paper-with-me

홈 › Papers

Learning task-agnostic representation via toddler-inspired learning

2021-01-27 · Kwanyoung Park, Junseok Park, Hyunseok Oh, Byoung-Tak Zhang, Youngki Lee

One of the inherent limitations of current AI systems, stemming from the passive learning mechanisms (e.g., supervised learning), is that they perform well on labeled datasets but cannot deduce knowledge on their own. To tackle this problem, we derive inspiration from a highly intentional learning system via action: the toddler. Inspired by the toddler's learning procedure, we design an interactive agent that can learn and store task-agnostic visual representation while exploring and interacting with objects in the virtual environment. Experimental results show that such obtained representation was expandable to various vision tasks such as image classification, object localization, and distance estimation tasks. In specific, the proposed model achieved 100%, 75.1% accuracy and 1.62% relative error, respectively, which is noticeably better than autoencoder-based model (99.7%, 66.1%, 1.95%), and also comparable with those of supervised models (100%, 87.3%, 0.71%).

📄 PDF Abstract BibTeX arXiv:2101.11221

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage ClassificationObject Localization

Similar Papers 제목 키워드 기반

Active Gaze Behavior Boosts Self-Supervised Object Learning

2024-11-04 · Zhengyang Yu, Arthur Aubret, Marcel C. Raabe, Jane Yang 외

Due to significant variations in the projection of the same object from different viewpoints, machine learning algorithms struggle to recognize the same object across various perspectives. In contrast, toddlers quickly l…

ObjectObject RecognitionSelf-Supervised Learning

Unveiling the Significance of Toddler-Inspired Reward Transition in Goal-Oriented Reinforcement Learning

2024-03-11 · Junseok Park, Yoonsung Kim, Hee Bin Yoo, Min Whoo Lee 외

Toddlers evolve from free exploration with sparse feedback to exploiting prior experiences for goal-directed learning with denser rewards. Drawing inspiration from this Toddler-Inspired Reward Transition, we set out to e…

Reinforcement Learning (RL)

From Sparse to Dense: Toddler-inspired Reward Transition in Goal-Oriented Reinforcement Learning

2025-01-29 · Junseok Park, Hyeonseo Yang, Min Whoo Lee, Won-Seok Choi 외

Reinforcement learning (RL) agents often face challenges in balancing exploration and exploitation, particularly in environments where sparse or dense rewards bias learning. Biological systems, such as human toddlers, na…

NavigateReinforcement Learning (RL)

ToddlerDiffusion: Interactive Structured Image Generation with Cascaded Schrödinger Bridge

2023-11-24 · Eslam Abdelrahman, Liangbing Zhao, Vincent Tao Hu, Matthieu Cord 외

Diffusion models break down the challenging task of generating data from high-dimensional distributions into a series of easier denoising steps. Inspired by this paradigm, we propose a novel approach that extends the dif…

DenoisingImage Generation

Enhance Gender and Identity Preservation in Face Aging Simulation for Infants and Toddlers

2020-11-15 · Yao Xiao, Yijun Zhao

Realistic age-progressed photos provide invaluable biometric information in a wide range of applications. In recent years, deep learning-based approaches have made remarkable progress in modeling the aging process of the…