English
Related papers

Related papers: Rethinking Data Augmentation for Robust Visual Que…

200 papers

Deep neural networks (DNNs) often rely on massive labelled data for training, which is inaccessible in many applications. Data augmentation (DA) tackles data scarcity by creating new labelled data from available ones. Different DA methods…

Neural and Evolutionary Computing · Computer Science 2022-05-31 Binyan Hu , Yu Sun , A. K. Qin

Knowledge distillation (KD) is a general neural network training approach that uses a teacher model to guide the student model. Existing works mainly study KD from the network output side (e.g., trying to design a better KD loss function),…

Computer Vision and Pattern Recognition · Computer Science 2023-02-23 Huan Wang , Suhas Lohit , Mike Jones , Yun Fu

Existing work on VQA explores data augmentation to achieve better generalization by perturbing the images in the dataset or modifying the existing questions and answers. While these methods exhibit good performance, the diversity of the…

Computer Vision and Pattern Recognition · Computer Science 2022-04-01 Paola Cascante-Bonilla , Hui Wu , Letao Wang , Rogerio Feris , Vicente Ordonez

We propose a conceptually simple and lightweight framework for improving the robustness of vision models through the combination of knowledge distillation and data augmentation. We address the conjecture that larger models do not make for…

Machine Learning · Computer Science 2024-02-06 Andy Zhou , Jindong Wang , Yu-Xiong Wang , Haohan Wang

In recent years, deep learning has achieved remarkable achievements in many fields, including computer vision, natural language processing, speech recognition and others. Adequate training data is the key to ensure the effectiveness of the…

Machine Learning · Computer Science 2019-05-24 Chunxu Zhang , Jiaxu Cui , Bo Yang

Unsupervised Domain Adaptation (UDA) is essential for enabling semantic segmentation in new domains without requiring costly pixel-wise annotations. State-of-the-art (SOTA) UDA methods primarily use self-training with architecturally…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Beomseok Kang , Niluthpol Chowdhury Mithun , Abhinav Rajvanshi , Han-Pang Chiu , Supun Samarasekera

Data augmentation is one of the most prevalent tools in deep learning, underpinning many recent advances, including those from classification, generative models, and representation learning. The standard approach to data augmentation…

Computer Vision and Pattern Recognition · Computer Science 2025-06-12 Brandon Trabucco , Kyle Doherty , Max Gurinas , Ruslan Salakhutdinov

Medical image data are often limited due to the expensive acquisition and annotation process. Hence, training a deep-learning model with only raw data can easily lead to overfitting. One solution to this problem is to augment the raw data…

Image and Video Processing · Electrical Eng. & Systems 2023-12-19 Xinyue Xu , Yuhan Hsi , Haonan Wang , Xiaomeng Li

Data augmentation (DA) has been widely used to improve the generalization of deep neural networks. While existing DA methods have proven effective, they often rely on augmentation operations with random magnitudes to each sample. However,…

Computer Vision and Pattern Recognition · Computer Science 2024-09-11 Suorong Yang , Furao Shen , Jian Zhao

Textual data augmentation (DA) is a prolific field of study where novel techniques to create artificial data are regularly proposed, and that has demonstrated great efficiency on small data settings, at least for text classification tasks.…

Computation and Language · Computer Science 2024-09-18 Frédéric Piedboeuf , Philippe Langlais

Data augmentation is a crucial regularization technique for deep neural networks, particularly in medical image classification. Mainstream data augmentation (DA) methods are usually applied at the image level. Due to the specificity and…

Computer Vision and Pattern Recognition · Computer Science 2024-06-28 Yaoyao Zhu , Xiuding Cai , Xueyao Wang , Xiaoqing Chen , Yu Yao , Zhongliang Fu

Visual recognition in a low-data regime is challenging and often prone to overfitting. To mitigate this issue, several data augmentation strategies have been proposed. However, standard transformations, e.g., rotation, cropping, and…

Computer Vision and Pattern Recognition · Computer Science 2023-11-08 Aniket Roy , Anshul Shah , Ketul Shah , Anirban Roy , Rama Chellappa

Scaling laws dictate that the performance of AI models is proportional to the amount of available data. Data augmentation is a promising solution to expanding the dataset size. Traditional approaches focused on augmentation using rotation,…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Fazle Rahat , M Shifat Hossain , Md Rubel Ahmed , Sumit Kumar Jha , Rickard Ewetz

Dataset Distillation (DD), a newly emerging field, aims at generating much smaller but efficient synthetic training datasets from large ones. Existing DD methods based on gradient matching achieve leading performance; however, they are…

Machine Learning · Computer Science 2023-04-18 Lei Zhang , Jie Zhang , Bowen Lei , Subhabrata Mukherjee , Xiang Pan , Bo Zhao , Caiwen Ding , Yao Li , Dongkuan Xu

Visual question answering (VQA) is challenging not only because the model has to handle multi-modal information, but also because it is just so hard to collect sufficient training examples -- there are too many questions one can ask about…

Computer Vision and Pattern Recognition · Computer Science 2022-11-10 Jihyung Kil , Cheng Zhang , Dong Xuan , Wei-Lun Chao

Adapting visual programming or prompting large language models (LLMs) to generate executable code for visual tasks like visual question answering (VQA) for specialized tasks or domains remains challenging due to high annotation and…

Computer Vision and Pattern Recognition · Computer Science 2025-11-05 Michal Shlapentokh-Rothman , Yu-Xiong Wang , Derek Hoiem

Knowledge distillation is one of the primary methods of transferring knowledge from large to small models. However, it requires massive task-specific data, which may not be plausible in many real-world applications. Data augmentation…

Computation and Language · Computer Science 2023-03-14 Ziqi Wang , Yuexin Wu , Frederick Liu , Daogao Liu , Le Hou , Hongkun Yu , Jing Li , Heng Ji

Device-directed speech detection (DDSD) is a binary classification task that separates the user's queries to a voice assistant (VA) from background speech or side conversations. This is important for achieving naturalistic user experience.…

Deep neural networks have emerged as very successful tools for image restoration and reconstruction tasks. These networks are often trained end-to-end to directly reconstruct an image from a noisy or corrupted measurement of that image. To…

Image and Video Processing · Electrical Eng. & Systems 2021-06-30 Zalan Fabian , Reinhard Heckel , Mahdi Soltanolkotabi

Large language models (LLMs) achieve state-of-the-art (SOTA) performance across language tasks, but are costly to deploy due to their size and resource demands. Knowledge Distillation (KD) addresses this by training smaller Student models…

Computation and Language · Computer Science 2026-05-19 Stella Eva Tsiapali , Cong-Thanh Do , Kate Knill