Data to 14 Oct 2026

TADAM: Task dependent adaptive metric for improved few-shot learning

arXiv 1805.10123 ↗First posted 23 May 2018cs.LG cs.AI cs.CVcited by 408

Not on the map. Why?

Abstract (arXiv)

Few-shot learning has become essential for producing models that generalize from few examples. In this work, we identify that metric scaling and metric task conditioning are important to improve the performance of few-shot algorithms. Our analysis reveals that simple metric scaling completely changes the nature of few-shot algorithm parameter updates. Metric scaling provides improvements up to 14% in accuracy for certain metrics on the mini-Imagenet 5-way 5-shot classification task. We further propose a simple and effective way of conditioning a learner on the task sample set, resulting in learning a task-dependent metric space. Moreover, we propose and empirically test a practical end-to-end optimization procedure based on auxiliary task co-training to learn a task-dependent metric space. The resulting few-shot learning model based on the task-dependent scaled metric achieves state of the art on mini-Imagenet. We confirm these results on another few-shot dataset that we introduce in this paper based on CIFAR100. Our code is publicly available at https://github.com/ElementAI/TADAM.

Key facts. Cited by 408 papers in the map (data through 14 Oct 2026). First posted on arXiv 23 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 137; 2022: 106; 2023: 66; 2024: 56; 2025: 28; 2026: 15.

408 papers.

Sort:

By area:

2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
2021A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentumcited by 106
2021On the Role of Neural Collapse in Transfer Learningcited by 100
2021Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representationscited by 96
2021Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generationcited by 93
2022Learning from Few Examples: A Summary of Approaches to Few-Shot Learningcited by 86
2021Cross-domain Few-shot Learning with Task-specific Adapterscited by 80
2021Relational Embedding for Few-Shot Classificationcited by 74
2021Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learningcited by 72
2022Test-Time Adaptation via Self-Training with Nearest Neighbor Informationcited by 64
2021Towards Gradient-based Bilevel Optimization with Non-convex Followers and Beyondcited by 63
2022Fast Finite Width Neural Tangent Kernelcited by 62

38 more

2021Learning a Universal Template for Few-shot Dataset Generalizationcited by 61
2021Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learningcited by 56
2021Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanationscited by 56
2022HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learningcited by 55
2023Learning with Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learningcited by 55
2023PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detectioncited by 53
2021Pareto Self-Supervised Training for Few-Shot Learningcited by 52
2021Deep Metric Learning for Open World Semantic Segmentationcited by 51
2021Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptationcited by 50
2022Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classificationcited by 50
2021Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learningcited by 49
2021Improving Transferability of Representations via Augmentation-Aware Self-Supervisioncited by 49
2021Shallow Bayesian Meta Learning for Real-World Few-Shot Recognitioncited by 48
2023A Closer Look at Few-shot Classification Againcited by 46
2022Task-Adaptive Few-shot Node Classificationcited by 43
2022Anomaly Detection-Inspired Few-Shot Medical Image Segmentation Through Self-Supervision With Supervoxelscited by 42
2021Learning Dynamic Alignment via Meta-filter for Few-shot Learningcited by 41
2022A Modern Self-Referential Weight Matrix That Learns to Modify Itselfcited by 41
2022Generating Representative Samples for Few-Shot Classificationcited by 39
2022Few-Shot Diffusion Modelscited by 38
2023MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognitioncited by 37
2021Partner-Assisted Learning for Few-Shot Image Classificationcited by 36
2022Rethinking Generalization in Few-Shot Classificationcited by 36
2022Learning Domain Invariant Prompt for Vision-Language Modelscited by 36
2023FedCP: Separating Feature Information for Personalized Federated Learning via Conditional Policycited by 36
2021A Survey of Self-Supervised and Few-Shot Object Detectioncited by 35
2022Sketch3T: Test-Time Training for Zero-Shot SBIRcited by 34
2022Few-shot Medical Image Segmentation with Cycle-resemblance Attentioncited by 33
2021Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifiercited by 32
2021A Metalearning Approach for Physics-Informed Neural Networks (PINNs): Application to Parameterized PDEscited by 32
2023Leveraging sparse and shared feature activations for disentangled representation learningcited by 32
2022Few-Shot Classification with Contrastive Learningcited by 31
2023Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image Classificationcited by 30
2023Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinementcited by 30
2023Semantic Prompt for Few-Shot Image Recognitioncited by 29
2021Few-shot Action Recognition with Prototype-centered Attentive Learningcited by 28
2021MetaHTR: Towards Writer-Adaptive Handwritten Text Recognitioncited by 27
2022Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learningcited by 27

50 most cited of 408 All 408 (JSON)