Zero-Shot Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 7
- 평가표
- 33
- 보존된 평가 기록
- 84
Zero-shot learning (ZSL) is a model's ability to detect classes never seen during training. The condition is that the classes are not known during supervised learning.
Earlier work in zero-shot learning use attributes in a two-step approach to infer unknown classes. In the computer vision context, more recent advances learn mappings from image feature space to semantic space. Other approaches learn non-linear multimodal embeddings. In the modern NLP context, language models can be evaluated on downstream tasks without fine tuning.
Benchmark datasets for zero-shot learning include aPY, AwA, and CUB, among others.
( Image credit: Prototypical Networks for Few shot Learning in PyTorch )
Further readings:
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
On the use of Silver Standard Data for Zero-shot Classification Tasks in Information Extraction
Editing Factual Knowledge and Explanatory Ability of Medical Large Language Models
TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understanding
Merino: Entropy-driven Design for Generative Language Models on IoT Devices
Context-based and Diversity-driven Specificity in Compositional Zero-Shot Learning
CARZero: Cross-Attention Alignment for Radiology Zero-Shot Classification
An Investigation into the Performances of the State-of-the-art Machine Learning Approaches for Various Cyber-attack Detection: A Survey
EEG classifier cross-task transfer to avoid training sessions in robot-assisted rehabilitation
Building Flexible Machine Learning Models for Scientific Computing at Scale
InstructEdit: Instruction-based Knowledge Editing for Large Language Models
An Adversarial Robustness Benchmark for Enterprise Network Intrusion Detection
How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries
Quaternion recurrent neural network with real-time recurrent learning and maximum correntropy criterion
Towards Unified Task Embeddings Across Multiple Models: Bridging the Gap for Prompt-Based Large Language Models and Beyond
Potential and Challenges of Model Editing for Social Debiasing
Knowledge Graph Enhanced Large Language Model Editing
EXACT-Net:EHR-guided lung tumor auto-segmentation for non-small cell lung cancer radiotherapy
Context-based Interpretable Spatio-Temporal Graph Convolutional Network for Human Motion Forecasting
Can GNN be Good Adapter for LLMs?
Stable Knowledge Editing in Large Language Models
Event-level Knowledge Editing
Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language Models
Learning to Edit: Aligning LLMs with Knowledge Editing
Exploring the Limits of Zero Shot Vision Language Models for Hate Meme Detection: The Vulnerabilities and their Interpretations
Empirical Study on Updating Key-Value Memories in Transformer Feed-forward Layers
Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models
Data Distribution Distilled Generative Model for Generalized Zero-Shot Recognition
GenAD: Generative End-to-End Autonomous Driving
MIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editing
ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs
EVEDIT: Event-based Knowledge Editing with Deductive Editing Boundaries
Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)
MFBind: a Multi-Fidelity Approach for Evaluating Drug Compounds in Practical Generative Modeling
Towards Uncovering How Large Language Model Works: An Explainability Perspective
WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.