Papers with Code 아카이브
Dictionary Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Dictionary Learning is an important problem in multiple areas, ranging from computational neuroscience, machine learning, to computer vision and image processing. The general goal is to find a good basis for given data. More formally, in the Dictionary Learning problem, also known as sparse coding, we are given samples of a random vector $y\in\mathbb{R}^n$, of the form $y=Ax$ where $A$ is some unknown matrix in $\mathbb{R}^{n×m}$, called dictionary, and $x$ is sampled from an unknown distribution over sparse vectors. The goal is to approximately recover the dictionary $A$.
Source: Polynomial-time tensor decompositions with sum-of-squares
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Decomposing MLP Activations into Interpretable Features via Semi-Nonnegative Matrix Factorization
Evaluating Sparse Autoencoders: From Shallow Design to Matching Pursuit
Mechanistic Decomposition of Sentence Representations
HyperSteer: Activation Steering at Scale with Hypernetworks
Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning
Towards Privacy-Preserving Fine-Grained Visual Classification via Hierarchical Learning from Label Proportions
DB-KSVD: Scalable Alternating Optimization for Disentangling High-Dimensional Embedding Spaces
Modeling Musical Genre Trajectories through Pathlet Learning
Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition
From Attention to Atoms: Spectral Dictionary Learning for Fast, Interpretable Language Models
Optimizing Hard Thresholding for Sparse Model Discovery
Unveiling Hidden Collaboration within Mixture-of-Experts in Large Language Models
Recognition of Geometrical Shapes by Dictionary Learning
Mixture-of-Shape-Experts (MoSE): End-to-End Shape Dictionary Framework to Prompt SAM for Generalizable Medical Segmentation
Koopman-Based Methods for EV Climate Dynamics: Comparing eDMD Approaches
Decentralized Federated Dataset Dictionary Learning for Multi-Source Domain Adaptation
Topological Dictionary Learning
Sparse Dictionary Learning for Image Recovery by Iterative Shrinkage
Online multidimensional dictionary learning
Weakly Supervised Convolutional Dictionary Learning for Multi-Label Classification
Personalized Convolutional Dictionary Learning of Physiological Time Series
Dynamic Dictionary Learning for Remote Sensing Image Segmentation
Unraveling the Localized Latents: Learning Stratified Manifold Structures in LLM Embedding Space with Sparse Mixture-of-Experts
Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models
Dictionary-Learning-Based Data Pruning for System Identification
Inversion of Magnetic Data using Learned Dictionaries and Scale Space
Boosting Adversarial Robustness and Generalization with Structural Prior
Exploring the Limitations of Structured Orthogonal Dictionary Learning
Multi-field Visualization: Trait design and trait-induced merge trees
A Zero-Shot Physics-Informed Dictionary Learning Approach for Sound Field Reconstruction
Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models
DNF: Unconditional 4D Generation with Dictionary-based Neural Fields
Monet: Mixture of Monosemantic Experts for Transformers
On the relationship between Koopman operator approximations and neural ordinary differential equations for data-driven time-evolution predictions
Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.