Search Results for author: Chun-Yi Lee

Found 26 papers, 8 papers with code

Cascaded Local Implicit Transformer for Arbitrary-Scale Super-Resolution

1 code implementation29 Mar 2023 Hao-Wei Chen, Yu-Syuan Xu, Min-Fong Hong, Yi-Min Tsai, Hsien-Kai Kuo, Chun-Yi Lee

Implicit neural representation has recently shown a promising ability in representing images with arbitrary resolutions.


Local Implicit Normalizing Flow for Arbitrary-Scale Image Super-Resolution

no code implementations9 Mar 2023 Jie-En Yao, Li-Yuan Tsao, Yi-Chen Lo, Roy Tseng, Chia-Che Chang, Chun-Yi Lee

Flow-based methods have demonstrated promising results in addressing the ill-posed nature of super-resolution (SR) by learning the distribution of high-resolution (HR) images with the normalizing flow.

Image Super-Resolution

Vision based Virtual Guidance for Navigation

no code implementations5 Mar 2023 Hsuan-Kung Yang, Yu-Ying Chen, Tsung-Chih Chiang, Chia-Chuan Hsu, Chun-Chia Huang, Chun-Wei Huang, Jou-Min Liu, Ting-Ru Liu, Tsu-Ching Hsiao, Chun-Yi Lee

This paper explores the impact of virtual guidance on mid-level representation-based navigation, where an agent performs navigation tasks based solely on visual observations.


ELDA: Using Edges to Have an Edge on Semantic Segmentation Based UDA

1 code implementation16 Nov 2022 Ting-Hsuan Liao, Huang-Ru Liao, Shan-Ya Yang, Jie-En Yao, Li-Yuan Tsao, Hsu-Shen Liu, Bo-Wun Cheng, Chen-Hao Chao, Chia-Che Chang, Yi-Chen Lo, Chun-Yi Lee

Despite their effectiveness, using depth as domain invariant information in UDA tasks may lead to multiple issues, such as excessively high extraction costs and difficulties in achieving a reliable prediction quality.

Semantic Segmentation Synthetic-to-Real Translation +1

On Investigating the Conservative Property of Score-Based Generative Models

no code implementations26 Sep 2022 Chen-Hao Chao, Wei-Fang Sun, Bo-Wun Cheng, Chun-Yi Lee

Existing Score-based Generative Models (SGMs) can be categorized into constrained SGMs (CSGMs) or unconstrained SGMs (USGMs) according to their parameterization approaches.

Pixel-Wise Prediction based Visual Odometry via Uncertainty Estimation

no code implementations18 Aug 2022 Hao-Wei Chen, Ting-Hsuan Liao, Hsuan-Kung Yang, Chun-Yi Lee

This paper introduces pixel-wise prediction based visual odometry (PWVO), which is a dense prediction task that evaluates the values of translation and rotation for every pixel in its input observations.

Translation Visual Odometry

Denoising Likelihood Score Matching for Conditional Score-based Data Generation

1 code implementation ICLR 2022 Chen-Hao Chao, Wei-Fang Sun, Bo-Wun Cheng, Yi-Chen Lo, Chia-Che Chang, Yu-Lun Liu, Yu-Lin Chang, Chia-Ping Chen, Chun-Yi Lee

These methods facilitate the training procedure of conditional score models, as a mixture of scores can be separately estimated using a score model and a classifier.


Investigation of Factorized Optical Flows as Mid-Level Representations

no code implementations9 Mar 2022 Hsuan-Kung Yang, Tsu-Ching Hsiao, Ting-Hsuan Liao, Hsu-Shen Liu, Li-Yuan Tsao, Tzu-Wen Wang, Shan-Ya Yang, Yu-Wen Chen, Huang-Ru Liao, Chun-Yi Lee

In this paper, we introduce a new concept of incorporating factorized flow maps as mid-level representations, for bridging the perception and the control modules in modular learning based robotic frameworks.

Optical Flow Estimation reinforcement-learning +1

Variable-Length Music Score Infilling via XLNet and Musically Specialized Positional Encoding

1 code implementation11 Aug 2021 Chin-Jui Chang, Chun-Yi Lee, Yi-Hsuan Yang

This paper proposes a new self-attention based model for music score infilling, i. e., to generate a polyphonic music sequence that fills in the gap between given past and future contexts.

Rethinking Ensemble-Distillation for Semantic Segmentation Based Unsupervised Domain Adaptation

1 code implementation29 Apr 2021 Chen-Hao Chao, Bo-Wun Cheng, Chun-Yi Lee

Recent researches on unsupervised domain adaptation (UDA) have demonstrated that end-to-end ensemble learning frameworks serve as a compelling option for UDA tasks.

Ensemble Learning Semantic Segmentation +1

DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning

1 code implementation16 Feb 2021 Wei-Fang Sun, Cheng-Kuang Lee, Chun-Yi Lee

In fully cooperative multi-agent reinforcement learning (MARL) settings, the environments are highly stochastic due to the partial observability of each agent and the continuously changing policies of the other agents.

Q-Learning SMAC+ +1

Semantic Segmentation Based Unsupervised Domain Adaptation via Pseudo-Label Fusion

no code implementations1 Jan 2021 Chen-Hao Chao, Bo-Wun Cheng, Chien Feng, Chun-Yi Lee

In this paper, we propose a pseudo label fusion framework (PLF), a learning framework developed to deal with the domain gap between a source domain and a target domain for performing semantic segmentation based UDA in the unseen target domain.

Pseudo Label

Toward Synergism in Macro Action Ensembles

1 code implementation1 Jan 2021 Yu Ming Chen, Kuan-Yu Chang, Chien Liu, Tsu-Ching Hsiao, Zhang-Wei Hong, Chun-Yi Lee

Macro actions have been demonstrated to be beneficial for the learning processes of an agent.

Neural Architecture Search

Mixture of Step Returns in Bootstrapped DQN

no code implementations16 Jul 2020 Po-Han Chiang, Hsuan-Kung Yang, Zhang-Wei Hong, Chun-Yi Lee

Nevertheless, integrating step returns into a single target sacrifices the diversity of the advantages offered by different step return targets.

Reusability and Transferability of Macro Actions for Reinforcement Learning

no code implementations5 Aug 2019 Yi-Hsiang Chang, Kuan-Yu Chang, Henry Kuo, Chun-Yi Lee

However, by using a proper macro action, defined as a sequence of primitive actions, an agent is able to bypass intermediate states to a farther state and facilitate its learning procedure.

reinforcement-learning Reinforcement Learning (RL)

Exploration via Flow-Based Intrinsic Rewards

1 code implementation24 May 2019 Hsuan-Kung Yang, Po-Han Chiang, Min-Fong Hong, Chun-Yi Lee

Exploration bonuses derived from the novelty of observations in an environment have become a popular approach to motivate exploration for reinforcement learning (RL) agents in the past few years.

Atari Games Optical Flow Estimation +1

A Self-Supervised Method for Mapping Human Instructions to Robot Policies

no code implementations ICLR 2019 Hsin-Wei Yu, Po-Yu Wu, Chih-An Tsao, You-An Shen, Shih-Hsuan Lin, Zhang-Wei Hong, Yi-Hsiang Chang, Chun-Yi Lee

In this paper, we propose a modular approach which separates the instruction-to-action mapping procedure into two separate stages.

Never Forget: Balancing Exploration and Exploitation via Learning Optical Flow

no code implementations24 Jan 2019 Hsuan-Kung Yang, Po-Han Chiang, Kuan-Wei Ho, Min-Fong Hong, Chun-Yi Lee

We propose to employ optical flow estimation errors to examine the novelty of new observations, such that agents are able to memorize and understand the visited states in a more comprehensive fashion.

Optical Flow Estimation

Visual Relationship Prediction via Label Clustering and Incorporation of Depth Information

no code implementations9 Sep 2018 Hsuan-Kung Yang, An-Chieh Cheng, Kuan-Wei Ho, Tsu-Jui Fu, Chun-Yi Lee

The additional depth prediction path supplements the relationship prediction model in a way that bounding boxes or segmentation masks are unable to deliver.

Depth Estimation Depth Prediction +3

Adversarial Active Exploration for Inverse Dynamics Model Learning

no code implementations ICLR 2019 Zhang-Wei Hong, Tsu-Jui Fu, Tzu-Yun Shann, Yi-Hsiang Chang, Chun-Yi Lee

Our framework consists of a deep reinforcement learning (DRL) agent and an inverse dynamics model contesting with each other.

Imitation Learning

Dynamic Video Segmentation Network

no code implementations CVPR 2018 Yu-Syuan Xu, Tsu-Jui Fu, Hsuan-Kung Yang, Chun-Yi Lee

We explore the use of a decision network to adaptively assign different frame regions to different networks based on a metric called expected confidence score.

Video Segmentation Video Semantic Segmentation

Diversity-Driven Exploration Strategy for Deep Reinforcement Learning

no code implementations NeurIPS 2018 Zhang-Wei Hong, Tzu-Yun Shann, Shih-Yang Su, Yi-Hsiang Chang, Chun-Yi Lee

Efficient exploration remains a challenging research problem in reinforcement learning, especially when an environment contains large state spaces, deceptive local optima, or sparse rewards.

Efficient Exploration reinforcement-learning +1

Virtual-to-Real: Learning to Control in Visual Semantic Segmentation

no code implementations1 Feb 2018 Zhang-Wei Hong, Chen Yu-Ming, Shih-Yang Su, Tzu-Yun Shann, Yi-Hsiang Chang, Hsuan-Kung Yang, Brian Hsi-Lin Ho, Chih-Chieh Tu, Yueh-Chuan Chang, Tsu-Ching Hsiao, Hsin-Wei Hsiao, Sih-Pin Lai, Chun-Yi Lee

Collecting training data from the physical world is usually time-consuming and even dangerous for fragile robots, and thus, recent advances in robot learning advocate the use of simulators as the training platform.

Image Segmentation Semantic Segmentation

A Deep Policy Inference Q-Network for Multi-Agent Systems

no code implementations21 Dec 2017 Zhang-Wei Hong, Shih-Yang Su, Tzu-Yun Shann, Yi-Hsiang Chang, Chun-Yi Lee

DPIQN incorporates the learned policy features as a hidden vector into its own deep Q-network (DQN), such that it is able to predict better Q values for the controllable agents than the state-of-the-art deep reinforcement learning models.

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