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 40 篇，第 1 / 1 页

1. CVPR 2025A Simple Data Augmentation for Feature Distribution Skewed Federated Learning
2. CVPR 2025ADD: Attribution-Driven Data Augmentation Framework for Boosting Image Super-Resolution
3. CVPR 2025BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis
4. CVPR 2025CADRef: Robust Out-of-Distribution Detection via Class-Aware Decoupled Relative Feature Leveraging
5. CVPR 2025CocoER: Aligning Multi-Level Feature by Competition and Coordination for Emotion Recognition
6. CVPR 2025CoMatcher: Multi-View Collaborative Feature Matching
7. CVPR 2025Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Space
8. CVPR 2025Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers
9. CVPR 2025Descriptor-In-Pixel : Point-Feature Tracking For Pixel Processor Arrays
10. CVPR 2025Deterministic-to-Stochastic Diverse Latent Feature Mapping for Human Motion Synthesis
11. CVPR 2025DFM: Differentiable Feature Matching for Anomaly Detection
12. CVPR 2025DiffCAM: Data-Driven Saliency Maps by Capturing Feature Differences
13. CVPR 2025EDM: Equirectangular Projection-Oriented Dense Kernelized Feature Matching
14. CVPR 2025Efficient Decoupled Feature 3D Gaussian Splatting via Hierarchical Compression
15. CVPR 2025Exploring Semantic Feature Discrimination for Perceptual Image Super-Resolution and Opinion-Unaware No-Reference Image Quality Assessment
16. CVPR 2025Feature Selection for Latent Factor Models
17. CVPR 2025Feature Spectrum Learning for Remote Sensing Change Detection
18. CVPR 2025Feature-Preserving Mesh Decimation for Normal Integration
19. CVPR 2025FFR: Frequency Feature Rectification for Weakly Supervised Semantic Segmentation
20. CVPR 2025FG^2: Fine-Grained Cross-View Localization by Fine-Grained Feature Matching
21. CVPR 2025FLAVC: Learned Video Compression with Feature Level Attention
22. CVPR 2025From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization
23. CVPR 2025g3D-LF: Generalizable 3D-Language Feature Fields for Embodied Tasks
24. CVPR 2025Improving Semi-Supervised Semantic Segmentation with Sliced-Wasserstein Feature Alignment and Uniformity
25. CVPR 2025JamMa: Ultra-lightweight Local Feature Matching with Joint Mamba
26. CVPR 2025Multi-Layer Visual Feature Fusion in Multimodal LLMs: Methods, Analysis, and Best Practices
27. CVPR 2025One is Plenty: A Polymorphic Feature Interpreter for Immutable Heterogeneous Collaborative Perception
28. CVPR 2025Open Ad-hoc Categorization with Contextualized Feature Learning
29. CVPR 2025PillarHist: A Quantization-aware Pillar Feature Encoder based on Height-aware Histogram
30. CVPR 2025PRaDA: Projective Radial Distortion Averaging
31. CVPR 2025Pseudo Visible Feature Fine-Grained Fusion for Thermal Object Detection
32. CVPR 2025RDD: Robust Feature Detector and Descriptor using Deformable Transformer
33. CVPR 2025Recurrent Feature Mining and Keypoint Mixup Padding for Category-Agnostic Pose Estimation
34. CVPR 2025Robust-MVTON: Learning Cross-Pose Feature Alignment and Fusion for Robust Multi-View Virtual Try-On
35. CVPR 2025SASep: Saliency-Aware Structured Separation of Geometry and Feature for Open Set Learning on Point Clouds
36. CVPR 2025SLVR: Super-Light Visual Reconstruction via Blueprint Controllable Convolutions and Exploring Feature Diversity Representation
37. CVPR 2025Stacking Brick by Brick: Aligned Feature Isolation for Incremental Face Forgery Detection
38. CVPR 2025Task-Agnostic Guided Feature Expansion for Class-Incremental Learning
39. CVPR 2025Task-aware Cross-modal Feature Refinement Transformer with Large Language Models for Visual Grounding
40. CVPR 2025UniNet: A Contrastive Learning-guided Unified Framework with Feature Selection for Anomaly Detection

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。