Search Results for author: Jungbeom Lee

Found 15 papers, 7 papers with code

Mutual Suppression Network for Video Prediction using Disentangled Features

no code implementations13 Apr 2018 Jungbeom Lee, Jangho Lee, Sungmin Lee, Sungroh Yoon

Video prediction can be performed by finding features in recent frames, and using them to generate approximations to upcoming frames.

 Ranked #1 on Video Prediction on KTH (Cond metric)

Optical Flow Estimation Representation Learning +1

FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference

no code implementations CVPR 2019 Jungbeom Lee, Eunji Kim, Sungmin Lee, Jangho Lee, Sungroh Yoon

The main obstacle to weakly supervised semantic image segmentation is the difficulty of obtaining pixel-level information from coarse image-level annotations.

Image Classification Image Segmentation +1

Frame-to-Frame Aggregation of Active Regions in Web Videos for Weakly Supervised Semantic Segmentation

no code implementations ICCV 2019 Jungbeom Lee, Eunji Kim, Sungmin Lee, Jangho Lee, Sungroh Yoon

We propose a method of using videos automatically harvested from the web to identify a larger region of the target object by using temporal information, which is not present in the static image.

Object Optical Flow Estimation +2

Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation

1 code implementation CVPR 2021 Jungbeom Lee, Eunji Kim, Sungroh Yoon

Weakly supervised semantic segmentation produces a pixel-level localization from a classifier, but it is likely to restrict its focus to a small discriminative region of the target object.

Adversarial Attack Object +4

Toward Spatially Unbiased Generative Models

2 code implementations ICCV 2021 Jooyoung Choi, Jungbeom Lee, Yonghyun Jeong, Sungroh Yoon

From our observations, the generator's implicit positional encoding is translation-variant, making the generator spatially biased.

Denoising Image Generation +1

Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation

1 code implementation NeurIPS 2021 Jungbeom Lee, Jooyoung Choi, Jisoo Mok, Sungroh Yoon

Weakly supervised semantic segmentation produces pixel-level localization from class labels; however, a classifier trained on such labels is likely to focus on a small discriminative region of the target object.

Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation

Weakly Supervised Semantic Segmentation using Out-of-Distribution Data

1 code implementation CVPR 2022 Jungbeom Lee, Seong Joon Oh, Sangdoo Yun, Junsuk Choe, Eunji Kim, Sungroh Yoon

However, training on class labels only, classifiers suffer from the spurious correlation between foreground and background cues (e. g. train and rail), fundamentally bounding the performance of WSSS.

Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation

Perception Prioritized Training of Diffusion Models

5 code implementations CVPR 2022 Jooyoung Choi, Jungbeom Lee, Chaehun Shin, Sungwon Kim, Hyunwoo Kim, Sungroh Yoon

Diffusion models learn to restore noisy data, which is corrupted with different levels of noise, by optimizing the weighted sum of the corresponding loss terms, i. e., denoising score matching loss.

Denoising

Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization

no code implementations11 Apr 2022 Jungbeom Lee, Eunji Kim, Jisoo Mok, Sungroh Yoon

This manipulation is realized in an anti-adversarial manner, so that the original image is perturbed along pixel gradients in directions opposite to those used in an adversarial attack.

Adversarial Attack Object +4

Toward Interactive Regional Understanding in Vision-Large Language Models

no code implementations27 Mar 2024 Jungbeom Lee, Sanghyuk Chun, Sangdoo Yun

Recent Vision-Language Pre-training (VLP) models have demonstrated significant advancements.

Cannot find the paper you are looking for? You can Submit a new open access paper.