vision techniques employed to carry out different tasks. This paper presents a comprehensive review of sports video analysis for various applications high-level analysis such as detection and classification of players, tracking player or ball in sports and predicting the trajectories of player or ball, recognizing the teams strategies, classifying various events in sports. The paper further discusses published works in a variety of application-specific tasks related to sports and the present researchers views regarding them. Since there is a wide research scope in sports for deploying computer vision techniques in various sports, some of the publicly available datasets related to a particular sport have been provided. This work reviews a detailed discussion on some of the artificial intelligence(AI)applications in sports vision, GPU-based work stations, and embedded platforms. Finally, this review identifies the research directions, probable challenges, and future trends in the area of visual recognition in sports.

arXiv:2203.02098

Universal Segmentation of 33 Anatomies

In the paper, we present an approach for learning a single model that universally segments 33 anatomical structures, including vertebrae, pelvic bones, and abdominal organs. Our model building has to address the following challenges. Firstly, while it is ideal to learn such a model from a large-scale, fully-annotated dataset, it is practically hard to curate such a dataset. Thus, we resort to learn from a union of multiple datasets, with each dataset containing the images that are partially labeled. Secondly, along the line of partial labelling, we contribute an open-source, large-scale vertebra segmentation dataset for the benefit of spine analysis community, CTSpine1K, boasting over 1,000 3D volumes and over 11K annotated vertebrae. Thirdly, in a 3D medical image segmentation task, due to the limitation of GPU memory, we always train a model using cropped patches as inputs instead a whole 3D volume, which limits the amount of contextual information to be learned. To this, we propose a cross-patch transformer module to fuse more information in adjacent patches, which enlarges the aggregated receptive field for improved segmentation performance. This is especially important for segmenting, say, the elongated spine. Based on 7 partially labeled datasets that collectively contain about 2,800 3D volumes, we successfully learn such a universal model. Finally, we evaluate the universal model on multiple open-source datasets, proving that our model has a good generalization performance and can potentially serve as a solid foundation for downstream tasks.

arXiv:2203.01877

Query Processing on Tensor Computation Runtimes

The huge demand for computation in artificial intelligence (AI) is driving unparalleled investments in hardware and software systems for AI. This leads to an explosion in the number of specialized hardware devices, which are now offered by major cloud vendors. By hiding the low-level complexity through a tensor-based interface, tensor computation runtimes (TCRs) such as PyTorch allow data scientists to efficiently exploit the exciting capabilities offered by the new hardware. In this paper, we explore how database management systems can ride the wave of innovation happening in the AI space. We design, build, and evaluate Tensor Query Processor (TQP): TQP transforms SQL queries into tensor programs and executes them on TCRs. TQP is able to run the full TPC-H benchmark by implementing novel algorithms for relational operators on the tensor routines. At the same time, TQP can support various hardware while only requiring a fraction of the usual development effort. Experiments show that TQP can improve query execution time by up to 10$\times$ over specialized CPU- and GPU-only systems. Finally, TQP can accelerate queries mixing ML predictions and SQL end-to-end, and deliver up to 9$\times$ speedup over CPU baselines.

arXiv:2203.01282공식 코드 · Papers with Code

py-irt: A Scalable Item Response Theory Library for Python

py-irt is a Python library for fitting Bayesian Item Response Theory (IRT) models. py-irt estimates latent traits of subjects and items, making it appropriate for use in IRT tasks as well as ideal-point models. py-irt is built on top of the Pyro and PyTorch frameworks and uses GPU-accelerated training to scale to large data sets. Code, documentation, and examples can be found at https://github.com/nd-ball/py-irt. py-irt can be installed from the GitHub page or the Python Package Index (PyPI).

논문 ID: 2022.10238

StaSiS-Net: a stacked and siamese stereo network for depth reconstruction in modern 3D laparoscopy.

Accurate and real-time methodologies for a non-invasive three-dimensional representa-tion and reconstruction of internal patient structures is one of the main research fieldsin computer-assisted surgery and endoscopy. Mono and stereo endoscopic images ofsoft tissues are converted into a three-dimensional representation by the estimation ofdepth maps. However, automatic, detailed, accurate and robust depth map estimationis a challenging problem which, moreover, is strictly dependent on a robust estimateof the disparity map. Many traditional algorithms are often inefficient or not accu-rate. In this work, novel self-supervised stacked and Siamese encoder/decoder neuralnetworks are proposed to compute accurate disparity maps for 3D laparoscopy depthreconstructions. These networks produce disparities in real-time on standard GPU-equipped desktop computers and after, with a minimal parameter configuration theirdepth reconstruction. We compare their performance on three different public datasetsand on a new challenging simulated dataset and they outperform state-of-the-art monoand stereo depth estimation methods. Extensive robustness and sensitivity analyses onmore than 30 000 frames has been performed. This work leads to important improve-ments in mono and stereo real-time depth estimations of soft tissues and organs with avery low average mean absolute disparity reconstruction error with respect to groundtruth.

논문 ID: document/9718415

Cardiotocogram Biomedical Signal Classification and Interpretation for Fetal Health Evaluation

Maternal and Neonatal health has been greatly constrained by the in-access to essential maternal health care services due to the preventive measures implemented against the spread of covid-19 hence making maternal and fetal monitoring so hard for physicians. Besides maternal toxic stress caused by fear of catching covid-19, affordable mobility of pregnant mothers to skilled health practitioners in limited resource settings is another contributor to maternal and neonatal mortality and morbidity. In this work, we leveraged existing health data to build interpretable Machine Learning (ML) models that allow physicians to offer precision maternal and fetal medicine based on biomedical signal classification results of fetal cardiotocograms (CTGs).We obtained 99%, 100% and 97% accuracy, precision and recall respectively for the LightGBM classification model without any GPU Learning resources. Then we explainably evaluated all built models with ELI5 and comprehensive feature extraction.

arXiv:2202.13564

Towards Machine Learning for Placement and Routing in Chip Design: a Methodological Overview

Placement and routing are two indispensable and challenging (NP-hard) tasks in modern chip design flows. Compared with traditional solvers using heuristics or expert-well-designed algorithms, machine learning has shown promising prospects by its data-driven nature, which can be of less reliance on knowledge and priors, and potentially more scalable by its advanced computational paradigms (e.g. deep networks with GPU acceleration). This survey starts with the introduction of basics of placement and routing, with a brief description on classic learning-free solvers. Then we present detailed review on recent advance in machine learning for placement and routing. Finally we discuss the challenges and opportunities for future research.

arXiv:2202.13638

GPU-Accelerated Policy Optimization via Batch Automatic Differentiation of Gaussian Processes for Real-World Control

The ability of Gaussian processes (GPs) to predict the behavior of dynamical systems as a more sample-efficient alternative to parametric models seems promising for real-world robotics research. However, the computational complexity of GPs has made policy search a highly time and memory consuming process that has not been able to scale to larger problems. In this work, we develop a policy optimization method by leveraging fast predictive sampling methods to process batches of trajectories in every forward pass, and compute gradient updates over policy parameters by automatic differentiation of Monte Carlo evaluations, all on GPU. We demonstrate the effectiveness of our approach in training policies on a set of reference-tracking control experiments with a heavy-duty machine. Benchmark results show a significant speedup over exact methods and showcase the scalability of our method to larger policy networks, longer horizons, and up to thousands of trajectories with a sublinear drop in speed.

arXiv:2202.13799

One-shot Ultra-high-Resolution Generative Adversarial Network That Synthesizes 16K Images On A Single GPU

We propose a one-shot ultra-high-resolution generative adversarial network (OUR-GAN) framework that generates non-repetitive 16K (16, 384 x 8, 640) images from a single training image and is trainable on a single consumer GPU. OUR-GAN generates an initial image that is visually plausible and varied in shape at low resolution, and then gradually increases the resolution by adding detail through super-resolution. Since OUR-GAN learns from a real ultra-high-resolution (UHR) image, it can synthesize large shapes with fine details and long-range coherence, which is difficult to achieve with conventional generative models that rely on the patch distribution learned from relatively small images. OUR-GAN can synthesize high-quality 16K images with 12.5 GB of GPU memory and 4K images with only 4.29 GB as it synthesizes a UHR image part by part through seamless subregion-wise super-resolution. Additionally, OUR-GAN improves visual coherence while maintaining diversity by applying vertical positional convolution. In experiments on the ST4K and RAISE datasets, OUR-GAN exhibited improved fidelity, visual coherency, and diversity compared with the baseline one-shot synthesis models. To the best of our knowledge, OUR-GAN is the first one-shot image synthesizer that generates non-repetitive UHR images on a single consumer GPU. The synthesized image samples are presented at https://our-gan.github.io.

arXiv:2202.13481

PARIS and ELSA: An Elastic Scheduling Algorithm for Reconfigurable Multi-GPU Inference Servers

In cloud machine learning (ML) inference systems, providing low latency to end-users is of utmost importance. However, maximizing server utilization and system throughput is also crucial for ML service providers as it helps lower the total-cost-of-ownership. GPUs have oftentimes been criticized for ML inference usages as its massive compute and memory throughput is hard to be fully utilized under low-batch inference scenarios. To address such limitation, NVIDIA's recently announced Ampere GPU architecture provides features to "reconfigure" one large, monolithic GPU into multiple smaller "GPU partitions". Such feature provides cloud ML service providers the ability to utilize the reconfigurable GPU not only for large-batch training but also for small-batch inference with the potential to achieve high resource utilization. In this paper, we study this emerging GPU architecture with reconfigurability to develop a high-performance multi-GPU ML inference server. Our first proposition is a sophisticated partitioning algorithm for reconfigurable GPUs that systematically determines a heterogeneous set of multi-granular GPU partitions, best suited for the inference server's deployment. Furthermore, we co-design an elastic scheduling algorithm tailored for our heterogeneously partitioned GPU server which effectively balances low latency and high GPU utilization.

arXiv:2202.13808공식 코드 · Papers with Code

DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN Training

A standard hardware bottleneck when training deep neural networks is GPU memory. The bulk of memory is occupied by caching intermediate tensors for gradient computation in the backward pass. We propose a novel method to reduce this footprint - Dropping Intermediate Tensors (DropIT). DropIT drops min-k elements of the intermediate tensors and approximates gradients from the sparsified tensors in the backward pass. Theoretically, DropIT reduces noise on estimated gradients and therefore has a higher rate of convergence than vanilla-SGD. Experiments show that we can drop up to 90\% of the intermediate tensor elements in fully-connected and convolutional layers while achieving higher testing accuracy for Visual Transformers and Convolutional Neural Networks on various tasks (e.g., classification, object detection, instance segmentation). Our code and models are available at https://github.com/chenjoya/dropit.

arXiv:2202.12510공식 코드 · Papers with Code

Asyncval: A Toolkit for Asynchronously Validating Dense Retriever Checkpoints during Training

The process of model checkpoint validation refers to the evaluation of the performance of a model checkpoint executed on a held-out portion of the training data while learning the hyperparameters of the model, and is used to avoid over-fitting and determine when the model has converged so as to stop training. A simple and efficient strategy to validate deep learning checkpoints is the addition of validation loops to execute during training. However, the validation of dense retrievers (DR) checkpoints is not as trivial -- and the addition of validation loops is not efficient. This is because, in order to accurately evaluate the performance of a DR checkpoint, the whole document corpus needs to be encoded into vectors using the current checkpoint before any actual retrieval operation for checkpoint validation can be performed. This corpus encoding process can be very time-consuming if the document corpus contains millions of documents (e.g., 8.8m for MS MARCO and 21m for Natural Questions). Thus, a naive use of validation loops during training will significantly increase training time. To address this issue, in this demo paper, we propose Asyncval: a Python-based toolkit for efficiently validating DR checkpoints during training. Instead of pausing the training loop for validating DR checkpoints, Asyncval decouples the validation loop from the training loop, uses another GPU to automatically validate new DR checkpoints and thus permits to perform validation asynchronously from training. Asyncval also implements a range of different corpus subset sampling strategies for validating DR checkpoints; these strategies allow to further speed up the validation process. We provide an investigation of these methods in terms of their impact on validation time and validation fidelity. Asyncval is made available as an open-source project at https://github.com/ielab/asyncval.

arXiv:2202.12210공식 코드 · Papers with Code

BERTVision -- A Parameter-Efficient Approach for Question Answering

We present a highly parameter efficient approach for Question Answering that significantly reduces the need for extended BERT fine-tuning. Our method uses information from the hidden state activations of each BERT transformer layer, which is discarded during typical BERT inference. Our best model achieves maximal BERT performance at a fraction of the training time and GPU or TPU expense. Performance is further improved by ensembling our model with BERTs predictions. Furthermore, we find that near optimal performance can be achieved for QA span annotation using less training data. Our experiments show that this approach works well not only for span annotation, but also for classification, suggesting that it may be extensible to a wider range of tasks.