Rethink, Revisit, Revise: A Spiral Reinforced Self-Revised Network for Zero-Shot Learning

• URL: http://arxiv.org/abs/2112.00410v1
• Date: Wed, 1 Dec 2021 10:51:57 GMT
• Title: Rethink, Revisit, Revise: A Spiral Reinforced Self-Revised Network for Zero-Shot Learning
• Authors: Zhe Liu, Yun Li, Lina Yao, Julian McAuley, and Sam Dixon
• Abstract summary: We propose a form of spiral learning which revisits visual representations based on a sequence of attribute groups. Spiral learning aims to learn generalized local correlations, enabling models to gradually enhance global learning. Our framework outperforms state-of-the-art algorithms on four benchmark datasets in both zero-shot and generalized zero-shot settings.
• Score: 35.75113836637253
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Current approaches to Zero-Shot Learning (ZSL) struggle to learn generalizable semantic knowledge capable of capturing complex correlations. Inspired by \emph{Spiral Curriculum}, which enhances learning processes by revisiting knowledge, we propose a form of spiral learning which revisits visual representations based on a sequence of attribute groups (e.g., a combined group of \emph{color} and \emph{shape}). Spiral learning aims to learn generalized local correlations, enabling models to gradually enhance global learning and thus understand complex correlations. Our implementation is based on a 2-stage \emph{Reinforced Self-Revised (RSR)} framework: \emph{preview} and \emph{review}. RSR first previews visual information to construct diverse attribute groups in a weakly-supervised manner. Then, it spirally learns refined localities based on attribute groups and uses localities to revise global semantic correlations. Our framework outperforms state-of-the-art algorithms on four benchmark datasets in both zero-shot and generalized zero-shot settings, which demonstrates the effectiveness of spiral learning in learning generalizable and complex correlations. We also conduct extensive analysis to show that attribute groups and reinforced decision processes can capture complementary semantic information to improve predictions and aid explainability.

Related papers

• Improved Generalization Bounds for Communication Efficient Federated Learning [4.3707341422218215]
  This paper focuses on reducing the communication cost of federated learning by exploring generalization bounds and representation learning. We design a novel Federated Learning with Adaptive Local Steps (FedALS) algorithm based on our generalization bound and representation learning analysis.
  arXiv  Detail & Related papers  (2024-04-17T21:17:48Z)
• Graph-level Protein Representation Learning by Structure Knowledge Refinement [50.775264276189695]
  This paper focuses on learning representation on the whole graph level in an unsupervised manner. We propose a novel framework called Structure Knowledge Refinement (SKR) which uses data structure to determine the probability of whether a pair is positive or negative.
  arXiv  Detail & Related papers  (2024-01-05T09:05:33Z)
• Adaptive Local-Component-aware Graph Convolutional Network for One-shot Skeleton-based Action Recognition [54.23513799338309]
  We present an Adaptive Local-Component-aware Graph Convolutional Network for skeleton-based action recognition. Our method provides a stronger representation than the global embedding and helps our model reach state-of-the-art.
  arXiv  Detail & Related papers  (2022-09-21T02:33:07Z)
• Self-Supervised Visual Representation Learning with Semantic Grouping [50.14703605659837]
  We tackle the problem of learning visual representations from unlabeled scene-centric data. We propose contrastive learning from data-driven semantic slots, namely SlotCon, for joint semantic grouping and representation learning.
  arXiv  Detail & Related papers  (2022-05-30T17:50:59Z)
• Entity-Conditioned Question Generation for Robust Attention Distribution in Neural Information Retrieval [51.53892300802014]
  We show that supervised neural information retrieval models are prone to learning sparse attention patterns over passage tokens. Using a novel targeted synthetic data generation method, we teach neural IR to attend more uniformly and robustly to all entities in a given passage.
  arXiv  Detail & Related papers  (2022-04-24T22:36:48Z)
• HiCLRE: A Hierarchical Contrastive Learning Framework for Distantly Supervised Relation Extraction [24.853265244512954]
  We propose a hierarchical contrastive learning Framework for DistantlySupervised relation extraction (HiCLRE) to reduce noisy sentences. Specifically, we propose a three-level hierarchical learning framework to interact with cross levels, generating the de-noising context-aware representations. Experiments demonstrate that HiCLRE significantly outperforms strong baselines in various mainstream DSRE datasets.
  arXiv  Detail & Related papers  (2022-02-27T12:48:26Z)
• An Entropy-guided Reinforced Partial Convolutional Network for Zero-Shot Learning [77.72330187258498]
  We propose a novel Entropy-guided Reinforced Partial Convolutional Network (ERPCNet) ERPCNet extracts and aggregates localities based on semantic relevance and visual correlations without human-annotated regions. It not only discovers global-cooperative localities dynamically but also converges faster for policy gradient optimization.
  arXiv  Detail & Related papers  (2021-11-03T11:13:13Z)
• Improving Facial Attribute Recognition by Group and Graph Learning [34.39507051712628]
  Exploiting the relationships between attributes is a key challenge for improving facial attribute recognition. In this work, we are concerned with two types of correlations that are spatial and non-spatial relationships. We propose a unified network called Multi-scale Group and Graph Network.
  arXiv  Detail & Related papers  (2021-05-28T13:36:28Z)
• Zero-shot Relation Classification from Side Information [5.609443065827996]
  A zero-shot learning approach mimics the way humans learn and recognize new concepts with no prior knowledge. ZSLRC uses advanced networks that are modified to utilize weighted side (auxiliary) information. ZSLRC significantly outperforms state-of-the-art methods on supervised learning, few-shot learning, and zero-shot learning tasks.
  arXiv  Detail & Related papers  (2020-11-13T20:57:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.