相关论文: Dual Randomized Smoothing: Beyond Global Noise Var…

Purpose: This work proposes a novel self-supervised noise-adaptive image denoising framework, called Repetition to Repetition (Rep2Rep) learning, for low-field (<1T) MRI applications. Methods: Rep2Rep learning extends the Noise2Noise…

Machine learning models have demonstrated remarkable success across diverse domains but remain vulnerable to adversarial attacks. Empirical defense mechanisms often fail, as new attacks constantly emerge, rendering existing defenses…

Stochastic resonance (SR) is a prominent phenomenon in many natural and engineered noisy system, whereby the response to a periodic forcing is greatly amplified when the intensity of the noise is tuned to within a specific range of values.…

Designing robust algorithms capable of training accurate neural networks on uncurated datasets from the web has been the subject of much research as it reduces the need for time consuming human labor. The focus of many previous research…

By driving models to converge to flat minima, sharpness-aware learning algorithms (such as SAM) have shown the power to achieve state-of-the-art performances. However, these algorithms will generally incur one extra forward-backward…

Numerous empirical evidence has corroborated that the noise plays a crucial rule in effective and efficient training of neural networks. The theory behind, however, is still largely unknown. This paper studies this fundamental problem…

Nowadays, deep learning based methods have demonstrated impressive performance on ideal super-resolution (SR) datasets, but most of these methods incur dramatically performance drops when directly applied in real-world SR reconstruction…

Noisy labels damage the performance of deep networks. For robust learning, a prominent two-stage pipeline alternates between eliminating possible incorrect labels and semi-supervised training. However, discarding part of noisy labels could…

In this paper, two local activity-tuned filtering frameworks are proposed for noise removal and image smoothing, where the local activity measurement is given by the clipped and normalized local variance or standard deviation. The first…

Recently, deep learning based single image super-resolution(SR) approaches have achieved great development. The state-of-the-art SR methods usually adopt a feed-forward pipeline to establish a non-linear mapping between low-res(LR) and…

We propose a novel and effective purification based adversarial defense method against pre-processor blind white- and black-box attacks. Our method is computationally efficient and trained only with self-supervised learning on general…

The robust self-training (RST) framework has emerged as a prominent approach for semi-supervised adversarial training. To explore the possibility of tackling more complicated tasks with even lower labeling budgets, unlike prior approaches…

Speech recognition system performance degrades in noisy environments. If the acoustic models are built using features of clean utterances, the features of a noisy test utterance would be acoustically mismatched with the trained model. This…

Modern machine learning is dominated by complex, overparameterized architectures capable of interpolating data and achieving zero training loss. For such models, we investigate the convergence properties of two popular modifications to…

Randomized smoothing is a powerful tool for certifying robustness to adversarial perturbations, including poisoning attacks via randomized training and evasion attacks via randomized inference. Extending these guarantees to backdoor…

Robust unsupervised anomaly detection (AD) in real-world scenarios is an important task. Current methods exhibit severe performance degradation on the MVTec AD 2 benchmark due to its complex real-world challenges. To solve this problem, we…

Detecting uncertainty in large language models (LLMs) is essential for building reliable systems, yet many existing approaches are overly complex and depend on brittle semantic clustering or access to model internals. We introduce Radial…

The use of spatial information with multiple microphones can improve far-field automatic speech recognition (ASR) accuracy. However, conventional microphone array techniques degrade speech enhancement performance when there is an array…

Keyword Spotting (KWS) systems with small footprint models deployed on edge devices face significant accuracy and robustness challenges due to domain shifts caused by varying noise and recording conditions. To address this, we propose a…

We provide a general framework for studying recurrent neural networks (RNNs) trained by injecting noise into hidden states. Specifically, we consider RNNs that can be viewed as discretizations of stochastic differential equations driven by…