相关论文: K-SAM: Sharpness-Aware Minimization at the Speed o…

Hybrid modeling, the combination of machine learning models and scientific mathematical models, enables flexible and robust data-driven prediction with partial interpretability. However, effectively the scientific models may be ignored in…

A central goal in deep learning is to learn compact representations of features at every layer of a neural network, which is useful for both unsupervised representation learning and structured network pruning. While there is a growing body…

In deep learning, fine-grained N:M sparsity reduces the data footprint and bandwidth of a General Matrix multiply (GEMM) up to x2, and doubles throughput by skipping computation of zero values. So far, it was mainly only used to prune…

Class imbalance is a common challenge in real-world recognition tasks, where the majority of classes have few samples, also known as tail classes. We address this challenge with the perspective of generalization and empirically find that…

High-resolution aerial images have a wide range of applications, such as military exploration, and urban planning. Semantic segmentation is a fundamental method extensively used in the analysis of high-resolution aerial images. However, the…

The training of deep neural networks is inherently a nonconvex optimization problem, yet standard approaches such as stochastic gradient descent (SGD) require simultaneous updates to all parameters, often leading to unstable convergence and…

Stochastic Gradient Descent (SGD) is one of the most widely used techniques for online optimization in machine learning. In this work, we accelerate SGD by adaptively learning how to sample the most useful training examples at each time…

Knowledge Distillation (KD) compresses neural networks by learning a small network (student) via transferring knowledge from a pre-trained large network (teacher). Many endeavours have been devoted to the image domain, while few works focus…

In this work, we question the necessity of adaptive gradient methods for training deep neural networks. SGD-SaI is a simple yet effective enhancement to stochastic gradient descent with momentum (SGDM). SGD-SaI performs learning rate…

The Segment Anything Model (SAM) family has become a widely adopted vision foundation model, but its ability to control segmentation granularity remains limited. Users often need to refine results manually - by adding more prompts or…

Self-paced learning and hard example mining re-weight training instances to improve learning accuracy. This paper presents two improved alternatives based on lightweight estimates of sample uncertainty in stochastic gradient descent (SGD):…

Segment Anything Model (SAM) has emerged as a transformative approach in image segmentation, acclaimed for its robust zero-shot segmentation capabilities and flexible prompting system. Nonetheless, its performance is challenged by images…

Weakly supervised visual recognition using inexact supervision is a critical yet challenging learning problem. It significantly reduces human labeling costs and traditionally relies on multi-instance learning and pseudo-labeling. This paper…

The recently introduced Segment Anything Model (SAM), a Visual Foundation Model (VFM), has demonstrated impressive capabilities in zero-shot segmentation tasks across diverse natural image datasets. Despite its success, SAM encounters…

In this paper, we address the challenge of image resolution variation for the Segment Anything Model (SAM). SAM, known for its zero-shot generalizability, exhibits a performance degradation when faced with datasets with varying image sizes.…

Prompt-free image segmentation aims to generate accurate masks without manual guidance. Typical pre-trained models, notably Segmentation Anything Model (SAM), generate prompts directly at a single granularity level. However, this approach…

Deep neural networks have been shown to achieve state-of-the-art performance in several machine learning tasks. Stochastic Gradient Descent (SGD) is the preferred optimization algorithm for training these networks and asynchronous SGD…

The Segment Anything Model (SAM) is a powerful vision foundation model that is revolutionizing the traditional paradigm of segmentation. Despite this, a reliance on prompting each frame and large computational cost limit its usage in…

Stochastic gradient descent (SGD) is a ubiquitous algorithm for a variety of machine learning problems. Researchers and industry have developed several techniques to optimize SGD's runtime performance, including asynchronous execution and…

Enabling low precision implementations of deep learning models, without considerable performance degradation, is necessary in resource and latency constrained settings. Moreover, exploiting the differences in sensitivity to quantization…