English
Related papers

Related papers: Precision at Scale: Domain-Specific Datasets On-De…

200 papers

We introduce a framework for optimizing domain-specific dataset construction in foundation model training. Specifically, we seek a cost-efficient way to estimate the quality of data sources (e.g. synthetically generated or filtered web…

Recent advances in semi-supervised learning (SSL) demonstrate that a combination of consistency regularization and pseudo-labeling can effectively improve image classification accuracy in the low-data regime. Compared to classification,…

Computer Vision and Pattern Recognition · Computer Science 2021-03-31 Yuliang Zou , Zizhao Zhang , Han Zhang , Chun-Liang Li , Xiao Bian , Jia-Bin Huang , Tomas Pfister

Self-Supervised Learning (SSL) has allowed leveraging large amounts of unlabeled speech data to improve the performance of speech recognition models even with small annotated datasets. Despite this, speech SSL representations may fail while…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-02 Salah Zaiem , Titouan Parcollet , Slim Essid

Pre-training and transfer learning are an important building block of current computer vision systems. While pre-training is usually performed on large real-world image datasets, in this paper we ask whether this is truly necessary. To this…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Ryo Nakamura , Ryu Tadokoro , Ryosuke Yamada , Yuki M. Asano , Iro Laina , Christian Rupprecht , Nakamasa Inoue , Rio Yokota , Hirokatsu Kataoka

In person re-identification (ReID), very recent researches have validated pre-training the models on unlabelled person images is much better than on ImageNet. However, these researches directly apply the existing self-supervised learning…

Computer Vision and Pattern Recognition · Computer Science 2022-07-21 Kuan Zhu , Haiyun Guo , Tianyi Yan , Yousong Zhu , Jinqiao Wang , Ming Tang

Existing data augmentation in self-supervised learning, while diverse, fails to preserve the inherent structure of natural images. This results in distorted augmented samples with compromised semantic information, ultimately impacting…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Renan A. Rojas-Gomez , Karan Singhal , Ali Etemad , Alex Bijamov , Warren R. Morningstar , Philip Andrew Mansfield

Existing learning-based surface reconstruction methods from point clouds are still facing challenges in terms of scalability and preservation of details on large-scale point clouds. In this paper, we propose the SSRNet, a novel scalable…

Computer Vision and Pattern Recognition · Computer Science 2020-04-15 Zhenxing Mi , Yiming Luo , Wenbing Tao

Although larger datasets are crucial for training large deep models, the rapid growth of dataset size has brought a significant challenge in terms of considerable training costs, which even results in prohibitive computational expenses.…

Computer Vision and Pattern Recognition · Computer Science 2025-08-06 Sheng-Feng Yu , Jia-Jiun Yao , Wei-Chen Chiu

Recent advancements in vision transformers (ViTs) have demonstrated that larger models often achieve superior performance. However, training these models remains computationally intensive and costly. To address this challenge, we introduce…

Computer Vision and Pattern Recognition · Computer Science 2025-10-23 Zhiwei Hao , Jianyuan Guo , Li Shen , Kai Han , Yehui Tang , Han Hu , Yunhe Wang

Deep convolutional neural networks (DCNNs) have shown dominant performance in the task of super-resolution (SR). However, their heavy memory cost and computation overhead significantly restrict their practical deployments on…

Image and Video Processing · Electrical Eng. & Systems 2020-11-10 Huixia Li , Chenqian Yan , Shaohui Lin , Xiawu Zheng , Yuchao Li , Baochang Zhang , Fan Yang , Rongrong Ji

An important goal of self-supervised learning is to enable model pre-training to benefit from almost unlimited data. However, one method that has recently become popular, namely masked image modeling (MIM), is suspected to be unable to…

Computer Vision and Pattern Recognition · Computer Science 2022-06-10 Zhenda Xie , Zheng Zhang , Yue Cao , Yutong Lin , Yixuan Wei , Qi Dai , Han Hu

Self-supervised learning (SSL) has transformed representation learning for large models, yet remains unexplored for microcontroller (MCU)-class models with fewer than 500K parameters. We identify three obstacles at this scale -- projection…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Bibin Wilson

In differentially private (DP) tabular data synthesis, the consensus is that statistical models are better than neural network (NN)-based methods. However, we argue that this conclusion is incomplete and overlooks the challenge of densely…

Machine Learning · Computer Science 2025-11-19 Kai Chen , Chen Gong , Tianhao Wang

Neural Architecture Search (NAS) is a powerful tool to automatically design deep neural networks for many tasks, including image classification. Due to the significant computational burden of the search phase, most NAS methods have focused…

Self-supervised learning on tabular data seeks to apply advances from natural language and image domains to the diverse domain of tables. However, current techniques often struggle with integrating multi-domain data and require data…

Machine Learning · Computer Science 2024-10-18 Marco Spinaci , Marek Polewczyk , Johannes Hoffart , Markus C. Kohler , Sam Thelin , Tassilo Klein

Recent advancements in unified image generation models, such as OmniGen, have enabled the handling of diverse image generation and editing tasks within a single framework, accepting multimodal, interleaved texts and images in free form.…

Computer Vision and Pattern Recognition · Computer Science 2025-07-23 Chao Zhou , Tianyi Wei , Nenghai Yu

We present a refinement framework to boost the performance of pre-trained semi-supervised video object segmentation (VOS) models. Our work is based on scale inconsistency, which is motivated by the observation that existing VOS models…

Computer Vision and Pattern Recognition · Computer Science 2022-05-04 Hengyi Wang , Changjae Oh

Pseudo-labeling is significant for semi-supervised instance segmentation, which generates instance masks and classes from unannotated images for subsequent training. However, in existing pipelines, pseudo-labels that contain valuable…

Computer Vision and Pattern Recognition · Computer Science 2023-08-11 Jie Hu , Chen Chen , Liujuan Cao , Shengchuan Zhang , Annan Shu , Guannan Jiang , Rongrong Ji

Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations. However, most of methods mainly focus on the instance level information…

Computer Vision and Pattern Recognition · Computer Science 2021-07-26 Mingkai Zheng , Shan You , Fei Wang , Chen Qian , Changshui Zhang , Xiaogang Wang , Chang Xu

The ability to classify images is dependent on having access to large labeled datasets and testing on data from the same domain that the model can train on. Classification becomes more challenging when dealing with new data from a different…

Computer Vision and Pattern Recognition · Computer Science 2023-10-20 Firas Al-Hindawi , Md Mahfuzur Rahman Siddiquee , Teresa Wu , Han Hu , Ying Sun