Dual-View Data Hallucination with Semantic Relation Guidance for Few-Shot Image Recognition
Not on the map. Why?
Abstract (arXiv)
Learning to recognize novel concepts from just a few image samples is very challenging as the learned model is easily overfitted on the few data and results in poor generalizability. One promising but underexplored solution is to compensate the novel classes by generating plausible samples. However, most existing works of this line exploit visual information only, rendering the generated data easy to be distracted by some challenging factors contained in the few available samples. Being aware of the semantic information in the textual modality that reflects human concepts, this work proposes a novel framework that exploits semantic relations to guide dual-view data hallucination for few-shot image recognition. The proposed framework enables generating more diverse and reasonable data samples for novel classes through effective information transfer from base classes. Specifically, an instance-view data hallucination module hallucinates each sample of a novel class to generate new data by employing local semantic correlated attention and global semantic feature fusion derived from base classes. Meanwhile, a prototype-view data hallucination module exploits semantic-aware measure to estimate the prototype of a novel class and the associated distribution from the few samples, which thereby harvests the prototype as a more stable sample and enables resampling a large number of samples. We conduct extensive experiments and comparisons with state-of-the-art methods on several popular few-shot benchmarks to verify the effectiveness of the proposed framework.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 54 of its 81 references that are in the map. First posted on arXiv 13 Jan 2024.
Builds on
54 of 81 references.
References · 54
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
- 2016Wide Residual Networkscited by 3,057
- 2017Prototypical Networks for Few-shot Learningcited by 3,001
- 2016Matching Networks for One Shot Learningcited by 2,246
- 2013Describing Textures in the Wildcited by 2,110
- 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
38 more
- 2018Meta-Learning with Latent Embedding Optimizationcited by 476
- 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
- 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
- 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 312
- 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
- 2017Meta Networkscited by 268
- 2017Feature Generating Networks for Zero-Shot Learningcited by 257
- 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 183
- 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
- 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
- 2018Zero-shot Recognition via Semantic Embeddings and Knowledge Graphscited by 155
- 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 135
- 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
- 2018Visual Semantic Navigation using Scene Priorscited by 127
- 2017Few-Shot Image Recognition by Predicting Parameters from Activationscited by 122
- 2019Learning Semantic-Specific Graph Representation for Multi-Label Image Recognitioncited by 116
- 2019Improved Few-Shot Visual Classificationcited by 114
- 2020Adversarial Feature Hallucination Networks for Few-Shot Learningcited by 110
- 2019Adaptive Cross-Modal Few-Shot Learningcited by 95
- 2018Delta-encoder: an effective sample synthesis method for few-shot object recognitioncited by 89
- 2019Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learningcited by 69
- 2020Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognitioncited by 69
- 2021Cross-Domain Few-Shot Classification via Adversarial Task Augmentationcited by 63
- 2018Multi-level Semantic Feature Augmentation for One-shot Learningcited by 62
- 2019Few-Shot Learning via Saliency-guided Hallucination of Samplescited by 49
- 2020DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learningcited by 49
- 2020Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learningcited by 46
- 2019An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learningcited by 38
- 2020Enhancing Few-Shot Image Classification with Unlabelled Examplescited by 32
- 2022Matching Feature Sets for Few-Shot Image Classificationcited by 25
- 2020Optimized Generic Feature Learning for Few-shot Classification across Domainscited by 23
- 2020Mixture-based Feature Space Learning for Few-shot Image Classificationcited by 23
- 2018Visual and Semantic Knowledge Transfer for Large Scale Semi-supervised Object Detectioncited by 22
- 2019A Two-Stage Approach to Few-Shot Learning for Image Recognitioncited by 18
- 2022Few-Shot Learning Meets Transformer: Unified Query-Support Transformers for Few-Shot Classificationcited by 16
- 2020Attributes-Guided and Pure-Visual Attention Alignment for Few-Shot Recognitioncited by 15
- 2021SEGA: Semantic Guided Attention on Visual Prototype for Few-Shot Learningcited by 15
- 2021Hybrid Graph Neural Networks for Few-Shot Learningcited by 15
50 most cited of 54 All 54 (JSON)
Built on by
Citing papers per year: 2025: 1.
1 paper.