域适应论文趋势 2023–2026

主要结论

• 域适应论文从 2023 年的 174 篇增长到 2026 年的 263 篇，三年间扩大到约 1.5 倍。
• CVPR 是发域适应论文最多的会议，2023–2026 年共 268 篇，占四个会议总量的 31%。
• 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 7 篇增至 2026 年的 38 篇。
• 在「元学习与迁移」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的基础模型适配是 3.8 倍，域适应是 1.5 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 2026A Dual-Domain Vision Transformer with Spectral Positional Bias
• ICML 2026Bayesian Meta-Learning with Expert Feedback for Task-Shift Adaptation through Causal Embeddings
• ICLR 2026Bayesian Evidence-Driven Prototype Evolution for Federated Domain Adaptation
• CVPR 2026Anatomical Domain Shifts Test-time Heterogeneous Adaptation for 3D Human Pose
• NeurIPS 20253DPE-Gaze:Unlocking the Potential of 3D Facial Priors for Generalized Gaze Estimation
• ICML 2025A General Representation-Based Approach to Multi-Source Domain Adaptation
• ICLR 2025Adaptive Energy Alignment for Accelerating Test-Time Adaptation
• CVPR 2025A4A: Adapter for Adapter Transfer via All-for-All Mapping for Cross-Architecture Models
• NeurIPS 2024A Cross-Domain Benchmark for Active Learning
• ICML 2024Batch Singular Value Polarization and Weighted Semantic Augmentation for Universal Domain Adaptation
• ICLR 2024Adapting Large Language Models via Reading Comprehension
• CVPR 2024Day-Night Cross-domain Vehicle Re-identification
• NeurIPS 2023(Almost) Provable Error Bounds Under Distribution Shift via Disagreement Discrepancy
• ICML 2023In Search for a Generalizable Method for Source Free Domain Adaptation
• ICLR 2023Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation
• CVPR 2023A New Benchmark: On the Utility of Synthetic Data With Blender for Bare Supervised Learning and Downstream Domain Adaptation
• NeurIPS 2026A unified pairwise distribution matching framework for graph domain adaptation under structure shift
• ICML 2026Content-Style Identification via Differential Independence
• ICLR 2026Beyond In-Domain Detection: SpikeScore for Cross-Domain Hallucination Detection
• CVPR 2026Bridge Basis-Driven Causal Inference Marries VFMs for Domain Generalization

全部域适应论文

共 209 篇，第 2 / 5 页

51. CVPR 2024Single Domain Generalization for Crowd Counting
52. CVPR 2024Single-to-Dual-View Adaptation for Egocentric 3D Hand Pose Estimation
53. CVPR 2024Source-Free Domain Adaptation with Frozen Multimodal Foundation Model
54. CVPR 2024Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation
55. CVPR 2024Stable Neighbor Denoising for Source-free Domain Adaptive Segmentation
56. CVPR 2024Test-Time Adaptation for Depth Completion
57. CVPR 2024Unbiased Faster R-CNN for Single-source Domain Generalized Object Detection
58. CVPR 2024Understanding and Improving Source-free Domain Adaptation from a Theoretical Perspective
59. CVPR 2024Unified Entropy Optimization for Open-Set Test-Time Adaptation
60. CVPR 2024Unified Language-driven Zero-shot Domain Adaptation
61. CVPR 2024Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias
62. CVPR 2024Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training
63. CVPR 2024Unveiling the Unknown: Unleashing the Power of Unknown to Known in Open-Set Source-Free Domain Adaptation
64. CVPR 2024View From Above: Orthogonal-View aware Cross-view Localization
65. CVPR 2024Wonder3D: Single Image to 3D using Cross-Domain Diffusion
66. ICLR 2024A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
67. ICLR 2024Active Test-Time Adaptation: Theoretical Analyses and An Algorithm
68. ICLR 2024Adapting Large Language Models via Reading Comprehension
69. ICLR 2024Adapting to Distribution Shift by Visual Domain Prompt Generation
70. ICLR 2024AUGCAL: Improving Sim2Real Adaptation by Uncertainty Calibration on Augmented Synthetic Images
71. ICLR 2024BayesPrompt: Prompting Large-Scale Pre-Trained Language Models on Few-shot Inference via Debiased Domain Abstraction
72. ICLR 2024Can We Evaluate Domain Adaptation Models Without Target-Domain Labels?
73. ICLR 2024Class Probability Matching with Calibrated Networks for Label Shift Adaption
74. ICLR 2024DDMI: Domain-agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations
75. ICLR 2024Dissecting learning and forgetting in language model finetuning
76. ICLR 2024Domain constraints improve risk prediction when outcome data is missing
77. ICLR 2024Domain-Inspired Sharpness-Aware Minimization Under Domain Shifts
78. ICLR 2024DREAM: Dual Structured Exploration with Mixup for Open-set Graph Domain Adaption
79. ICLR 2024Exploring the Common Appearance-Boundary Adaptation for Nighttime Optical Flow
80. ICLR 2024FedWon: Triumphing Multi-domain Federated Learning Without Normalization
81. ICLR 2024Few-shot Hybrid Domain Adaptation of Image Generator
82. ICLR 2024Gradual Domain Adaptation via Gradient Flow
83. ICLR 2024Improving Domain Generalization with Domain Relations
84. ICLR 2024Improving Non-Transferable Representation Learning by Harnessing Content and Style
85. ICLR 2024Learning Conditional Invariances through Non-Commutativity
86. ICLR 2024Memory-Assisted Sub-Prototype Mining for Universal Domain Adaptation
87. ICLR 2024Minimum width for universal approximation using ReLU networks on compact domain
88. ICLR 2024OpenTab: Advancing Large Language Models as Open-domain Table Reasoners
89. ICLR 2024Principled Federated Domain Adaptation: Gradient Projection and Auto-Weighting
90. ICLR 2024PROGRAM: PROtotype GRAph Model based Pseudo-Label Learning for Test-Time Adaptation
91. ICLR 2024ReTaSA: A Nonparametric Functional Estimation Approach for Addressing Continuous Target Shift
92. ICLR 2024Rethinking CNN’s Generalization to Backdoor Attack from Frequency Domain
93. ICLR 2024Robust agents learn causal world models
94. ICLR 2024SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data Augmentation
95. ICLR 2024Source-Free and Image-Only Unsupervised Domain Adaptation for Category Level Object Pose Estimation
96. ICLR 2024SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs
97. ICLR 2024Towards Cross Domain Generalization of Hamiltonian Representation via Meta Learning
98. ICLR 2024Towards Identifiable Unsupervised Domain Translation: A Diversified Distribution Matching Approach
99. ICLR 2024Un-Mixing Test-Time Normalization Statistics: Combatting Label Temporal Correlation
100. ICLR 2024Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translation

常见问题

2023–2026 年四大会议一共有多少篇域适应论文？

共 866 篇，按年份分别是 2023 年 174 篇、2024 年 209 篇、2025 年 220 篇、2026 年 263 篇。

NeurIPS 2026 有多少篇域适应论文？

NeurIPS 2026 有 78 篇域适应论文，上一届是 81 篇。

ICLR 2026 有多少篇域适应论文？

ICLR 2026 有 46 篇域适应论文，上一届是 45 篇。

ICML 2026 有多少篇域适应论文？

ICML 2026 有 69 篇域适应论文，上一届是 48 篇。

CVPR 2026 有多少篇域适应论文？

CVPR 2026 有 70 篇域适应论文，上一届是 46 篇。

哪个会议的域适应论文最多？

CVPR，2023–2026 年共 268 篇。