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.
Model Editing by Standard Fine-Tuning
The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse
BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains
Advancing Human Action Recognition with Foundation Models trained on Unlabeled Public Videos
Long-form evaluation of model editing
Intriguing Differences Between Zero-Shot and Systematic Evaluations of Vision-Language Transformer Models
Knowledge Editing on Black-box Large Language Models
Rethinking Machine Unlearning for Large Language Models
Exploring Saliency Bias in Manipulation Detection
VisLingInstruct: Elevating Zero-Shot Learning in Multi-Modal Language Models with Autonomous Instruction Optimization
An Empirical Study Into What Matters for Calibrating Vision-Language Models
SemTra: A Semantic Skill Translator for Cross-Domain Zero-Shot Policy Adaptation
IR-Aware ECO Timing Optimization Using Reinforcement Learning
Model Editing with Canonical Examples
Enhancing Zero-shot Counting via Language-guided Exemplar Learning
On the Robustness of Editing Large Language Models
MEMORYLLM: Towards Self-Updatable Large Language Models
Boosting Adversarial Transferability across Model Genus by Deformation-Constrained Warping
Parameter-tuning-free data entry error unlearning with adaptive selective synaptic dampening
Taylor Videos for Action Recognition
SIMPL: A Simple and Efficient Multi-agent Motion Prediction Baseline for Autonomous Driving
Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes
Deep Semantic-Visual Alignment for Zero-Shot Remote Sensing Image Scene Classification
Zero-shot sketch-based remote sensing image retrieval based on multi-level and attention-guided tokenization
Data-Driven Prediction of Seismic Intensity Distributions Featuring Hybrid Classification-Regression Models
Wavelet-Decoupling Contrastive Enhancement Network for Fine-Grained Skeleton-Based Action Recognition
SynthDST: Synthetic Data is All You Need for Few-Shot Dialog State Tracking
Direct side information learning for zero-shot regression
AutoGCN -- Towards Generic Human Activity Recognition with Neural Architecture Search
Continual Learning for Large Language Models: A Survey
MEIA: Multimodal Embodied Perception and Interaction in Unknown Environments
Propagation and Pitfalls: Reasoning-based Assessment of Knowledge Editing through Counterfactual Tasks
Neighboring Perturbations of Knowledge Editing on Large Language Models
Fine-Grained Zero-Shot Learning: Advances, Challenges, and Prospects
SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.