mlsanityData to 7 Oct 2026

Shaping Visual Representations with Language for Few-shot Classification

arXiv 1911.02683 ↗First posted 6 Nov 2019cs.CV cs.CLcited by 27

Not on the map. Why?

Abstract (arXiv)

By describing the features and abstractions of our world, language is a crucial tool for human learning and a promising source of supervision for machine learning models. We use language to improve few-shot visual classification in the underexplored scenario where natural language task descriptions are available during training, but unavailable for novel tasks at test time. Existing models for this setting sample new descriptions at test time and use those to classify images. Instead, we propose language-shaped learning (LSL), an end-to-end model that regularizes visual representations to predict language. LSL is conceptually simpler, more data efficient, and outperforms baselines in two challenging few-shot domains.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 10; 2022: 10; 2023: 3; 2024: 4.

27 papers.

Sort:

By area:

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2022Can language models learn from explanations in context?cited by 248
  3. 2023Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Modelscited by 91
  4. 2023Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinementcited by 89
  5. 2021VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognitioncited by 65
  6. 2021Leveraging Language to Learn Program Abstractions and Search Heuristicscited by 44
  7. 2021Tell me why! Explanations support learning relational and causal structurecited by 36
  8. 2022Fixing Model Bugs with Natural Language Patchescited by 32
  9. 2022On Guiding Visual Attention with Language Specificationcited by 30
  10. 2021Supervising Model Attention with Human Explanations for Robust Natural Language Inferencecited by 29
  11. 2024Explaining Datasets in Words: Statistical Models with Natural Language Parameterscited by 21
  12. 2022Using Natural Language and Program Abstractions to Instill Human Inductive Biases in Machinescited by 20
15 more
  1. 2021Rich Semantics Improve Few-shot Learningcited by 15
  2. 2024A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysiscited by 14
  3. 2022G^3: Geolocation via Guidebook Groundingcited by 12
  4. 2021Multimodality in Meta-Learning: A Comprehensive Surveycited by 11
  5. 2023Predictive Chemistry Augmented with Text Retrievalcited by 9
  6. 2022Improving Few-Shot Image Classification Using Machine- and User-Generated Natural Language Descriptionscited by 6
  7. 2022Learning to Reason With Relational Abstractionscited by 5
  8. 2021TexRel: a Green Family of Datasets for Emergent Communications on Relationscited by 3
  9. 2022Visual-Semantic Contrastive Alignment for Few-Shot Image Classificationcited by 3
  10. 2021Embedding Adaptation is Still Needed for Few-Shot Learningcited by 2
  11. 2022SemSup: Semantic Supervision for Simple and Scalable Zero-shot Generalizationcited by 2
  12. 2024One-Stage Open-Vocabulary Temporal Action Detection Leveraging Temporal Multi-scale and Action Label Featurescited by 2
  13. 2022Semantics-driven Attentive Few-shot Learning over Clean and Noisy Samplescited by 1
  14. 2021Neural Abstructions: Abstractions that Support Construction for Grounded Language Learningcited by 0
  15. 2024Reading Is Believing: Revisiting Language Bottleneck Models for Image Classificationcited by 0