613 citations · 1.6k across the 49 of their papers we have counts for
9 papers · 1 filter
The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification
Seulki Park, Youngkyu Hong, Byeongho Heo +2
The problem of class imbalanced data is that the generalization performance of the classifier deteriorates due to the lack of data from minority classes. In this paper, we propose…
OCR-free Document Understanding Transformer
Geewook Kim, Teakgyu Hong, Moonbin Yim +7
Understanding document images (e.g., invoices) is a core but challenging task since it requires complex functions such as reading text and a holistic understanding of the document.…
Progressive Transmission and Inference of Deep Learning Models
Youngsoo Lee, Sangdoo Yun, Yeonghun Kim +1
Modern image files are usually progressively transmitted and provide a preview before downloading the entire image for improved user experience to cope with a slow network connecti…
Observations on K-image Expansion of Image-Mixing Augmentation for Classification
Joonhyun Jeong, Sungmin Cha, Youngjoon Yoo +3
Image-mixing augmentations (e.g., Mixup and CutMix), which typically involve mixing two images, have become the de-facto training techniques for image classification. Despite their…
Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective
Luca Scimeca, Seong Joon Oh, Sanghyuk Chun +2
Deep neural networks (DNNs) often rely on easy-to-learn discriminatory features, or cues, that are not necessarily essential to the problem at hand. For example, ducks in an image…
Normalization Matters in Weakly Supervised Object Localization
Jeesoo Kim, Junsuk Choe, Sangdoo Yun +1
Weakly-supervised object localization (WSOL) enables finding an object using a dataset without any localization information. By simply training a classification model using only im…
Influential Rank: A New Perspective of Post-training for Robust Model against Noisy Labels
Seulki Park, Hwanjun Song, Daeho Um +3
Deep neural network can easily overfit to even noisy labels due to its high capacity, which degrades the generalization performance of a model. To overcome this issue, we propose a…
Rethinking Spatial Dimensions of Vision Transformers
Byeongho Heo, Sangdoo Yun, Dongyoon Han +3
Vision Transformer (ViT) extends the application range of transformers from language processing to computer vision tasks as being an alternative architecture against the existing c…
Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels
Sangdoo Yun, Seong Joon Oh, Byeongho Heo +3
ImageNet has been arguably the most popular image classification benchmark, but it is also the one with a significant level of label noise. Recent studies have shown that many samp…