HIRL: A General Framework for Hierarchical Image Representation Learning

2022-05-26 · Minghao Xu, Yuanfan Guo, Xuanyu Zhu, Jiawen Li, Zhenbang Sun, Jian Tang, Yi Xu, Bingbing Ni

Learning self-supervised image representations has been broadly studied to boost various visual understanding tasks. Existing methods typically learn a single level of image semantics like pairwise semantic similarity or image clustering patterns. However, these methods can hardly capture multiple levels of semantic information that naturally exists in an image dataset, e.g., the semantic hierarchy of "Persian cat to cat to mammal" encoded in an image database for species. It is thus unknown whether an arbitrary image self-supervised learning (SSL) approach can benefit from learning such hierarchical semantics. To answer this question, we propose a general framework for Hierarchical Image Representation Learning (HIRL). This framework aims to learn multiple semantic representations for each image, and these representations are structured to encode image semantics from fine-grained to coarse-grained. Based on a probabilistic factorization, HIRL learns the most fine-grained semantics by an off-the-shelf image SSL approach and learns multiple coarse-grained semantics by a novel semantic path discrimination scheme. We adopt six representative image SSL methods as baselines and study how they perform under HIRL. By rigorous fair comparison, performance gain is observed on all the six methods for diverse downstream tasks, which, for the first time, verifies the general effectiveness of learning hierarchical image semantics. All source code and model weights are available at https://github.com/hirl-team/HIRL

📄 PDF Abstract BibTeX arXiv:2205.13159

Code (1)

hirl-team/hirl 공식 구현 pytorch

Tasks

Image Clustering Representation Learning Self-Supervised Learning Semantic Similarity Semantic Textual Similarity

Context-Hierarchy Inverse Reinforcement Learning

2022-02-25 · Wei Gao, David Hsu, Wee Sun Lee

An inverse reinforcement learning (IRL) agent learns to act intelligently by observing expert demonstrations and learning the expert's underlying reward function. Although learning the reward functions from demonstration…

Autonomous Driving reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

Receding Horizon Inverse Reinforcement Learning

2022-06-09 · Yiqing Xu, Wei Gao, David Hsu

Inverse reinforcement learning (IRL) seeks to infer a cost function that explains the underlying goals and preferences of expert demonstrations. This paper presents receding horizon inverse reinforcement learning (RHIRL)…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Towards Scalable Verification of Deep Reinforcement Learning

2021-05-25 · Guy Amir, Michael Schapira, Guy Katz

Deep neural networks (DNNs) have gained significant popularity in recent years, becoming the state of the art in a variety of domains. In particular, deep reinforcement learning (DRL) has recently been employed to train …

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Advancing Legal Reasoning: The Integration of AI to Navigate Complexities and Biases in Global Jurisprudence with Semi-Automated Arbitration Processes (SAAPs)

2024-02-06 · Michael De'Shazer

This study consists of a novel approach toward the analysis of court judgments spanning five countries, including the United States, the United Kingdom, Rwanda, Sweden and Hong Kong. This study also explores the intersec…

Fairness Jurisprudence Legal Reasoning Navigate

Human-to-Robot Imitation in the Wild

2022-07-19 · Shikhar Bahl, Abhinav Gupta, Deepak Pathak

We approach the problem of learning by watching humans in the wild. While traditional approaches in Imitation and Reinforcement Learning are promising for learning in the real world, they are either sample inefficient or…