小样本学习论文趋势 2023–2026

主要结论

• 小样本学习论文从 2023 年的 251 篇降到 2026 年的 224 篇，热度在回落。
• CVPR 是发小样本学习论文最多的会议，2023–2026 年共 303 篇，占四个会议总量的 34%。
• 交叉方向里涨得最快的是扩散模型：同时属于两个主题的论文从 2023 年的 4 篇增至 2026 年的 24 篇。
• 在「元学习与迁移」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的基础模型适配是 3.8 倍，小样本学习是 0.9 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026BAPM: Boundary-Aware Prompt Mining for Training-Free Few-Shot Medical Image Segmentation
• ICML 2026Bayes-inspired Integration of Pretrained Priors and Few-Shot Evidence for Few-Shot Classification
• ICLR 2026Adaptive Concept Discovery for Interpretable Few-Shot Text Classification
• CVPR 2026A Closer Look at Cross-Domain Few-Shot Object Detection Fine-Tuning Matters
• NeurIPS 2025A Few Moments Please: Scalable Graphon Learning via Moment Matching
• ICML 2025FedBEns: One-Shot Federated Learning based on Bayesian Ensemble
• ICLR 2025Dist Loss: Enhancing Regression in Few-Shot Region through Distribution Distance Constraint
• CVPR 20253D Prior Is All You Need: Cross-Task Few-shot 2D Gaze Estimation
• NeurIPS 2024Few-shot Algorithms for Consistent Neural Decoding (FALCON) Benchmark
• ICML 2024Accelerating Convergence in Bayesian Few-Shot Classification
• ICLR 2024Few-shot Hybrid Domain Adaptation of Image Generator
• CVPR 2024Deformable One-shot Face Stylization via DINO Semantic Guidance
• NeurIPS 2023Alignment with human representations supports robust few-shot learning
• ICML 2023A Category-theoretical Meta-analysis of Definitions of Disentanglement
• ICLR 2023Bidirectional Language Models Are Also Few-shot Learners
• CVPR 2023A Meta-Learning Approach to Predicting Performance and Data Requirements
• NeurIPS 2026Beyond Normal References: Discriminative Few-Shot Anomaly Detection
• ICML 2026BiCrossNet with Decoupled Dual Generators: A Parameter‑Efficient and Generalizable Few‑Shot Custom Gesture Recognition Framework
• ICLR 2026Dual Distillation for Few-Shot Anomaly Detection
• CVPR 2026Beyond Patches Global-aware Autoregressive Model for Multimodal Few-Shot Font Generation

全部小样本学习论文

共 897 篇，第 2 / 18 页

51. CVPR 2026ProjFlow Projection Sampling with Flow Matching for Zero-Shot Exact Spatial
52. CVPR 2026PromptStereo Zero-Shot Stereo Matching via Structure and Motion Prompts
53. CVPR 2026Quantized Residuals to Continuous Prompts for Few-Shot Class Incremental Learning
54. CVPR 2026Reading Your Actions Learning Generalizable Action Representations via Pre-training AEMG
55. CVPR 2026Reclaiming Lost Text Layers for Source-Free Cross-Domain Few-Shot Learning
56. CVPR 2026Reevaluating the Intra-Modal Misalignment Hypothesis in CLIP
57. CVPR 2026RefTon Reference person shot assist virtual Try-on
58. CVPR 2026Remedying Target-Domain Astigmatism for Cross-Domain Few-Shot Object Detection
59. CVPR 2026Retrieve and Segment Are a Few Examples Enough to Bridge
60. CVPR 2026Robustness Under Data Scarcity Few-Shot Continual Adversarial Training for Evolving
61. CVPR 2026SD-FSMIS Adapting Stable Diffusion for Few-Shot Medical Image Segmentation
62. CVPR 2026Semantic-Guided Global-Local Collaborative Prompt Learning for Few-Shot Class Incremental Learning
63. CVPR 2026SkeletonContext Skeleton-side Context Prompt Learning for Zero-Shot Skeleton-based Action Recognition
64. CVPR 2026STiTch Semantic Transition and Transportation in Collaboration for Training-Free Zero-Shot
65. CVPR 2026SubspaceAD Training-Free Few-Shot Anomaly Detection via Subspace Modeling
66. CVPR 2026SWIFT Sliding Window Reconstruction for Few-Shot Training-Free Generated Video Attribution
67. CVPR 2026TAPE Task-Adaptive Prototype Evolution in Audio-Language Models for Fully Few-shot
68. CVPR 2026Towards Multimodal Domain Generalization with Few Labels
69. CVPR 2026Training-Only Heterogeneous Image-Patch-Text Graph Supervision for Advancing Few-Shot Learning Adapters
70. CVPR 2026Uni-DAD Unified Distillation and Adaptation of Diffusion Models for Few-step
71. CVPR 2026Universal-to-Specific Dynamic Knowledge-Guided Multiple Instance Learning for Few-Shot Whole Slide
72. CVPR 2026Unlocking Pre-trained Weights Parameter Inheritance for Zero-Shot Initialization
73. CVPR 2026VGGT-360 Geometry-Consistent Zero-Shot Panoramic Depth Estimation
74. CVPR 2026What Makes Good Synthetic Training Data for Zero-Shot Stereo Matching
75. CVPR 2026X-WIN Building Chest Radiograph World Model via Predictive Sensing
76. CVPR 2026Your Dissimilarities Define You Complementary Learning Exploiting Class Diversities
77. CVPR 2026Zero-shot Detection of AI-Generated Image via RAW-RGB Alignment
78. CVPR 2026Zero-Shot Reconstruction of Animatable 3D Avatars with Cloth Dynamics from
79. ICLR 2026A One-shot Framework for Directed Evolution of Antibodies
80. ICLR 2026Adaptive Concept Discovery for Interpretable Few-Shot Text Classification
81. ICLR 2026Boomerang Distillation Enables Zero-Shot Model Size Interpolation
82. ICLR 2026Compositional Generalization through Gradient Search in Nonparametric Latent Space
83. ICLR 2026Consistency-Driven Calibration and Matching for Few-Shot Class Incremental Learning
84. ICLR 2026Dual Distillation for Few-Shot Anomaly Detection
85. ICLR 2026DVLA-RL: Dual-Level Vision–Language Alignment with Reinforcement Learning Gating for Few-Shot Learning
86. ICLR 2026EdgeCape: Edge Weight Prediction For Category-Agnostic Pose Estimation
87. ICLR 2026Efficient Zero-shot Inpainting with Decoupled Diffusion Guidance
88. ICLR 2026Evaluating Data Influence in Meta Learning
89. ICLR 2026Exploiting Low-Dimensional Manifold of Features for Few-shot Whole Slide Image Classification
90. ICLR 2026Exploring Cross-Modal Flows for Few-Shot Learning
91. ICLR 2026FastGHA: Generalized Few-Shot 3D Gaussian Head Avatars with Real-Time Animation
92. ICLR 2026Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors
93. ICLR 2026FSOD-VFM: Few-Shot Object Detection with Vision Foundation Models and Graph Diffusion
94. ICLR 2026FSPO: Few-Shot Optimization of Synthetic Preferences Effectively Personalizes to Real Users
95. ICLR 2026GNN-as-Judge: Unleashing the Power of LLMs for Graph Few-shot Semi-supervised Learning with GNN Feedback
96. ICLR 2026Identifying Robust Neural Pathways: Few-Shot Adversarial Mask Tuning for Vision-Language Models
97. ICLR 2026Learnability and Privacy Vulnerability are Entangled in a Few Critical Weights
98. ICLR 2026Learning from Algorithm Feedback: One-Shot SAT Solver Guidance with GNNs
99. ICLR 2026Low-Rank Few-Shot Node Classification by Node-Level Graph Diffusion
100. ICLR 2026Meta-Adaptive Prompt Distillation for Few-Shot Visual Question Answering

常见问题

2023–2026 年四大会议一共有多少篇小样本学习论文？

共 898 篇，按年份分别是 2023 年 251 篇、2024 年 220 篇、2025 年 203 篇、2026 年 224 篇。

NeurIPS 2026 有多少篇小样本学习论文？

NeurIPS 2026 有 51 篇小样本学习论文，上一届是 68 篇。

ICLR 2026 有多少篇小样本学习论文？

ICLR 2026 有 38 篇小样本学习论文，上一届是 36 篇。

ICML 2026 有多少篇小样本学习论文？

ICML 2026 有 56 篇小样本学习论文，上一届是 35 篇。

CVPR 2026 有多少篇小样本学习论文？

CVPR 2026 有 79 篇小样本学习论文，上一届是 64 篇。

哪个会议的小样本学习论文最多？

CVPR，2023–2026 年共 303 篇。