613 citations · 777 across the 19 of their papers we have counts for
19 papers · 1 filter
Rethinking the Use of Vision Transformers for AI-Generated Image Detection
NaHyeon Park, Kunhee Kim, Junsuk Choe +1
Rich feature representations derived from CLIP-ViT have been widely utilized in AI-generated image detection. While most existing methods primarily leverage features from the final…
What "Not" to Detect: Negation-Aware VLMs via Structured Reasoning and Token Merging
Inha Kang, Youngsun Lim, Seonho Lee +3
State-of-the-art vision-language models (VLMs) suffer from a critical failure in understanding negation, often referred to as affirmative bias. This limitation is particularly seve…
Sampling Bag of Views for Open-Vocabulary Object Detection
Hojun Choi, Junsuk Choe, Hyunjung Shim
Existing open-vocabulary object detection (OVD) develops methods for testing unseen categories by aligning object region embeddings with corresponding VLM features. A recent study…
OVS Meets Continual Learning: Towards Sustainable Open-Vocabulary Segmentation
Dongjun Hwang, Yejin Kim, Minyoung Lee +2
Open-Vocabulary Segmentation (OVS) aims to segment classes that are not present in the training dataset. However, most existing studies assume that the training data is fixed in ad…
Weakly Supervised Semantic Segmentation for Driving Scenes
Dongseob Kim, Seungho Lee, Junsuk Choe +1
State-of-the-art techniques in weakly-supervised semantic segmentation (WSSS) using image-level labels exhibit severe performance degradation on driving scene datasets such as City…
Small Objects Matters in Weakly-supervised Semantic Segmentation
Cheolhyun Mun, Sanghuk Lee, Youngjung Uh +2
Weakly-supervised semantic segmentation (WSSS) performs pixel-wise classification given only image-level labels for training. Despite the difficulty of this task, the research comm…
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…
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…
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…
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…
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…
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…
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…
Attention-based Dropout Layer for Weakly Supervised Object Localization
Junsuk Choe, Hyunjung Shim
Weakly Supervised Object Localization (WSOL) techniques learn the object location only using image-level labels, without location annotations. A common limitation for these techniq…
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…
Generative Adversarial Networks for Unsupervised Object Co-localization
Junsuk Choe, Joo Hyun Park, Hyunjung Shim
This paper introduces a novel approach for unsupervised object co-localization using Generative Adversarial Networks (GANs). GAN is a powerful tool that can implicitly learn unknow…
Improved Techniques For Weakly-Supervised Object Localization
Junsuk Choe, Joo Hyun Park, Hyunjung Shim
We propose an improved technique for weakly-supervised object localization. Conventional methods have a limitation that they focus only on most discriminative parts of the target o…