paper-with-me

홈 › Papers

SEAL: Simultaneous Label Hierarchy Exploration And Learning

2023-04-26 · Zhiquan Tan, ZiHao Wang, Yifan Zhang

Label hierarchy is an important source of external knowledge that can enhance classification performance. However, most existing methods rely on predefined label hierarchies that may not match the data distribution. To address this issue, we propose Simultaneous label hierarchy Exploration And Learning (SEAL), a new framework that explores the label hierarchy by augmenting the observed labels with latent labels that follow a prior hierarchical structure. Our approach uses a 1-Wasserstein metric over the tree metric space as an objective function, which enables us to simultaneously learn a data-driven label hierarchy and perform (semi-)supervised learning. We evaluate our method on several datasets and show that it achieves superior results in both supervised and semi-supervised scenarios and reveals insightful label structures. Our implementation is available at https://github.com/tzq1999/SEAL.

📄 PDF Abstract BibTeX arXiv:2304.13374

Code (1)

tzq1999/seal 공식 구현 pytorch

Similar Papers 제목 키워드 기반

SEAL: Simultaneous Exploration and Localization in Multi-Robot Systems

2023-06-22 · Ehsan Latif, Ramviyas Parasuraman

The availability of accurate localization is critical for multi-robot exploration strategies; noisy or inconsistent localization causes failure in meeting exploration objectives. We aim to achieve high localization accur…

Gaussian Processes

SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency

2021-12-02 · NeurIPS 2021 12 · Devendra Singh Chaplot, Murtaza Dalal, Saurabh Gupta, Jitendra Malik 외

In this paper, we explore how we can build upon the data and models of Internet images and use them to adapt to robot vision without requiring any extra labels. We present a framework called Self-supervised Embodied Acti…

Active LearningInstance Segmentationobject-detectionObject Detection+1

Seal2Real: Prompt Prior Learning on Diffusion Model for Unsupervised Document Seal Data Generation and Realisation

2023-10-01 · Jiancheng Huang, Yifan Liu, Yi Huang, Shifeng Chen

In document processing, seal-related tasks have very large commercial applications, such as seal segmentation, seal authenticity discrimination, seal removal, and text recognition under seals. However, these seal-related…

SEAL: Segment-wise Extractive-Abstractive Long-form Text Summarization

2020-06-18 · Yao Zhao, Mohammad Saleh, Peter J. Liu

Most prior work in the sequence-to-sequence paradigm focused on datasets with input sequence lengths in the hundreds of tokens due to the computational constraints of common RNN and Transformer architectures. In this pap…

Abstractive Text SummarizationDecoderFormText Summarization

MM-SEAL: A Large-scale Video Dataset of Multi-person Multi-grained Spatio-temporally Action Localization

2022-04-06 · Shimin Chen, Wei Li, Chen Chen, Jianyang Gu 외

In this paper, we introduce a novel large-scale video dataset dubbed MM-SEAL for multi-person multi-grained spatio-temporal action localization among human daily life. We are the first to propose a new benchmark for mult…

Action LocalizationAction RecognitionSpatio-Temporal Action LocalizationTemporal Action Localization+1