深度学习 · self supervised learning论文趋势 2023–2026

主要结论

• 深度学习 · self supervised learning论文从 2023 年的 455 篇增长到 2026 年的 534 篇，三年间扩大到约 1.2 倍。
• ICLR 是发深度学习 · self supervised learning论文最多的会议，2023–2026 年共 693 篇，占四个会议总量的 35%。
• 交叉方向里涨得最快的是通用机器学习 · unsupervised and semisupervised learning：同时属于两个主题的论文从 2023 年的 23 篇增至 2026 年的 86 篇。
• 在「深度学习」的 11 个主题里，它的 2026 年论文数排第 4；同组增长最快的扩散模型是 4.1 倍，深度学习 · self supervised learning是 1.2 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 2026Attending on Attention ($A^2$): Smaller Self-Supervised ViTs Localize Better Than Larger Ones
• ICML 20263D-DLP: Self-supervised 3D Object-centric Scene Representation Learning
• ICLR 2026A Single Architecture for Representing Invariance Under Any Space Group
• CVPR 2026A Stitch in Time Learning Procedural Workflow via Self-Supervised Plackett-Luce
• NeurIPS 2025$\textit{HiMaCon:}$ Discovering Hierarchical Manipulation Concepts from Unlabeled Multi-Modal Data
• ICML 2025An Augmentation-Aware Theory for Self-Supervised Contrastive Learning
• ICLR 2025Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding
• CVPR 2025A Unified Framework for Heterogeneous Semi-supervised Learning
• NeurIPS 2024Intrinsic Self-Supervision for Data Quality Audits
• ICML 2024Binning as a Pretext Task: Improving Self-Supervised Learning in Tabular Domains
• ICLR 2024A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks
• CVPR 2024Exploring Efficient Asymmetric Blind-Spots for Self-Supervised Denoising in Real-World Scenarios
• NeurIPS 2023A Graph-Theoretic Framework for Understanding Open-World Semi-Supervised Learning
• ICML 2023A Closer Look at Self-Supervised Lightweight Vision Transformers
• ICLR 2023A Multi-Grained Self-Interpretable Symbolic-Neural Model For Single/Multi-Labeled Text Classification
• CVPR 2023Are Data-Driven Explanations Robust Against Out-of-Distribution Data?
• NeurIPS 2026AudioSphere: Towards Self-Supervised Spatial Audio Representation Models
• ICML 20263DPoV: Improving 3D understanding via Patch Ordering on Videos
• ICLR 2026Angle K-Means
• CVPR 2026Action Motifs Self-Supervised Hierarchical Representation of Human Body Movements

全部深度学习 · self supervised learning论文

共 472 篇，第 3 / 10 页

101. CVPR 2024VSRD: Instance-Aware Volumetric Silhouette Rendering for Weakly Supervised 3D Object Detection
102. CVPR 2024Weakly Supervised Monocular 3D Detection with a Single-View Image
103. CVPR 2024Weakly Supervised Point Cloud Semantic Segmentation via Artificial Oracle
104. CVPR 2024Weakly Supervised Video Individual Counting
105. CVPR 2024What When and Where? Self-Supervised Spatio-Temporal Grounding in Untrimmed Multi-Action Videos from Narrated Instructions
106. ICLR 20243D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining
107. ICLR 2024A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks
108. ICLR 2024A Mutual Information Perspective on Federated Contrastive Learning
109. ICLR 2024A Recipe for Improved Certifiable Robustness
110. ICLR 2024A representation-learning game for classes of prediction tasks
111. ICLR 2024Accelerated Sampling with Stacked Restricted Boltzmann Machines
112. ICLR 2024An Investigation of Representation and Allocation Harms in Contrastive Learning
113. ICLR 2024Annealing Self-Distillation Rectification Improves Adversarial Training
114. ICLR 2024Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?
115. ICLR 2024Attention-based Iterative Decomposition for Tensor Product Representation
116. ICLR 2024AUC-CL: A Batchsize-Robust Framework for Self-Supervised Contrastive Representation Learning
117. ICLR 2024Batch normalization is sufficient for universal function approximation in CNNs
118. ICLR 2024BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation
119. ICLR 2024Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain
120. ICLR 2024Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness
121. ICLR 2024Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environments
122. ICLR 2024Bridging State and History Representations: Understanding Self-Predictive RL
123. ICLR 2024CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perception
124. ICLR 2024Candidate Label Set Pruning: A Data-centric Perspective for Deep Partial-label Learning
125. ICLR 2024CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting
126. ICLR 2024Cauchy-Schwarz Divergence Information Bottleneck for Regression
127. ICLR 2024Certified Adversarial Robustness for Rate Encoded Spiking Neural Networks
128. ICLR 2024CODE REPRESENTATION LEARNING AT SCALE
129. ICLR 2024Compressing Latent Space via Least Volume
130. ICLR 2024ConR: Contrastive Regularizer for Deep Imbalanced Regression
131. ICLR 2024Consistent Multi-Class Classification from Multiple Unlabeled Datasets
132. ICLR 2024Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation
133. ICLR 2024Contrastive Learning is Spectral Clustering on Similarity Graph
134. ICLR 2024CrIBo: Self-Supervised Learning via Cross-Image Object-Level Bootstrapping
135. ICLR 2024DAFA: Distance-Aware Fair Adversarial Training
136. ICLR 2024Deep Geodesic Canonical Correlation Analysis for Covariance-Based Neuroimaging Data
137. ICLR 2024Deep Orthogonal Hypersphere Compression for Anomaly Detection
138. ICLR 2024Deep Temporal Graph Clustering
139. ICLR 2024Dictionary Contrastive Learning for Efficient Local Supervision without Auxiliary Networks
140. ICLR 2024Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learning
141. ICLR 2024Distinguished In Uniform: Self-Attention Vs. Virtual Nodes
142. ICLR 2024Diving Segmentation Model into Pixels
143. ICLR 2024Do Generated Data Always Help Contrastive Learning?
144. ICLR 2024Does CLIP’s generalization performance mainly stem from high train-test similarity?
145. ICLR 2024Dual-Encoders for Extreme Multi-label Classification
146. ICLR 2024Early Stopping Against Label Noise Without Validation Data
147. ICLR 2024Effective pruning of web-scale datasets based on complexity of concept clusters
148. ICLR 2024Efficient Score Matching with Deep Equilibrium Layers
149. ICLR 2024Enabling Lanuguage Models to Implicitly Learn Self-Improvement
150. ICLR 2024Enhancing Tail Performance in Extreme Classifiers by Label Variance Reduction

常见问题

2023–2026 年四大会议一共有多少篇深度学习 · self supervised learning论文？

共 1,958 篇，按年份分别是 2023 年 455 篇、2024 年 472 篇、2025 年 497 篇、2026 年 534 篇。

NeurIPS 2026 有多少篇深度学习 · self supervised learning论文？

NeurIPS 2026 有 110 篇深度学习 · self supervised learning论文，上一届是 147 篇。

ICLR 2026 有多少篇深度学习 · self supervised learning论文？

ICLR 2026 有 195 篇深度学习 · self supervised learning论文，上一届是 195 篇。

ICML 2026 有多少篇深度学习 · self supervised learning论文？

ICML 2026 有 135 篇深度学习 · self supervised learning论文，上一届是 72 篇。

CVPR 2026 有多少篇深度学习 · self supervised learning论文？

CVPR 2026 有 94 篇深度学习 · self supervised learning论文，上一届是 83 篇。

哪个会议的深度学习 · self supervised learning论文最多？

ICLR，2023–2026 年共 693 篇。