Sensitivity-Aware Finetuning for Accuracy Recovery on Deep Learning Hardware

• URL: http://arxiv.org/abs/2306.03076v1
• Date: Mon, 5 Jun 2023 17:52:44 GMT
• Title: Sensitivity-Aware Finetuning for Accuracy Recovery on Deep Learning Hardware
• Authors: Lakshmi Nair and Darius Bunandar
• Abstract summary: We introduce the Sensitivity-Aware Finetuning approach that identifies noise sensitive layers in a model, and uses the information to freeze specific layers for noise-injection training. Our results show that SAFT achieves comparable accuracy to noise-injection training and is 2x to 8x faster.
• Score: 2.610470075814367
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing methods to recover model accuracy on analog-digital hardware in the presence of quantization and analog noise include noise-injection training. However, it can be slow in practice, incurring high computational costs, even when starting from pretrained models. We introduce the Sensitivity-Aware Finetuning (SAFT) approach that identifies noise sensitive layers in a model, and uses the information to freeze specific layers for noise-injection training. Our results show that SAFT achieves comparable accuracy to noise-injection training and is 2x to 8x faster.

Related papers

• DDTR: Diffusion Denoising Trace Recovery [2.6006110020577564]
  We develop a novel deep learning approach for trace recovery based on Diffusion Denoising Probabilistic Models (DDPM)<n>We conduct an empirical evaluation demonstrating state-of-the-art performance with up to a 25% improvement over existing methods, along with increased robustness under high noise levels.
  arXiv  Detail & Related papers  (2025-10-26T06:43:53Z)
• Extending Straight-Through Estimation for Robust Neural Networks on Analog CIM Hardware [5.100973962435092]
  We propose a noise-aware training method for analog Compute-In-Memory (CIM) systems.<n>We decouple forward noise simulation from backward gradient computation, enabling noise-aware training with more accurate but computationally intractable noise modeling.<n>Our framework achieves up to 5.3% accuracy improvement on image classification, 0.72 perplexity reduction on text generation, 2.2$times$ speedup in training time, and 37.9% lower peak memory usage.
  arXiv  Detail & Related papers  (2025-08-16T06:53:44Z)
• Noise Conditional Variational Score Distillation [60.38982038894823]
  Noise Conditional Variational Score Distillation (NCVSD) is a novel method for distilling pretrained diffusion models into generative denoisers.<n>By integrating this insight into the Variational Score Distillation framework, we enable scalable learning of generative denoisers.
  arXiv  Detail & Related papers  (2025-06-11T06:01:39Z)
• Variance-Aware Noisy Training: Hardening DNNs against Unstable Analog Computations [5.975221928631025]
  Noisy Training is one of the most effective techniques for enhancing robustness, but its performance degrades in real-world environments. We propose Variance-Aware Noisy Training, a novel approach that incorporates noise schedules which emulate the evolving noise conditions encountered during inference. We demonstrate a significant increase in robustness, from 72.3% with conventional Noisy Training to 97.3% with Variance-Aware Noisy Training on CIFAR-10 and from 38.5% to 89.9% on Tiny ImageNet.
  arXiv  Detail & Related papers  (2025-03-20T14:34:03Z)
• Learning with Noisy Foundation Models [95.50968225050012]
  This paper is the first work to comprehensively understand and analyze the nature of noise in pre-training datasets. We propose a tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise and improve generalization.
  arXiv  Detail & Related papers  (2024-03-11T16:22:41Z)
• Blue noise for diffusion models [50.99852321110366]
  We introduce a novel and general class of diffusion models taking correlated noise within and across images into account. Our framework allows introducing correlation across images within a single mini-batch to improve gradient flow. We perform both qualitative and quantitative evaluations on a variety of datasets using our method.
  arXiv  Detail & Related papers  (2024-02-07T14:59:25Z)
• Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks [91.15120211190519]
  This paper aims to understand the nature of noise in pre-training datasets and to mitigate its impact on downstream tasks. We propose a light-weight black-box tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise.
  arXiv  Detail & Related papers  (2023-09-29T06:18:15Z)
• DiffSED: Sound Event Detection with Denoising Diffusion [70.18051526555512]
  We reformulate the SED problem by taking a generative learning perspective. Specifically, we aim to generate sound temporal boundaries from noisy proposals in a denoising diffusion process. During training, our model learns to reverse the noising process by converting noisy latent queries to the groundtruth versions.
  arXiv  Detail & Related papers  (2023-08-14T17:29:41Z)
• Realistic Noise Synthesis with Diffusion Models [68.48859665320828]
  Deep image denoising models often rely on large amount of training data for the high quality performance. We propose a novel method that synthesizes realistic noise using diffusion models, namely Realistic Noise Synthesize Diffusor (RNSD) RNSD can incorporate guided multiscale content, such as more realistic noise with spatial correlations can be generated at multiple frequencies.
  arXiv  Detail & Related papers  (2023-05-23T12:56:01Z)
• Latent Class-Conditional Noise Model [54.56899309997246]
  We introduce a Latent Class-Conditional Noise model (LCCN) to parameterize the noise transition under a Bayesian framework. We then deduce a dynamic label regression method for LCCN, whose Gibbs sampler allows us efficiently infer the latent true labels. Our approach safeguards the stable update of the noise transition, which avoids previous arbitrarily tuning from a mini-batch of samples.
  arXiv  Detail & Related papers  (2023-02-19T15:24:37Z)
• A Novel Noise Injection-based Training Scheme for Better Model Robustness [9.749718440407811]
  Noise injection-based method has been shown to be able to improve the robustness of artificial neural networks. In this work, we propose a novel noise injection-based training scheme for better model robustness. Experiment results show that our proposed method achieves a much better performance on adversarial robustness and slightly better performance on original accuracy.
  arXiv  Detail & Related papers  (2023-02-17T02:50:25Z)
• Hard Sample Aware Noise Robust Learning for Histopathology Image Classification [4.75542005200538]
  We introduce a novel hard sample aware noise robust learning method for histopathology image classification. To distinguish the informative hard samples from the harmful noisy ones, we build an easy/hard/noisy (EHN) detection model. We propose a noise suppressing and hard enhancing (NSHE) scheme to train the noise robust model.
  arXiv  Detail & Related papers  (2021-12-05T11:07:55Z)
• Rethinking Noise Synthesis and Modeling in Raw Denoising [75.55136662685341]
  We introduce a new perspective to synthesize noise by directly sampling from the sensor's real noise. It inherently generates accurate raw image noise for different camera sensors.
  arXiv  Detail & Related papers  (2021-10-10T10:45:24Z)
• Physics-based Noise Modeling for Extreme Low-light Photography [63.65570751728917]
  We study the noise statistics in the imaging pipeline of CMOS photosensors. We formulate a comprehensive noise model that can accurately characterize the real noise structures. Our noise model can be used to synthesize realistic training data for learning-based low-light denoising algorithms.
  arXiv  Detail & Related papers  (2021-08-04T16:36:29Z)
• Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed [0.0]
  Iterative generative models, such as noise conditional score networks, produce high quality samples by gradually denoising an initial noise vector. We establish a novel connection between knowledge distillation and image generation with a technique that distills a multi-step denoising process into a single step. Our Denoising Student generates high quality samples comparable to GANs on the CIFAR-10 and CelebA datasets, without adversarial training.
  arXiv  Detail & Related papers  (2021-01-07T06:12:28Z)
• Identifying Training Stop Point with Noisy Labeled Data [0.0]
  We develop an algorithm to find a training stop point (TSP) at or close to test accuracy (MOTA) We validated the robustness of our algorithm (AutoTSP) through several experiments on CIFAR-10, CIFAR-100, and a real-world noisy dataset.
  arXiv  Detail & Related papers  (2020-12-24T20:07:30Z)
• Robust Processing-In-Memory Neural Networks via Noise-Aware Normalization [26.270754571140735]
  PIM accelerators often suffer from intrinsic noise in the physical components. We propose a noise-agnostic method to achieve robust neural network performance against any noise setting.
  arXiv  Detail & Related papers  (2020-07-07T06:51:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.