特征归因论文趋势 2023–2026

主要结论

• 特征归因论文从 2023 年的 118 篇增长到 2026 年的 219 篇，三年间扩大到约 1.9 倍。
• NeurIPS 是发特征归因论文最多的会议，2023–2026 年共 193 篇，占四个会议总量的 28%。
• 交叉方向里涨得最快的是理论 · learning theory：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 14 篇。
• 在「可解释性」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的机制解释是 8.1 倍，特征归因是 1.9 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 2026ADAPT: Hybrid Prompt Optimization for LLM Feature Visualization
• ICML 2026Activation with Intrinsic-Extrinsic Consensus
• ICLR 2026AnyUp: Universal Feature Upsampling
• CVPR 2026A Training-Free Style-Personalization via SVD-Based Feature Decomposition
• NeurIPS 2025Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks
• ICML 2025BCE vs. CE in Deep Feature Learning
• ICLR 2025A Differentiable Rank-Based Objective for Better Feature Learning
• CVPR 2025A Simple Data Augmentation for Feature Distribution Skewed Federated Learning
• NeurIPS 2024$\texttt{dattri}$: A Library for Efficient Data Attribution
• ICML 2024Asymptotics of feature learning in two-layer networks after one gradient-step
• ICLR 2024An Intuitive Multi-Frequency Feature Representation for SO(3)-Equivariant Networks
• CVPR 2024DYSON: Dynamic Feature Space Self-Organization for Online Task-Free Class Incremental Learning
• NeurIPS 2023$\mathcal{M}^4$: A Unified XAI Benchmark for Faithfulness Evaluation of Feature Attribution Methods across Metrics, Modalities and Models
• ICML 2023Decoding Layer Saliency in Language Transformers
• ICLR 2023Can We Faithfully Represent Absence States to Compute Shapley Values on a DNN?
• CVPR 2023A Practical Upper Bound for the Worst-Case Attribution Deviations
• NeurIPS 2026Adaptive Feature Propagation for Attribute-Missing Graph Clustering
• ICML 2026Aggregate Models, Not Explanations: Improving Feature Importance Estimation
• ICLR 2026Attribution-Guided Decoding
• CVPR 2026FBTA Enabling Single-GPU End-to-End Gigapixel WSI Classification with Feature Bridging

全部特征归因论文

共 167 篇，第 3 / 4 页

101. CVPR 2024Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology
102. CVPR 2024FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurring
103. CVPR 2024From Feature to Gaze: A Generalizable Replacement of Linear Layer for Gaze Estimation
104. CVPR 2024HDQMF: Holographic Feature Decomposition Using Quantum Algorithms
105. CVPR 2024Improving Depth Completion via Depth Feature Upsampling
106. CVPR 2024LLaMA-Excitor: General Instruction Tuning via Indirect Feature Interaction
107. CVPR 2024Mean-Shift Feature Transformer
108. CVPR 2024NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation
109. CVPR 2024Neural Refinement for Absolute Pose Regression with Feature Synthesis
110. CVPR 2024Neural Video Compression with Feature Modulation
111. CVPR 2024OmniGlue: Generalizable Feature Matching with Foundation Model Guidance
112. CVPR 2024One-Class Face Anti-spoofing via Spoof Cue Map-Guided Feature Learning
113. CVPR 2024Physical Property Understanding from Language-Embedded Feature Fields
114. CVPR 2024Privacy-Preserving Face Recognition Using Trainable Feature Subtraction
115. CVPR 2024Puff-Net: Efficient Style Transfer with Pure Content and Style Feature Fusion Network
116. CVPR 2024Revisiting Global Translation Estimation with Feature Tracks
117. CVPR 2024RoMa: Robust Dense Feature Matching
118. CVPR 2024SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimation
119. CVPR 2024SHAP-EDITOR: Instruction-Guided Latent 3D Editing in Seconds
120. CVPR 2024TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models
121. CVPR 2024Towards the Uncharted: Density-Descending Feature Perturbation for Semi-supervised Semantic Segmentation
122. CVPR 2024Unsupervised Feature Learning with Emergent Data-Driven Prototypicality
123. CVPR 2024VideoRF: Rendering Dynamic Radiance Fields as 2D Feature Video Streams
124. CVPR 2024VRetouchEr: Learning Cross-frame Feature Interdependence with Imperfection Flow for Face Retouching in Videos
125. CVPR 2023A Practical Upper Bound for the Worst-Case Attribution Deviations
126. CVPR 2023Adaptive Assignment for Geometry Aware Local Feature Matching
127. CVPR 2023Adaptive Spot-Guided Transformer for Consistent Local Feature Matching
128. CVPR 2023AdaptiveMix: Improving GAN Training via Feature Space Shrinkage
129. CVPR 2023AGAIN: Adversarial Training With Attribution Span Enlargement and Hybrid Feature Fusion
130. CVPR 2023Block Selection Method for Using Feature Norm in Out-of-Distribution Detection
131. CVPR 2023CafeBoost: Causal Feature Boost To Eliminate Task-Induced Bias for Class Incremental Learning
132. CVPR 2023Camouflaged Object Detection With Feature Decomposition and Edge Reconstruction
133. CVPR 2023Clothing-Change Feature Augmentation for Person Re-Identification
134. CVPR 2023Correspondence Transformers With Asymmetric Feature Learning and Matching Flow Super-Resolution
135. CVPR 2023Curvature-Balanced Feature Manifold Learning for Long-Tailed Classification
136. CVPR 2023Data-Driven Feature Tracking for Event Cameras
137. CVPR 2023Data-Free Knowledge Distillation via Feature Exchange and Activation Region Constraint
138. CVPR 2023Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object Detection
139. CVPR 2023Discriminator-Cooperated Feature Map Distillation for GAN Compression
140. CVPR 2023DKM: Dense Kernelized Feature Matching for Geometry Estimation
141. CVPR 2023Efficient View Synthesis and 3D-Based Multi-Frame Denoising With Multiplane Feature Representations
142. CVPR 2023FAC: 3D Representation Learning via Foreground Aware Feature Contrast
143. CVPR 2023FCC: Feature Clusters Compression for Long-Tailed Visual Recognition
144. CVPR 2023Feature Separation and Recalibration for Adversarial Robustness
145. CVPR 2023Feature Shrinkage Pyramid for Camouflaged Object Detection With Transformers
146. CVPR 2023FeatureBooster: Boosting Feature Descriptors With a Lightweight Neural Network
147. CVPR 2023Fix the Noise: Disentangling Source Feature for Controllable Domain Translation
148. CVPR 2023GCFAgg: Global and Cross-View Feature Aggregation for Multi-View Clustering
149. CVPR 2023Generalizable Local Feature Pre-Training for Deformable Shape Analysis
150. CVPR 2023Gradient-Based Uncertainty Attribution for Explainable Bayesian Deep Learning

常见问题

2023–2026 年四大会议一共有多少篇特征归因论文？

共 695 篇，按年份分别是 2023 年 118 篇、2024 年 168 篇、2025 年 190 篇、2026 年 219 篇。

NeurIPS 2026 有多少篇特征归因论文？

NeurIPS 2026 有 61 篇特征归因论文，上一届是 57 篇。

ICLR 2026 有多少篇特征归因论文？

ICLR 2026 有 53 篇特征归因论文，上一届是 42 篇。

ICML 2026 有多少篇特征归因论文？

ICML 2026 有 56 篇特征归因论文，上一届是 51 篇。

CVPR 2026 有多少篇特征归因论文？

CVPR 2026 有 49 篇特征归因论文，上一届是 40 篇。

哪个会议的特征归因论文最多？

NeurIPS，2023–2026 年共 193 篇。