相关论文: CR-SAM: Curvature Regularized Sharpness-Aware Mini…

Regularization is essential in deep learning to enhance generalization and mitigate overfitting. However, conventional techniques often rely on heuristics, making them less reliable or effective across diverse settings. We propose Self…

Sharpness-Aware Minimization (SAM) is most known for achieving state-of the-art performances on natural image and language tasks. However, its most pronounced improvements (of tens of percent) is rather in the presence of label noise.…

Deep neural networks suffer from the catastrophic forgetting problem in the field of continual learning (CL). To address this challenge, we propose MGSER-SAM, a novel memory replay-based algorithm specifically engineered to enhance the…

In this paper we introduce a novel method of gradient normalization and decay with respect to depth. Our method leverages the simple concept of normalizing all gradients in a deep neural network, and then decaying said gradients with…

Image-based crack detection algorithms are increasingly in demand in infrastructure monitoring, as early detection of cracks is of paramount importance for timely maintenance planning. While deep learning has significantly advanced crack…

We characterize the effectiveness of Sharpness-aware minimization (SAM) under machine unlearning scheme, where unlearning forget signals interferes with learning retain signals. While previous work prove that SAM improves generalization…

Harnessing the local topography of the loss landscape is a central challenge in advanced optimization tasks. By accounting for the effect of potential parameter changes, we can alter the model more efficiently. Contrary to standard…

Sharpness-Aware Minimization (SAM) has substantially improved the generalization of neural networks under various settings. Despite the success, its effectiveness remains poorly understood. In this work, we discover an intriguing phenomenon…

There has been a lot of recent research on improving the efficiency of fine-tuning foundation models. In this paper, we propose a novel efficient fine-tuning method that allows the input image size of Segment Anything Model (SAM) to be…

We consider fine-tuning a pretrained deep neural network on a target task. We study the generalization properties of fine-tuning to understand the problem of overfitting, which has often been observed (e.g., when the target dataset is small…

Reconstructing under-sampled k-space measurements in Compressed Sensing MRI (CS-MRI) is classically solved with regularized least-squares. Recently, deep learning has been used to amortize this optimization by training reconstruction…

Recently, Sharpness-Aware Minimization (SAM) has shown state-of-the-art performance by seeking flat minima. To minimize the maximum loss within a neighborhood in the parameter space, SAM uses an ascent step, which perturbs the weights along…

Compressed Sensing MRI reconstructs images of the body's internal anatomy from undersampled measurements, thereby reducing scan time. Recently, deep learning has shown great potential for reconstructing high-fidelity images from highly…

The challenge of fine-grained visual recognition often lies in discovering the key discriminative regions. While such regions can be automatically identified from a large-scale labeled dataset, a similar method might become less effective…

The discontinuous operations inherent in quantization and sparsification introduce a long-standing obstacle to backpropagation, particularly in ultra-low precision and sparse regimes. While the community has long viewed quantization as…

Deep learning models, despite their impressive achievements, suffer from high computational costs and memory requirements, limiting their usability in resource-constrained environments. Sparse neural networks significantly alleviate these…

Learning from Noisy Labels (LNL) remains a fundamental challenge in deep learning because real-world datasets often contain corrupted annotations. Most existing methods rely on label correction or sample selection mechanisms. In contrast,…

Recent research in robust optimization has shown an overfitting-like phenomenon in which models trained against adversarial attacks exhibit higher robustness on the training set compared to the test set. Although previous work provided…

Can we modify the training data distribution to encourage the underlying optimization method toward finding solutions with superior generalization performance on in-distribution data? In this work, we approach this question for the first…

In an effort to improve generalization in deep learning and automate the process of learning rate scheduling, we propose SALR: a sharpness-aware learning rate update technique designed to recover flat minimizers. Our method dynamically…