相关论文: Data Pruning Can Do More: A Comprehensive Data Pru…

The rapid growth of dataset scales has been a key driver in advancing deep learning research. However, as dataset scale increases, the training process becomes increasingly inefficient due to the presence of low-value samples, including…

Machine unlearning aims to efficiently eliminate the memory about deleted data from trained models and address the right to be forgotten. Despite the success of existing unlearning algorithms, unlearning in sparse models has not yet been…

Pruning Deep Neural Networks (DNNs) is a prominent field of study in the goal of inference runtime acceleration. In this paper, we introduce a novel data-free pruning protocol RED++. Only requiring a trained neural network, and not specific…

It is prohibitively expensive to annotate a large-scale video-based person re-identification (re-ID) dataset, which makes fully supervised methods inapplicable to real-world deployment. How to maximally reduce the annotation cost while…

Pruning provides a practical solution to reduce the resources required to run large language models (LLMs) to benefit from their effective capabilities as well as control their cost for training and inference. Research on LLM pruning often…

In data mining applications, feature selection is an essential process since it reduces a model's complexity. The cost of obtaining the feature values must be taken into consideration in many domains. In this paper, we study the…

The fashion industry has been identified as a major contributor to waste and emissions, leading to an increased interest in promoting the second-hand market. Machine learning methods play an important role in facilitating the creation and…

Pruning neural networks, i.e., removing some of their parameters whilst retaining their accuracy, is one of the main ways to reduce the latency of a machine learning pipeline, especially in resource- and/or bandwidth-constrained scenarios.…

Machine learning optimization often depends on stochastic gradient descent, where the precision of gradient estimation is vital for model performance. Gradients are calculated from mini-batches formed by uniformly selecting data samples…

Due to its significant capability of modeling long-range dependencies, vision transformer (ViT) has achieved promising success in both holistic and occluded person re-identification (Re-ID) tasks. However, the inherent problems of…

Dataset distillation and dataset pruning are two prominent techniques for compressing datasets to improve computational and storage efficiency. Despite their overlapping objectives, these approaches are rarely compared directly. Even within…

Deep pre-trained Transformer models have achieved state-of-the-art results over a variety of natural language processing (NLP) tasks. By learning rich language knowledge with millions of parameters, these models are usually…

Visual instruction tuning adapts pre-trained Multimodal Large Language Models (MLLMs) to follow human instructions for real-world applications. However, the rapid growth of these datasets introduces significant redundancy, leading to…

Network pruning is widely used for reducing the heavy inference cost of deep models in low-resource settings. A typical pruning algorithm is a three-stage pipeline, i.e., training (a large model), pruning and fine-tuning. During pruning,…

In this paper, we present SwiftLearn, a data-efficient approach to accelerate training of deep learning models using a subset of data samples selected during the warm-up stages of training. This subset is selected based on an importance…

Machine unlearning aims to remove the influence of specific training data from a model without requiring full retraining. This capability is crucial for ensuring privacy, safety, and regulatory compliance. Therefore, verifying whether a…

Reliable classification of 3D-printed objects is essential for automating post-production workflows in industrial additive manufacturing. Despite extensive automation in other stages of the printing pipeline, this task still relies heavily…

Person re-identification (re-id) is a critical problem in video analytics applications such as security and surveillance. The public release of several datasets and code for vision algorithms has facilitated rapid progress in this area over…

We introduce a DNN training technique that learns only a fraction of the full parameter set without incurring an accuracy penalty. To do this, our algorithm constrains the total number of weights updated during backpropagation to those with…

As the capabilities of Vision-Language Models (VLMs) advance, they can process increasingly large inputs, which, unlike in LLMs, generates significant visual token redundancy and leads to prohibitive inference costs. While many methods aim…