mlsanityData to 7 Oct 2026

On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Survey

arXiv 2408.04879 ↗First posted 9 Aug 2024cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Zero-shot image recognition (ZSIR) aims to recognize and reason in unseen domains by learning generalized knowledge from limited data in the seen domain. The gist of ZSIR is constructing a well-aligned mapping between the input visual space and the target semantic space, which is a bottom-up paradigm inspired by the process by which humans observe the world. In recent years, ZSIR has witnessed significant progress on a broad spectrum, from theory to algorithm design, as well as widespread applications. However, to the best of our knowledge, there remains a lack of a systematic review of ZSIR from an element-wise perspective, i.e., learning fine-grained elements of data and their inferential associations. To fill the gap, this paper thoroughly investigates recent advances in element-wise ZSIR and provides a sound basis for its future development. Concretely, we first integrate three basic ZSIR tasks, i.e., object recognition, compositional recognition, and foundation model-based open-world recognition, into a unified element-wise paradigm and provide a detailed taxonomy and analysis of the main approaches. Next, we summarize the benchmarks, covering technical implementations, standardized datasets, and some more details as a library. Last, we sketch out related applications, discuss vital challenges, and suggest potential future directions.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 180 of its 292 references that are in the map. First posted on arXiv 9 Aug 2024.

Builds on

180 of 292 references.

References · 180

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020Language Models are Few-Shot Learnerscited by 32,199
  5. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  6. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  7. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  8. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  9. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  10. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  11. 2023Segment Anythingcited by 8,158
  12. 2022Generative Adversarial Networkscited by 5,603
38 more
  1. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  2. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  3. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  4. 2014Going Deeper with Convolutionscited by 4,231
  5. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  6. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  7. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  8. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  9. 2013Describing Textures in the Wildcited by 2,110
  10. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  11. 2013Fine-Grained Visual Classification of Aircraftcited by 1,701
  12. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,488
  13. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  14. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,427
  15. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  16. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  17. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  18. 2023Vision-Language Models for Vision Tasks: A Surveycited by 834
  19. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  20. 2021Domain Generalization: A Surveycited by 760
  21. 2021FLAVA: A Foundational Language And Vision Alignment Modelcited by 646
  22. 2021FILIP: Fine-grained Interactive Language-Image Pre-Trainingcited by 626
  23. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  24. 2020A Survey on Contrastive Self-supervised Learningcited by 553
  25. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
  26. 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 467
  27. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  28. 2021Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigmcited by 405
  29. 2022Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Modelscited by 379
  30. 2022Visual Classification via Description from Large Language Modelscited by 331
  31. 2023Large Language Models are Zero-Shot Rankers for Recommender Systemscited by 307
  32. 2022What does a platypus look like? Generating customized prompts for zero-shot image classificationcited by 263
  33. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  34. 2022Generating Training Data with Language Models: Towards Zero-Shot Language Understandingcited by 199
  35. 2018Zero-Shot Object Detectioncited by 189
  36. 2014Evaluation of Output Embeddings for Fine-Grained Image Classificationcited by 166
  37. 2020Attribute Prototype Network for Zero-Shot Learningcited by 160
  38. 2020A Review of Generalized Zero-Shot Learning Methodscited by 159

50 most cited of 180 All 180 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 4.

5 papers.

  1. 2024Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognitioncited by 13
  2. 2025Cluster-Aware Prompt Ensemble Learning for Few-Shot Vision-Language Model Adaptationcited by 7
  3. 2025SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learningcited by 6
  4. 2025Distributed Zero-Shot Learning for Visual Recognitioncited by 3
  5. 2025FedAPA: Server-side Gradient-Based Adaptive Personalized Aggregation for Federated Learning on Heterogeneous Datacited by 0