613 citations · 1.5k across the 47 of their papers we have counts for
26 papers · 1 filter
EgoGapBench: Benchmarking Egocentric Action Selection in Multi-Agent Scenes
Jihyeok Jung, Jeewu Lee, Sanghyeop Kim +2
Existing egocentric benchmarks have primarily constructed the egocentric setting from first-person-view data, which makes it difficult to evaluate egocentric perspective itself in…
Pretrained Visual Uncertainties
Michael Kirchhof, Mark Collier, Seong Joon Oh +1
Accurate uncertainty estimation is vital to trustworthy machine learning, yet uncertainties typically have to be learned for each task anew. This work introduces the first pretrain…
Neglected Free Lunch -- Learning Image Classifiers Using Annotation Byproducts
Dongyoon Han, Junsuk Choe, Seonghyeok Chun +5
Supervised learning of image classifiers distills human knowledge into a parametric model through pairs of images and corresponding labels (X,Y). We argue that this simple and wide…
SelecMix: Debiased Learning by Contradicting-pair Sampling
Inwoo Hwang, Sangjun Lee, Yunhyeok Kwak +4
Neural networks trained with ERM (empirical risk minimization) sometimes learn unintended decision rules, in particular when their training data is biased, i.e., when training labe…
Scratching Visual Transformer's Back with Uniform Attention
Nam Hyeon-Woo, Kim Yu-Ji, Byeongho Heo +3
The favorable performance of Vision Transformers (ViTs) is often attributed to the multi-head self-attention (MSA). The MSA enables global interactions at each layer of a ViT model…
ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCO
Sanghyuk Chun, Wonjae Kim, Song Park +2
Image-Text matching (ITM) is a common task for evaluating the quality of Vision and Language (VL) models. However, existing ITM benchmarks have a significant limitation. They have…
Weakly Supervised Semantic Segmentation using Out-of-Distribution Data
Jungbeom Lee, Seong Joon Oh, Sangdoo Yun +3
Weakly supervised semantic segmentation (WSSS) methods are often built on pixel-level localization maps obtained from a classifier. However, training on class labels only, classifi…
Keep CALM and Improve Visual Feature Attribution
Jae Myung Kim, Junsuk Choe, Zeynep Akata +1
The class activation mapping, or CAM, has been the cornerstone of feature attribution methods for multiple vision tasks. Its simplicity and effectiveness have led to wide applicati…
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…
Probabilistic Embeddings for Cross-Modal Retrieval
Sanghyuk Chun, Seong Joon Oh, Rafael Sampaio de Rezende +2
Cross-modal retrieval methods build a common representation space for samples from multiple modalities, typically from the vision and the language domains. For images and their cap…
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…
VideoMix: Rethinking Data Augmentation for Video Classification
Sangdoo Yun, Seong Joon Oh, Byeongho Heo +2
State-of-the-art video action classifiers often suffer from overfitting. They tend to be biased towards specific objects and scene cues, rather than the foreground action content,…
Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets
Junsuk Choe, Seong Joon Oh, Sanghyuk Chun +3
Weakly-supervised object localization (WSOL) has gained popularity over the last years for its promise to train localization models with only image-level labels. Since the seminal…
An Empirical Evaluation on Robustness and Uncertainty of Regularization Methods
Sanghyuk Chun, Seong Joon Oh, Sangdoo Yun +3
Despite apparent human-level performances of deep neural networks (DNN), they behave fundamentally differently from humans. They easily change predictions when small corruptions su…
Reliable Fidelity and Diversity Metrics for Generative Models
Muhammad Ferjad Naeem, Seong Joon Oh, Youngjung Uh +2
Devising indicative evaluation metrics for the image generation task remains an open problem. The most widely used metric for measuring the similarity between real and generated im…
Evaluating Weakly Supervised Object Localization Methods Right
Junsuk Choe, Seong Joon Oh, Seungho Lee +3
Weakly-supervised object localization (WSOL) has gained popularity over the last years for its promise to train localization models with only image-level labels. Since the seminal…
On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention
Junyeop Lee, Sungrae Park, Jeonghun Baek +3
Scene text recognition (STR) is the task of recognizing character sequences in natural scenes. While there have been great advances in STR methods, current methods still fail to re…
Learning De-biased Representations with Biased Representations
Hyojin Bahng, Sanghyuk Chun, Sangdoo Yun +2
Many machine learning algorithms are trained and evaluated by splitting data from a single source into training and test sets. While such focus on in-distribution learning scenario…
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
Sangdoo Yun, Dongyoon Han, Seong Joon Oh +3
Regional dropout strategies have been proposed to enhance the performance of convolutional neural network classifiers. They have proved to be effective for guiding the model to att…
What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis
Jeonghun Baek, Geewook Kim, Junyeop Lee +5
Many new proposals for scene text recognition (STR) models have been introduced in recent years. While each claim to have pushed the boundary of the technology, a holistic and fair…
Person Recognition in Personal Photo Collections
Seong Joon Oh, Rodrigo Benenson, Mario Fritz +1
People nowadays share large parts of their personal lives through social media. Being able to automatically recognise people in personal photos may greatly enhance user convenience…
Generating Descriptions with Grounded and Co-Referenced People
Anna Rohrbach, Marcus Rohrbach, Siyu Tang +2
Learning how to generate descriptions of images or videos received major interest both in the Computer Vision and Natural Language Processing communities. While a few works have pr…
Adversarial Image Perturbation for Privacy Protection -- A Game Theory Perspective
Seong Joon Oh, Mario Fritz, Bernt Schiele
Users like sharing personal photos with others through social media. At the same time, they might want to make automatic identification in such photos difficult or even impossible.…
Exploiting saliency for object segmentation from image level labels
Seong Joon Oh, Rodrigo Benenson, Anna Khoreva +3
There have been remarkable improvements in the semantic labelling task in the recent years. However, the state of the art methods rely on large-scale pixel-level annotations. This…