mlsanityData to 14 Oct 2026

Locality and compositionality in zero-shot learning

arXiv 1912.12179 ↗First posted 20 Dec 2019cs.CV cs.LGcited by 29

Not on the map. Why?

Abstract (arXiv)

In this work we study locality and compositionality in the context of learning representations for Zero Shot Learning (ZSL). In order to well-isolate the importance of these properties in learned representations, we impose the additional constraint that, differently from most recent work in ZSL, no pre-training on different datasets (e.g. ImageNet) is performed. The results of our experiments show how locality, in terms of small parts of the input, and compositionality, i.e. how well can the learned representations be expressed as a function of a smaller vocabulary, are both deeply related to generalization and motivate the focus on more local-aware models in future research directions for representation learning.

Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 10; 2022: 11; 2023: 3; 2024: 2; 2025: 2; 2026: 1.

29 papers.

Sort:

By area:

  1. 2021Goal-Oriented Gaze Estimation for Zero-Shot Learningcited by 68
  2. 2021Independent Prototype Propagation for Zero-Shot Compositionalitycited by 42
  3. 2022Open-vocabulary Attribute Detectioncited by 29
  4. 2022How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Compositioncited by 27
  5. 2023Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximizationcited by 24
  6. 2021Cross-Trajectory Representation Learning for Zero-Shot Generalization in RLcited by 20
  7. 2022Attribute Prototype Network for Any-Shot Learningcited by 19
  8. 2024COMAE: COMprehensive Attribute Exploration for Zero-shot Hashingcited by 16
  9. 2021Zero-shot Node Classification with Decomposed Graph Prototype Networkcited by 15
  10. 2022Cross-modal Representation Learning for Zero-shot Action Recognitioncited by 15
  11. 2021Contrastive Attraction and Contrastive Repulsion for Representation Learningcited by 13
  12. 2021Region Semantically Aligned Network for Zero-Shot Learningcited by 6
17 more
  1. 2022Global Contrastive Batch Sampling via Optimization on Sample Permutationscited by 5
  2. 2021An Entropy-guided Reinforced Partial Convolutional Network for Zero-Shot Learningcited by 4
  3. 2022Diversity-boosted Generalization-Specialization Balancing for Zero-shot Learningcited by 4
  4. 2023Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learningcited by 4
  5. 2025Learning Skill-Attributes for Transferable Assessment in Videocited by 4
  6. 2024LLM-TS Integrator: Integrating LLM for Enhanced Time Series Modelingcited by 3
  7. 2021Compositional Fine-Grained Low-Shot Learningcited by 1
  8. 2022Style-Content Disentanglement in Language-Image Pretraining Representations for Zero-Shot Sketch-to-Image Synthesiscited by 1
  9. 2022Self-supervised multimodal neuroimaging yields predictive representations for a spectrum of Alzheimer's phenotypescited by 1
  10. 2021Concepts, Properties and an Approach for Compositional Generalizationcited by 0
  11. 2021What Remains of Visual Semantic Embeddingscited by 0
  12. 2022The Sandbox Environment for Generalizable Agent Research (SEGAR)cited by 0
  13. 2022On a Built-in Conflict between Deep Learning and Systematic Generalizationcited by 0
  14. 2022A Short Survey of Systematic Generalizationcited by 0
  15. 2023Robust Reinforcement Learning Objectives for Sequential Recommender Systemscited by 0
  16. 2025ResNetVLLM -- Multi-modal Vision LLM for the Video Understanding Taskcited by 0
  17. 2026Zero-Shot Skeleton-Based Action Anticipationcited by 0