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 2 / 4 页

51. CVPR 2025ADD: Attribution-Driven Data Augmentation Framework for Boosting Image Super-Resolution
52. CVPR 2025BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis
53. CVPR 2025CADRef: Robust Out-of-Distribution Detection via Class-Aware Decoupled Relative Feature Leveraging
54. CVPR 2025CocoER: Aligning Multi-Level Feature by Competition and Coordination for Emotion Recognition
55. CVPR 2025CoMatcher: Multi-View Collaborative Feature Matching
56. CVPR 2025Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Space
57. CVPR 2025Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers
58. CVPR 2025Descriptor-In-Pixel : Point-Feature Tracking For Pixel Processor Arrays
59. CVPR 2025Deterministic-to-Stochastic Diverse Latent Feature Mapping for Human Motion Synthesis
60. CVPR 2025DFM: Differentiable Feature Matching for Anomaly Detection
61. CVPR 2025DiffCAM: Data-Driven Saliency Maps by Capturing Feature Differences
62. CVPR 2025EDM: Equirectangular Projection-Oriented Dense Kernelized Feature Matching
63. CVPR 2025Efficient Decoupled Feature 3D Gaussian Splatting via Hierarchical Compression
64. CVPR 2025Exploring Semantic Feature Discrimination for Perceptual Image Super-Resolution and Opinion-Unaware No-Reference Image Quality Assessment
65. CVPR 2025Feature Selection for Latent Factor Models
66. CVPR 2025Feature Spectrum Learning for Remote Sensing Change Detection
67. CVPR 2025Feature-Preserving Mesh Decimation for Normal Integration
68. CVPR 2025FFR: Frequency Feature Rectification for Weakly Supervised Semantic Segmentation
69. CVPR 2025FG^2: Fine-Grained Cross-View Localization by Fine-Grained Feature Matching
70. CVPR 2025FLAVC: Learned Video Compression with Feature Level Attention
71. CVPR 2025From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization
72. CVPR 2025g3D-LF: Generalizable 3D-Language Feature Fields for Embodied Tasks
73. CVPR 2025Improving Semi-Supervised Semantic Segmentation with Sliced-Wasserstein Feature Alignment and Uniformity
74. CVPR 2025JamMa: Ultra-lightweight Local Feature Matching with Joint Mamba
75. CVPR 2025Multi-Layer Visual Feature Fusion in Multimodal LLMs: Methods, Analysis, and Best Practices
76. CVPR 2025One is Plenty: A Polymorphic Feature Interpreter for Immutable Heterogeneous Collaborative Perception
77. CVPR 2025Open Ad-hoc Categorization with Contextualized Feature Learning
78. CVPR 2025PillarHist: A Quantization-aware Pillar Feature Encoder based on Height-aware Histogram
79. CVPR 2025PRaDA: Projective Radial Distortion Averaging
80. CVPR 2025Pseudo Visible Feature Fine-Grained Fusion for Thermal Object Detection
81. CVPR 2025RDD: Robust Feature Detector and Descriptor using Deformable Transformer
82. CVPR 2025Recurrent Feature Mining and Keypoint Mixup Padding for Category-Agnostic Pose Estimation
83. CVPR 2025Robust-MVTON: Learning Cross-Pose Feature Alignment and Fusion for Robust Multi-View Virtual Try-On
84. CVPR 2025SASep: Saliency-Aware Structured Separation of Geometry and Feature for Open Set Learning on Point Clouds
85. CVPR 2025SLVR: Super-Light Visual Reconstruction via Blueprint Controllable Convolutions and Exploring Feature Diversity Representation
86. CVPR 2025Stacking Brick by Brick: Aligned Feature Isolation for Incremental Face Forgery Detection
87. CVPR 2025Task-Agnostic Guided Feature Expansion for Class-Incremental Learning
88. CVPR 2025Task-aware Cross-modal Feature Refinement Transformer with Large Language Models for Visual Grounding
89. CVPR 2025UniNet: A Contrastive Learning-guided Unified Framework with Feature Selection for Anomaly Detection
90. CVPR 20243D Feature Tracking via Event Camera
91. CVPR 2024A Stealthy Wrongdoer: Feature-Oriented Reconstruction Attack against Split Learning
92. CVPR 2024Adaptive Random Feature Regularization on Fine-tuning Deep Neural Networks
93. CVPR 2024AdaShift: Learning Discriminative Self-Gated Neural Feature Activation With an Adaptive Shift Factor
94. CVPR 2024Adversarial Distillation Based on Slack Matching and Attribution Region Alignment
95. CVPR 2024Collaborative Semantic Occupancy Prediction with Hybrid Feature Fusion in Connected Automated Vehicles
96. CVPR 2024DYSON: Dynamic Feature Space Self-Organization for Online Task-Free Class Incremental Learning
97. CVPR 2024Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed
98. CVPR 2024Exploiting Inter-sample and Inter-feature Relations in Dataset Distillation
99. CVPR 2024FCS: Feature Calibration and Separation for Non-Exemplar Class Incremental Learning
100. CVPR 2024Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields

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。