Residual Neural Processes

Lee, Byung Jun; Hong, Seunghoon; Kim, Kee Eung

doi:10.1609/aaai.v34i04.5883

Cited by 4 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, document image enhancement systems mostly concentrate on the intelligibility and texture of scanned images and shadow in terms of image quality (SSIM and SNR) (Tensmeyer et al 2019;Dey and Jawanpuria 2021). Few generative networks for data augmentation of document image enhancement systems are applied successfully in (Tensmeyer et al 2019;Lee, Hong, and Kim 2021).…”

Section: Introductionmentioning

confidence: 99%

Generative Pipeline for Data Augmentation of Unconstrained Document Images with Structural and Textural Degradation (Student Abstract)

Poddar

Sah

Dey

et al. 2023

AAAI

View full text Add to dashboard Cite

Computer vision applications for document image understanding (DIU) such as optical character recognition, word spotting, enhancement etc. suffer from structural deformations like strike-outs and unconstrained strokes, to name a few. They also suffer from texture degradation due to blurring, aging, or blotting-spots etc. The DIU applications with deep networks are limited to constrained environment and lack diverse data with text-level and pixel-level annotation simultaneously. In this work, we propose a generative framework to produce realistic synthetic handwritten document images with simultaneous annotation of text and corresponding pixel-level spatial foreground information. The proposed approach generates realistic backgrounds with artificial handwritten texts which supplements data-augmentation in multiple unconstrained DIU systems. The proposed framework is an early work to facilitate DIU system-evaluation in both image quality and recognition performance at a go.

show abstract

Section: Introductionmentioning

confidence: 99%

Generative Pipeline for Data Augmentation of Unconstrained Document Images with Structural and Textural Degradation (Student Abstract)

Poddar

Sah

Dey

et al. 2023

AAAI

View full text Add to dashboard Cite

show abstract

NP-PROV: Neural Processes with Position-Relevant-Only Variances

Wang

Yao

Nie

et al. 2021

Web Information Systems Engineering – WISE 2021

View full text Add to dashboard Cite

What Matters For Meta-Learning Vision Regression Tasks?

Gao

Ziesche

Vien

et al. 2022

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Meta-learning is widely used in few-shot classification and function regression due to its ability to quickly adapt to unseen tasks. However, it has not yet been well explored on regression tasks with high dimensional inputs such as images. This paper makes two main contributions that help understand this barely explored area. First, we design two new types of cross-category level vision regression tasks, namely object discovery and pose estimation of unprecedented complexity in the meta-learning domain for computer vision. To this end, we (i) exhaustively evaluate common meta-learning techniques on these tasks, and (ii) quantitatively analyze the effect of various deep learning techniques commonly used in recent meta-learning algorithms in order to strengthen the generalization capability: data augmentation, domain randomization, task augmentation and meta-regularization. Finally, we (iii) provide some insights and practical recommendations for training metalearning algorithms on vision regression tasks. Second, we propose the addition of functional contrastive learning (FCL) over the task representations in Conditional Neural Processes (CNPs) and train in an end-to-end fashion. The experimental results show that the results of prior work are misleading as a consequence of a poor choice of the loss function as well as too small meta-training sets. Specifically, we find that CNPs outperform MAML on most tasks without fine-tuning. Furthermore, we observe that naive task augmentation without a tailored design results in underfitting.

show abstract

Residual Neural Processes

Cited by 4 publications

References 6 publications

Generative Pipeline for Data Augmentation of Unconstrained Document Images with Structural and Textural Degradation (Student Abstract)

Generative Pipeline for Data Augmentation of Unconstrained Document Images with Structural and Textural Degradation (Student Abstract)

NP-PROV: Neural Processes with Position-Relevant-Only Variances

What Matters For Meta-Learning Vision Regression Tasks?

Contact Info

Product

Resources

About