PyTorchKR Papers

최신 논문

총 2,153편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2405.17934

Proof of Quality: A Costless Paradigm for Trustless Generative AI Model Inference on Blockchains

Generative AI models, such as GPT-4 and Stable Diffusion, have demonstrated powerful and disruptive capabilities in natural language and image tasks. However, deploying these models in decentralized environments remains challenging. Unlike traditional centralized deployment, systematically guaranteeing the integrity of AI model services in fully decentralized environments, particularly on trustless blockchains, is both crucial and difficult. In this paper, we present a new inference paradigm called \emph{proof of quality} (PoQ) to enable the deployment of arbitrarily large generative models on blockchain architecture. Unlike traditional approaches based on validating inference procedures, such as ZKML or OPML, our PoQ paradigm focuses on the outcome quality of model inference. Using lightweight BERT-based cross-encoders as our underlying quality evaluation model, we design and implement PQML, the first practical protocol for real-world NLP generative model inference on blockchains, tailored for popular open-source models such as Llama 3 and Mixtral. Our analysis demonstrates that our protocol is robust against adversarial but rational participants in ecosystems, where lazy or dishonest behavior results in fewer benefits compared to well-behaving participants. The computational overhead of validating the quality evaluation is minimal, allowing quality validators to complete the quality check within a second, even using only a CPU. Preliminary simulation results show that PoQ consensus is generated in milliseconds, 1,000 times faster than any existing scheme.

arXiv:2405.16096공식 코드 · Papers with Code

MINet: Multi-scale Interactive Network for Real-time Salient Object Detection of Strip Steel Surface Defects

The automated surface defect detection is a fundamental task in industrial production, and the existing saliencybased works overcome the challenging scenes and give promising detection results. However, the cutting-edge efforts often suffer from large parameter size, heavy computational cost, and slow inference speed, which heavily limits the practical applications. To this end, we devise a multi-scale interactive (MI) module, which employs depthwise convolution (DWConv) and pointwise convolution (PWConv) to independently extract and interactively fuse features of different scales, respectively. Particularly, the MI module can provide satisfactory characterization for defect regions with fewer parameters. Embarking on this module, we propose a lightweight Multi-scale Interactive Network (MINet) to conduct real-time salient object detection of strip steel surface defects. Comprehensive experimental results on SD-Saliency-900 dataset, which contains three kinds of strip steel surface defect detection images (i.e., inclusion, patches, and scratches), demonstrate that the proposed MINet presents comparable detection accuracy with the state-of-the-art methods while running at a GPU speed of 721FPS and a CPU speed of 6.3FPS for 368*368 images with only 0.28M parameters. The code is available at https://github.com/Kunye-Shen/MINet.

arXiv:2405.14185공식 코드 · Papers with Code

A Structure-Aware Framework for Learning Device Placements on Computation Graphs

Computation graphs are Directed Acyclic Graphs (DAGs) where the nodes correspond to mathematical operations and are used widely as abstractions in optimizations of neural networks. The device placement problem aims to identify optimal allocations of those nodes to a set of (potentially heterogeneous) devices. Existing approaches rely on two types of architectures known as grouper-placer and encoder-placer, respectively. In this work, we bridge the gap between encoder-placer and grouper-placer techniques and propose a novel framework for the task of device placement, relying on smaller computation graphs extracted from the OpenVINO toolkit. The framework consists of five steps, including graph coarsening, node representation learning and policy optimization. It facilitates end-to-end training and takes into account the DAG nature of the computation graphs. We also propose a model variant, inspired by graph parsing networks and complex network analysis, enabling graph representation learning and jointed, personalized graph partitioning, using an unspecified number of groups. To train the entire framework, we use reinforcement learning using the execution time of the placement as a reward. We demonstrate the flexibility and effectiveness of our approach through multiple experiments with three benchmark models, namely Inception-V3, ResNet, and BERT. The robustness of the proposed framework is also highlighted through an ablation study. The suggested placements improve the inference speed for the benchmark models by up to 58.2% over CPU execution and by up to 60.24% compared to other commonly used baselines.

arXiv:2405.14453

Domain-specific augmentations with resolution agnostic self-attention mechanism improves choroid segmentation in optical coherence tomography images

The choroid is a key vascular layer of the eye, supplying oxygen to the retinal photoreceptors. Non-invasive enhanced depth imaging optical coherence tomography (EDI-OCT) has recently improved access and visualisation of the choroid, making it an exciting frontier for discovering novel vascular biomarkers in ophthalmology and wider systemic health. However, current methods to measure the choroid often require use of multiple, independent semi-automatic and deep learning-based algorithms which are not made open-source. Previously, Choroidalyzer -- an open-source, fully automatic deep learning method trained on 5,600 OCT B-scans from 385 eyes -- was developed to fully segment and quantify the choroid in EDI-OCT images, thus addressing these issues. Using the same dataset, we propose a Robust, Resolution-agnostic and Efficient Attention-based network for CHoroid segmentation (REACH). REACHNet leverages multi-resolution training with domain-specific data augmentation to promote generalisation, and uses a lightweight architecture with resolution-agnostic self-attention which is not only faster than Choroidalyzer's previous network (4 images/s vs. 2.75 images/s on a standard laptop CPU), but has greater performance for segmenting the choroid region, vessels and fovea (Dice coefficient for region 0.9769 vs. 0.9749, vessels 0.8612 vs. 0.8192 and fovea 0.8243 vs. 0.3783) due to its improved hyperparameter configuration and model training pipeline. REACHNet can be used with Choroidalyzer as a drop-in replacement for the original model and will be made available upon publication.

arXiv:2405.13938

eXmY: A Data Type and Technique for Arbitrary Bit Precision Quantization

eXmY is a novel data type for quantization of ML models. It supports both arbitrary bit widths and arbitrary integer and floating point formats. For example, it seamlessly supports 3, 5, 6, 7, 9 bit formats. For a specific bit width, say 7, it defines all possible formats e.g. e0m6, e1m5, e2m4, e3m3, e4m2, e5m1 and e6m0. For non-power of two bit widths e.g. 5, 6, 7, we created a novel encoding and decoding scheme which achieves perfect compression, byte addressability and is amenable to sharding and vector processing. We implemented libraries for emulation, encoding and decoding tensors and checkpoints in C++, TensorFlow, JAX and PAX. For optimal performance, the codecs use SIMD instructions on CPUs and vector instructions on TPUs and GPUs. eXmY is also a technique and exploits the statistical distribution of exponents in tensors. It can be used to quantize weights, static and dynamic activations, gradients, master weights and optimizer state. It can reduce memory (CPU DRAM and accelerator HBM), network and disk storage and transfers. It can increase multi tenancy and accelerate compute. eXmY has been deployed in production for almost 2 years.

arXiv:2405.14398공식 코드 · Papers with Code

SpGesture: Source-Free Domain-adaptive sEMG-based Gesture Recognition with Jaccard Attentive Spiking Neural Network

Surface electromyography (sEMG) based gesture recognition offers a natural and intuitive interaction modality for wearable devices. Despite significant advancements in sEMG-based gesture-recognition models, existing methods often suffer from high computational latency and increased energy consumption. Additionally, the inherent instability of sEMG signals, combined with their sensitivity to distribution shifts in real-world settings, compromises model robustness. To tackle these challenges, we propose a novel SpGesture framework based on Spiking Neural Networks, which possesses several unique merits compared with existing methods: (1) Robustness: By utilizing membrane potential as a memory list, we pioneer the introduction of Source-Free Domain Adaptation into SNN for the first time. This enables SpGesture to mitigate the accuracy degradation caused by distribution shifts. (2) High Accuracy: With a novel Spiking Jaccard Attention, SpGesture enhances the SNNs' ability to represent sEMG features, leading to a notable rise in system accuracy. To validate SpGesture's performance, we collected a new sEMG gesture dataset which has different forearm postures, where SpGesture achieved the highest accuracy among the baselines ($89.26\%$). Moreover, the actual deployment on the CPU demonstrated a system latency below 100ms, well within real-time requirements. This impressive performance showcases SpGesture's potential to enhance the applicability of sEMG in real-world scenarios. The code is available at https://github.com/guoweiyu/SpGesture/.

arXiv:2405.14024

Two Heads are Better Than One: Neural Networks Quantization with 2D Hilbert Curve-based Output Representation

Quantization is widely used to increase deep neural networks' (DNN) memory, computation, and power efficiency. Various techniques, such as post-training quantization and quantization-aware training, have been proposed to improve quantization quality. We introduce a novel approach for DNN quantization that uses a redundant representation of DNN's output. We represent the target quantity as a point on a 2D parametric curve. The DNN model is modified to predict 2D points that are mapped back to the target quantity at a post-processing stage. We demonstrate that this mapping can reduce quantization error. For the low-order parametric Hilbert curve, Depth-From-Stereo task, and two models represented by U-Net architecture and vision transformer, we achieved a quantization error reduction by about 5 times for the INT8 model at both CPU and DSP delegates. This gain comes with a minimal inference time increase (less than 7%). Our approach can be applied to other tasks, including segmentation, object detection, and key-points prediction.

arXiv:2405.12965공식 코드 · Papers with Code

The future of cosmological likelihood-based inference: accelerated high-dimensional parameter estimation and model comparison

We advocate for a new paradigm of cosmological likelihood-based inference, leveraging recent developments in machine learning and its underlying technology, to accelerate Bayesian inference in high-dimensional settings. Specifically, we combine (i) emulation, where a machine learning model is trained to mimic cosmological observables, e.g. CosmoPower-JAX; (ii) differentiable and probabilistic programming, e.g. JAX and NumPyro, respectively; (iii) scalable Markov chain Monte Carlo (MCMC) sampling techniques that exploit gradients, e.g. Hamiltonian Monte Carlo; and (iv) decoupled and scalable Bayesian model selection techniques that compute the Bayesian evidence purely from posterior samples, e.g. the learned harmonic mean implemented in harmonic. This paradigm allows us to carry out a complete Bayesian analysis, including both parameter estimation and model selection, in a fraction of the time of traditional approaches. First, we demonstrate the application of this paradigm on a simulated cosmic shear analysis for a Stage IV survey in 37- and 39-dimensional parameter spaces, comparing $\Lambda$CDM and a dynamical dark energy model ($w_0w_a$CDM). We recover posterior contours and evidence estimates that are in excellent agreement with those computed by the traditional nested sampling approach while reducing the computational cost from 8 months on 48 CPU cores to 2 days on 12 GPUs. Second, we consider a joint analysis between three simulated next-generation surveys, each performing a 3x2pt analysis, resulting in 157- and 159-dimensional parameter spaces. Standard nested sampling techniques are simply unlikely to be feasible in this high-dimensional setting, requiring a projected 12 years of compute time on 48 CPU cores; on the other hand, the proposed approach only requires 8 days of compute time on 24 GPUs. All packages used in our analyses are publicly available.

arXiv:2405.12463

Stochastic Learning of Computational Resource Usage as Graph Structured Multimarginal Schrödinger Bridge

We propose to learn the time-varying stochastic computational resource usage of software as a graph structured Schr\"odinger bridge problem. In general, learning the computational resource usage from data is challenging because resources such as the number of CPU instructions and the number of last level cache requests are both time-varying and statistically correlated. Our proposed method enables learning the joint time-varying stochasticity in computational resource usage from the measured profile snapshots in a nonparametric manner. The method can be used to predict the most-likely time-varying distribution of computational resource availability at a desired time. We provide detailed algorithms for stochastic learning in both single and multi-core cases, discuss the convergence guarantees, computational complexities, and demonstrate their practical use in two case studies: a single-core nonlinear model predictive controller, and a synthetic multi-core software.

arXiv:2405.11564

CRF360D: Monocular 360 Depth Estimation via Spherical Fully-Connected CRFs

Monocular 360 depth estimation is challenging due to the inherent distortion of the equirectangular projection (ERP). This distortion causes a problem: spherical adjacent points are separated after being projected to the ERP plane, particularly in the polar regions. To tackle this problem, recent methods calculate the spherical neighbors in the tangent domain. However, as the tangent patch and sphere only have one common point, these methods construct neighboring spherical relationships around the common point. In this paper, we propose spherical fully-connected CRFs (SF-CRFs). We begin by evenly partitioning an ERP image with regular windows, where windows at the equator involve broader spherical neighbors than those at the poles. To improve the spherical relationships, our SF-CRFs enjoy two key components. Firstly, to involve sufficient spherical neighbors, we propose a Spherical Window Transform (SWT) module. This module aims to replicate the equator window's spherical relationships to all other windows, leveraging the rotational invariance of the sphere. Remarkably, the transformation process is highly efficient, completing the transformation of all windows in a 512X1024 ERP with 0.038 seconds on CPU. Secondly, we propose a Planar-Spherical Interaction (PSI) module to facilitate the relationships between regular and transformed windows, which not only preserves the local details but also captures global structures. By building a decoder based on the SF-CRFs blocks, we propose CRF360D, a novel 360 depth estimation framework that achieves state-of-the-art performance across diverse datasets. Our CRF360D is compatible with different perspective image-trained backbones (e.g., EfficientNet), serving as the encoder.

arXiv:2405.11536

RobMOT: Robust 3D Multi-Object Tracking by Observational Noise and State Estimation Drift Mitigation on LiDAR PointCloud

This paper addresses limitations in 3D tracking-by-detection methods, particularly in identifying legitimate trajectories and reducing state estimation drift in Kalman filters. Existing methods often use threshold-based filtering for detection scores, which can fail for distant and occluded objects, leading to false positives. To tackle this, we propose a novel track validity mechanism and multi-stage observational gating process, significantly reducing ghost tracks and enhancing tracking performance. Our method achieves a $29.47\%$ improvement in Multi-Object Tracking Accuracy (MOTA) on the KITTI validation dataset with the Second detector. Additionally, a refined Kalman filter term reduces localization noise, improving higher-order tracking accuracy (HOTA) by $4.8\%$. The online framework, RobMOT, outperforms state-of-the-art methods across multiple detectors, with HOTA improvements of up to $3.92\%$ on the KITTI testing dataset and $8.7\%$ on the validation dataset, while achieving low identity switch scores. RobMOT excels in challenging scenarios, tracking distant objects and prolonged occlusions, with a $1.77\%$ MOTA improvement on the Waymo Open dataset, and operates at a remarkable 3221 FPS on a single CPU, proving its efficiency for real-time multi-object tracking.

arXiv:2405.11724공식 코드 · Papers with Code

Token-wise Influential Training Data Retrieval for Large Language Models

Given a Large Language Model (LLM) generation, how can we identify which training data led to this generation? In this paper, we proposed RapidIn, a scalable framework adapting to LLMs for estimating the influence of each training data. The proposed framework consists of two stages: caching and retrieval. First, we compress the gradient vectors by over 200,000x, allowing them to be cached on disk or in GPU/CPU memory. Then, given a generation, RapidIn efficiently traverses the cached gradients to estimate the influence within minutes, achieving over a 6,326x speedup. Moreover, RapidIn supports multi-GPU parallelization to substantially accelerate caching and retrieval. Our empirical result confirms the efficiency and effectiveness of RapidIn.

arXiv:2405.07392공식 코드 · Papers with Code

NGD-SLAM: Towards Real-Time Dynamic SLAM without GPU

Many existing visual SLAM methods can achieve high localization accuracy in dynamic environments by leveraging deep learning to mask moving objects. However, these methods incur significant computational overhead as the camera tracking needs to wait for the deep neural network to generate mask at each frame, and they typically require GPUs for real-time operation, which restricts their practicality in real-world robotic applications. Therefore, this paper proposes a real-time dynamic SLAM system that runs exclusively on a CPU. Our approach incorporates a mask propagation mechanism that decouples camera tracking and deep learning-based masking for each frame. We also introduce a hybrid tracking strategy that integrates ORB features with optical flow methods, enhancing both robustness and efficiency by selectively allocating computational resources to input frames. Compared to previous methods, our system maintains high localization accuracy in dynamic environments while achieving a tracking frame rate of 60 FPS on a laptop CPU. These results demonstrate the feasibility of utilizing deep learning for dynamic SLAM without GPU support. Since most existing dynamic SLAM systems are not open-source, we make our code publicly available at: https://github.com/yuhaozhang7/NGD-SLAM

arXiv:2405.06289공식 코드 · Papers with Code

Look Once to Hear: Target Speech Hearing with Noisy Examples

In crowded settings, the human brain can focus on speech from a target speaker, given prior knowledge of how they sound. We introduce a novel intelligent hearable system that achieves this capability, enabling target speech hearing to ignore all interfering speech and noise, but the target speaker. A naive approach is to require a clean speech example to enroll the target speaker. This is however not well aligned with the hearable application domain since obtaining a clean example is challenging in real world scenarios, creating a unique user interface problem. We present the first enrollment interface where the wearer looks at the target speaker for a few seconds to capture a single, short, highly noisy, binaural example of the target speaker. This noisy example is used for enrollment and subsequent speech extraction in the presence of interfering speakers and noise. Our system achieves a signal quality improvement of 7.01 dB using less than 5 seconds of noisy enrollment audio and can process 8 ms of audio chunks in 6.24 ms on an embedded CPU. Our user studies demonstrate generalization to real-world static and mobile speakers in previously unseen indoor and outdoor multipath environments. Finally, our enrollment interface for noisy examples does not cause performance degradation compared to clean examples, while being convenient and user-friendly. Taking a step back, this paper takes an important step towards enhancing the human auditory perception with artificial intelligence. We provide code and data at: https://github.com/vb000/LookOnceToHear.

arXiv:2405.05465공식 코드 · Papers with Code

Vidur: A Large-Scale Simulation Framework For LLM Inference

Optimizing the deployment of Large language models (LLMs) is expensive today since it requires experimentally running an application workload against an LLM implementation while exploring large configuration space formed by system knobs such as parallelization strategies, batching techniques, and scheduling policies. To address this challenge, we present Vidur - a large-scale, high-fidelity, easily-extensible simulation framework for LLM inference performance. Vidur models the performance of LLM operators using a combination of experimental profiling and predictive modeling, and evaluates the end-to-end inference performance for different workloads by estimating several metrics of interest such as latency and throughput. We validate the fidelity of Vidur on several LLMs and show that it estimates inference latency with less than 9% error across the range. Further, we present Vidur-Search, a configuration search tool that helps optimize LLM deployment. Vidur-Search uses Vidur to automatically identify the most cost-effective deployment configuration that meets application performance constraints. For example, Vidur-Search finds the best deployment configuration for LLaMA2-70B in one hour on a CPU machine, in contrast to a deployment-based exploration which would require 42K GPU hours - costing ~218K dollars. Source code for Vidur is available at https://github.com/microsoft/vidur.

arXiv:2405.05231

DiskGNN: Bridging I/O Efficiency and Model Accuracy for Out-of-Core GNN Training

Graph neural networks (GNNs) are machine learning models specialized for graph data and widely used in many applications. To train GNNs on large graphs that exceed CPU memory, several systems store data on disk and conduct out-of-core processing. However, these systems suffer from either read amplification when reading node features that are usually smaller than a disk page or degraded model accuracy by treating the graph as disconnected partitions. To close this gap, we build a system called DiskGNN, which achieves high I/O efficiency and thus fast training without hurting model accuracy. The key technique used by DiskGNN is offline sampling, which helps decouple graph sampling from model computation. In particular, by conducting graph sampling beforehand, DiskGNN acquires the node features that will be accessed by model computation, and such information is utilized to pack the target node features contiguously on disk to avoid read amplification. Besides, \name{} also adopts designs including four-level feature store to fully utilize the memory hierarchy to cache node features and reduce disk access, batched packing to accelerate the feature packing process, and pipelined training to overlap disk access with other operations. We compare DiskGNN with Ginex and MariusGNN, which are state-of-the-art systems for out-of-core GNN training. The results show that DiskGNN can speed up the baselines by over 8x while matching their best model accuracy.

arXiv:2405.03967공식 코드 · Papers with Code

SwiftRL: Towards Efficient Reinforcement Learning on Real Processing-In-Memory Systems

Reinforcement Learning (RL) trains agents to learn optimal behavior by maximizing reward signals from experience datasets. However, RL training often faces memory limitations, leading to execution latencies and prolonged training times. To overcome this, SwiftRL explores Processing-In-Memory (PIM) architectures to accelerate RL workloads. We achieve near-linear performance scaling by implementing RL algorithms like Tabular Q-learning and SARSA on UPMEM PIM systems and optimizing for hardware. Our experiments on OpenAI GYM environments using UPMEM hardware demonstrate superior performance compared to CPU and GPU implementations.

arXiv:2405.00738공식 코드 · Papers with Code

HLSTransform: Energy-Efficient Llama 2 Inference on FPGAs Via High Level Synthesis

Graphics Processing Units (GPUs) have become the leading hardware accelerator for deep learning applications and are used widely in training and inference of transformers; transformers have achieved state-of-the-art performance in many areas of machine learning and are especially used in most modern Large Language Models (LLMs). However, GPUs require large amounts of energy, which poses environmental concerns, demands high operational costs, and causes GPUs to be unsuitable for edge computing. We develop an accelerator for transformers, namely, Llama 2, an open-source state-of-the-art LLM, using high level synthesis (HLS) on Field Programmable Gate Arrays (FPGAs). HLS allows us to rapidly prototype FPGA designs without writing code at the register-transfer level (RTL). We name our method HLSTransform, and the FPGA designs we synthesize with HLS achieve up to a 12.75x reduction and 8.25x reduction in energy used per token on the Xilinx Virtex UltraScale+ VU9P FPGA compared to an Intel Xeon Broadwell E5-2686 v4 CPU and NVIDIA RTX 3090 GPU respectively, while increasing inference speeds by up to 2.46x compared to CPU and maintaining 0.53x the speed of an RTX 3090 GPU despite the GPU's 4 times higher base clock rate. With the lack of existing open-source FPGA accelerators for transformers, we open-source our code and document our steps for synthesis. We hope this work will serve as a step in democratizing the use of FPGAs in transformer inference and inspire research into energy-efficient inference methods as a whole. The code can be found on https://github.com/HLSTransform/submission.

arXiv:2405.01306

Graph is all you need? Lightweight data-agnostic neural architecture search without training

Neural architecture search (NAS) enables the automatic design of neural network models. However, training the candidates generated by the search algorithm for performance evaluation incurs considerable computational overhead. Our method, dubbed nasgraph, remarkably reduces the computational costs by converting neural architectures to graphs and using the average degree, a graph measure, as the proxy in lieu of the evaluation metric. Our training-free NAS method is data-agnostic and light-weight. It can find the best architecture among 200 randomly sampled architectures from NAS-Bench201 in 217 CPU seconds. Besides, our method is able to achieve competitive performance on various datasets including NASBench-101, NASBench-201, and NDS search spaces. We also demonstrate that nasgraph generalizes to more challenging tasks on Micro TransNAS-Bench-101.

arXiv:2404.19174

XFeat: Accelerated Features for Lightweight Image Matching

We introduce a lightweight and accurate architecture for resource-efficient visual correspondence. Our method, dubbed XFeat (Accelerated Features), revisits fundamental design choices in convolutional neural networks for detecting, extracting, and matching local features. Our new model satisfies a critical need for fast and robust algorithms suitable to resource-limited devices. In particular, accurate image matching requires sufficiently large image resolutions - for this reason, we keep the resolution as large as possible while limiting the number of channels in the network. Besides, our model is designed to offer the choice of matching at the sparse or semi-dense levels, each of which may be more suitable for different downstream applications, such as visual navigation and augmented reality. Our model is the first to offer semi-dense matching efficiently, leveraging a novel match refinement module that relies on coarse local descriptors. XFeat is versatile and hardware-independent, surpassing current deep learning-based local features in speed (up to 5x faster) with comparable or better accuracy, proven in pose estimation and visual localization. We showcase it running in real-time on an inexpensive laptop CPU without specialized hardware optimizations. Code and weights are available at www.verlab.dcc.ufmg.br/descriptors/xfeat_cvpr24.