English
Related papers

Related papers: SubZeroCore: A Submodular Approach with Zero Train…

200 papers

Supervised deep learning performance is heavily tied to the availability of high-quality labels for training. Neural networks can gradually overfit corrupted labels if directly trained on noisy datasets, leading to severe performance…

Machine Learning · Computer Science 2021-02-02 Ziyi Huang , Haofeng Zhang , Andrew Laine , Elsa Angelini , Christine Hendon , Yu Gan

Subsampling algorithms are a natural approach to reduce data size before fitting models on massive datasets. In recent years, several works have proposed methods for subsampling rows from a data matrix while maintaining relevant information…

Machine Learning · Computer Science 2023-01-18 Fred Lu , Edward Raff , James Holt

Model compression techniques reduce the computational load and memory consumption of deep neural networks. After the compression operation, e.g. parameter pruning, the model is normally fine-tuned on the original training dataset to recover…

Computer Vision and Pattern Recognition · Computer Science 2023-06-23 Adrian Holzbock , Achyut Hegde , Klaus Dietmayer , Vasileios Belagiannis

Channel pruning is an important family of methods to speed up deep model's inference. Previous filter pruning algorithms regard channel pruning and model fine-tuning as two independent steps. This paper argues that combining them into a…

Computer Vision and Pattern Recognition · Computer Science 2019-01-18 Jian-Hao Luo , Jianxin Wu

Model Interpretation aims at the extraction of insights from the internals of a trained model. A common approach to address this task is the characterization of relevant features internally encoded in the model that are critical for its…

Machine Learning · Computer Science 2024-10-07 Hamed Behzadi-Khormouji , José Oramas

Varying-size models are often required to deploy ASR systems under different hardware and/or application constraints such as memory and latency. To avoid redundant training and optimization efforts for individual models of different sizes,…

Audio and Speech Processing · Electrical Eng. & Systems 2024-07-30 Jingjing Xu , Wei Zhou , Zijian Yang , Eugen Beck , Ralf Schlueter

The great success of deep learning heavily relies on increasingly larger training data, which comes at a price of huge computational and infrastructural costs. This poses crucial questions that, do all training data contribute to model's…

Machine Learning · Computer Science 2023-02-28 Shuo Yang , Zeke Xie , Hanyu Peng , Min Xu , Mingming Sun , Ping Li

Learning-based denoising algorithms achieve state-of-the-art performance across various denoising tasks. However, training such models relies on access to large training datasets consisting of clean and noisy image pairs. On the other hand,…

Image and Video Processing · Electrical Eng. & Systems 2025-03-31 Ali Zafari , Xi Chen , Shirin Jalali

Training deep networks and tuning hyperparameters on large datasets is computationally intensive. One of the primary research directions for efficient training is to reduce training costs by selecting well-generalizable subsets of training…

Semi-supervised learning (SSL) algorithms have had great success in recent years in limited labeled data regimes. However, the current state-of-the-art SSL algorithms are computationally expensive and entail significant compute time and…

Machine Learning · Computer Science 2021-10-29 Krishnateja Killamsetty , Xujiang Zhao , Feng Chen , Rishabh Iyer

Audio source separation is fundamental for machines to understand complex acoustic environments and underpins numerous audio applications. Current supervised deep learning approaches, while powerful, are limited by the need for extensive,…

The increasing availability of massive data sets poses a series of challenges for machine learning. Prominent among these is the need to learn models under hardware or human resource constraints. In such resource-constrained settings, a…

Machine Learning · Computer Science 2021-09-28 Zalán Borsos , Mojmír Mutný , Marco Tagliasacchi , Andreas Krause

Weakly supervised semantic segmentation aims to achieve pixel-level predictions using image-level labels. Existing methods typically entangle semantic recognition and object localization, which often leads models to focus exclusively on…

Computer Vision and Pattern Recognition · Computer Science 2026-04-17 Qingze He , Fagui Liu , Dengke Zhang , Qingmao Wei , Quan Tang

Active learning enables the efficient construction of a labeled dataset by labeling informative samples from an unlabeled dataset. In a real-world active learning scenario, considering the diversity of the selected samples is crucial…

Machine Learning · Computer Science 2022-07-15 Yeachan Kim , Bonggun Shin

Diffusion-based remote sensing (RS) generative foundation models are cruial for downstream tasks. However, these models rely on large amounts of globally representative data, which often contain redundancy, noise, and class imbalance,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Fan Wei , Runmin Dong , Yushan Lai , Yixiang Yang , Zhaoyang Luo , Jinxiao Zhang , Miao Yang , Shuai Yuan , Jiyao Zhao , Bin Luo , Haohuan Fu

In this paper, we present InfoMax, a novel data pruning method, also known as coreset selection, designed to maximize the information content of selected samples while minimizing redundancy. By doing so, InfoMax enhances the overall…

Computer Vision and Pattern Recognition · Computer Science 2025-08-15 Haoru Tan , Sitong Wu , Wei Huang , Shizhen Zhao , Xiaojuan Qi

High-quality training data is essential for building reliable and efficient machine learning systems. One-shot coreset selection addresses this by pruning the dataset while maintaining or even improving model performance, often relying on…

Machine Learning · Computer Science 2025-08-15 Elisa Tsai , Haizhong Zheng , Atul Prakash

Recently, dataset-generation-based zero-shot learning has shown promising results by training a task-specific model with a dataset synthesized from large pre-trained language models (PLMs). The final task-specific model often achieves…

Computation and Language · Computer Science 2022-10-25 Jiacheng Ye , Jiahui Gao , Jiangtao Feng , Zhiyong Wu , Tao Yu , Lingpeng Kong

Subword modeling for zero-resource languages aims to learn low-level representations of speech audio without using transcriptions or other resources from the target language (such as text corpora or pronunciation dictionaries). A good…

Audio and Speech Processing · Electrical Eng. & Systems 2020-04-20 Enno Hermann , Herman Kamper , Sharon Goldwater

Deep learning approaches have achieved unprecedented performance in visual recognition tasks such as object detection and pose estimation. However, state-of-the-art models have millions of parameters represented as floats which make them…

Computer Vision and Pattern Recognition · Computer Science 2021-02-08 Gedeon Muhawenayo , Georgia Gkioxari