Search Results for author: Heewon Kim

Found 15 papers, 7 papers with code

Learning with Noisy Labels: Interconnection of Two Expectation-Maximizations

no code implementations9 Jan 2024 Heewon Kim, Hyun Sung Chang, Kiho Cho, Jaeyun Lee, Bohyung Han

In this framework, we provide a proper objective function and an optimization algorithm based on two expectation-maximization (EM) cycles.

Learning with noisy labels

CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution

1 code implementation21 Jul 2022 Cheeun Hong, Sungyong Baik, Heewon Kim, Seungjun Nah, Kyoung Mu Lee

In this work, to achieve high average bit-reduction with less accuracy loss, we propose a novel Content-Aware Dynamic Quantization (CADyQ) method for SR networks that allocates optimal bits to local regions and layers adaptively based on the local contents of an input image.

Image Super-Resolution Quantization

Controllable Image Enhancement

no code implementations16 Jun 2022 Heewon Kim, Kyoung Mu Lee

Specifically, an encoder-decoder framework encodes the retouching skills into latent codes and decodes them into the parameters of image signal processing (ISP) functions.

Image Enhancement Photo Retouching

Batch Normalization Tells You Which Filter is Important

no code implementations2 Dec 2021 Junghun Oh, Heewon Kim, Sungyong Baik, Cheeun Hong, Kyoung Mu Lee

The goal of filter pruning is to search for unimportant filters to remove in order to make convolutional neural networks (CNNs) efficient without sacrificing the performance in the process.

Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning

1 code implementation ICCV 2021 Sungyong Baik, Janghoon Choi, Heewon Kim, Dohee Cho, Jaesik Min, Kyoung Mu Lee

The problem lies in that each application and task may require different auxiliary loss function, especially when tasks are diverse and distinct.

Few-Shot Learning

DAQ: Channel-Wise Distribution-Aware Quantization for Deep Image Super-Resolution Networks

2 code implementations21 Dec 2020 Cheeun Hong, Heewon Kim, Sungyong Baik, Junghun Oh, Kyoung Mu Lee

Quantizing deep convolutional neural networks for image super-resolution substantially reduces their computational costs.

Image Super-Resolution Quantization

Searching for Controllable Image Restoration Networks

no code implementations ICCV 2021 Heewon Kim, Sungyong Baik, Myungsub Choi, Janghoon Choi, Kyoung Mu Lee

Diverse user preferences over images have recently led to a great amount of interest in controlling the imagery effects for image restoration tasks.

Image Restoration Neural Architecture Search

Meta-Learning with Adaptive Hyperparameters

2 code implementations NeurIPS 2020 Sungyong Baik, Myungsub Choi, Janghoon Choi, Heewon Kim, Kyoung Mu Lee

Despite its popularity, several recent works question the effectiveness of MAML when test tasks are different from training tasks, thus suggesting various task-conditioned methodology to improve the initialization.

Few-Shot Learning

Channel Attention Is All You Need for Video Frame Interpolation

1 code implementation AAAI Conference on Artificial Intelligence 2020 Myungsub Choi, Heewon Kim, Bohyung Han, Ning Xu, Kyoung Mu Lee

Prevailing video frame interpolation techniques rely heavily on optical flow estimation and require additional model complexity and computational cost; it is also susceptible to error propagation in challenging scenarios with large motion and heavy occlusion.

Motion Estimation Optical Flow Estimation +1

Fine-Grained Neural Architecture Search

no code implementations18 Nov 2019 Heewon Kim, Seokil Hong, Bohyung Han, Heesoo Myeong, Kyoung Mu Lee

We present an elegant framework of fine-grained neural architecture search (FGNAS), which allows to employ multiple heterogeneous operations within a single layer and can even generate compositional feature maps using several different base operations.

Image Classification Image Super-Resolution +1

Task-Aware Image Downscaling

no code implementations ECCV 2018 Heewon Kim, Myungsub Choi, Bee Lim, Kyoung Mu Lee

Our framework is efficient, and it can be generalized to handle an arbitrary image resizing operation.

Colorization Image Colorization +1

Enhanced Deep Residual Networks for Single Image Super-Resolution

47 code implementations10 Jul 2017 Bee Lim, Sanghyun Son, Heewon Kim, Seungjun Nah, Kyoung Mu Lee

Recent research on super-resolution has progressed with the development of deep convolutional neural networks (DCNN).

Image Super-Resolution Spectral Reconstruction

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