Data to 7 Oct 2026

Low-Shot Learning from Imaginary Data

arXiv 1801.05401 ↗First posted 16 Jan 2018cs.CVcited by 181

Not on the map. Why?

Abstract (arXiv)

Humans can quickly learn new visual concepts, perhaps because they can easily visualize or imagine what novel objects look like from different views. Incorporating this ability to hallucinate novel instances of new concepts might help machine vision systems perform better low-shot learning, i.e., learning concepts from few examples. We present a novel approach to low-shot learning that uses this idea. Our approach builds on recent progress in meta-learning ("learning to learn") by combining a meta-learner with a "hallucinator" that produces additional training examples, and optimizing both models jointly. Our hallucinator can be incorporated into a variety of meta-learners and provides significant gains: up to a 6 point boost in classification accuracy when only a single training example is available, yielding state-of-the-art performance on the challenging ImageNet low-shot classification benchmark.

Key facts. Cited by 181 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Jan 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 77; 2022: 57; 2023: 24; 2024: 12; 2025: 5; 2026: 5.

181 papers.

Sort:

By area:

2021Distribution Alignment: A Unified Framework for Long-tail Visual Recognitioncited by 198
2021FSCE: Few-Shot Object Detection via Contrastive Proposal Encodingcited by 168
2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
2023Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Modelscited by 91
2022Learning from Few Examples: A Summary of Approaches to Few-Shot Learningcited by 86
2021Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detectioncited by 80
2021Detecting Human-Object Interaction via Fabricated Compositional Learningcited by 79
2021Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspectioncited by 77
2021RSG: A Simple but Effective Module for Learning Imbalanced Datasetscited by 61
2021Rectifying the Shortcut Learning of Background for Few-Shot Learningcited by 51
2021Deep Metric Learning for Open World Semantic Segmentationcited by 51
2021Hallucination Improves Few-Shot Object Detectioncited by 50

38 more

2022Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigationcited by 45
2021Few-Shot Object Detection via Association and DIscriminationcited by 39
2022Generating Representative Samples for Few-Shot Classificationcited by 39
2022Adaptive Transformers for Robust Few-shot Cross-domain Face Anti-spoofingcited by 38
2022Pose for Everything: Towards Category-Agnostic Pose Estimationcited by 36
2022Visual Localization via Few-Shot Scene Region Classificationcited by 36
2023MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognitioncited by 36
2021TA2N: Two-Stage Action Alignment Network for Few-shot Action Recognitioncited by 35
2021Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgettingcited by 33
2021Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifiercited by 32
2021GistNet: a Geometric Structure Transfer Network for Long-Tailed Recognitioncited by 31
2021PFENet++: Boosting Few-shot Semantic Segmentation with the Noise-filtered Context-aware Prior Maskcited by 31
2022Memorizing Complementation Network for Few-Shot Class-Incremental Learningcited by 30
2023A Systematic Review of Few-Shot Learning in Medical Imagingcited by 28
2021Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detectioncited by 27
2022Matching Feature Sets for Few-Shot Image Classificationcited by 25
2021Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developmentscited by 23
2021Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentationcited by 23
2021How to Train Your MAML to Excel in Few-Shot Classificationcited by 22
2022Open Long-Tailed Recognition in a Dynamic Worldcited by 21
2022FHIST: A Benchmark for Few-shot Classification of Histological Imagescited by 20
2022Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroidcited by 20
2022Attribute Prototype Network for Any-Shot Learningcited by 19
2023Boosting Few-shot 3D Point Cloud Segmentation via Query-Guided Enhancementcited by 19
2021TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptationcited by 17
2021LARGE: Latent-Based Regression through GAN Semanticscited by 17
2021Few-Shot Learning with a Strong Teachercited by 16
2022Towards better understanding and better generalization of few-shot classification in histology images with contrastive learningcited by 16
2022ImaginaryNet: Learning Object Detectors without Real Images and Annotationscited by 16
2023Hallucination Improves the Performance of Unsupervised Visual Representation Learningcited by 16
2023Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learningcited by 16
2021Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learningcited by 15
2021Few-Shot Temporal Action Localization with Query Adaptive Transformercited by 15
2024Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuningcited by 15
2021Generative Modeling for Multi-task Visual Learningcited by 14
2021On the Importance of Distractors for Few-Shot Classificationcited by 14
2022A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillancecited by 14
2022Adaptive Distribution Calibration for Few-Shot Learning with Hierarchical Optimal Transportcited by 14

50 most cited of 181 All 181 (JSON)