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.
Human Motion Prediction, Reconstruction, and Generation
Edit Once, Update Everywhere: A Simple Framework for Cross-Lingual Knowledge Synchronization in LLMs
Entity Framing and Role Portrayal in the News
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
Revealing and Mitigating Over-Attention in Knowledge Editing
Using tournaments to calculate AUROC for zero-shot classification with LLMs
CoME: An Unlearning-based Approach to Conflict-free Model Editing
SNN-Driven Multimodal Human Action Recognition via Event Camera and Skeleton Data Fusion
MaizeEar-SAM: Zero-Shot Maize Ear Phenotyping
Enhancing Chest X-ray Classification through Knowledge Injection in Cross-Modality Learning
A Survey of Text Classification Under Class Distribution Shift
Gesture-Aware Zero-Shot Speech Recognition for Patients with Language Disorders
DELMAN: Dynamic Defense Against Large Language Model Jailbreaking with Model Editing
Personality Editing for Language Models through Relevant Knowledge Editing
Text Classification in the LLM Era - Where do we stand?
The Mirage of Model Editing: Revisiting Evaluation in the Wild
K-Edit: Language Model Editing with Contextual Knowledge Awareness
Semantics-aware Test-time Adaptation for 3D Human Pose Estimation
E2CB2former: Effecitve and Explainable Transformer for CB2 Receptor Ligand Activity Prediction
An Innovative Next Activity Prediction Approach Using Process Entropy and DAW-Transformer
Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion Model
Optimizing GPT for Video Understanding: Zero-Shot Performance and Prompt Engineering
Not All Frame Features Are Equal: Video-to-4D Generation via Decoupling Dynamic-Static Features
From Haystack to Needle: Label Space Reduction for Zero-shot Classification
MEMIT-Merge: Addressing MEMIT's Key-Value Conflicts in Same-Subject Batch Editing for LLMs
Captured by Captions: On Memorization and its Mitigation in CLIP Models
Learning Clustering-based Prototypes for Compositional Zero-shot Learning
Reinforced Lifelong Editing for Language Models
HyLiFormer: Hyperbolic Linear Attention for Skeleton-based Human Action Recognition
Injecting Universal Jailbreak Backdoors into LLMs in Minutes
AnyEdit: Edit Any Knowledge Encoded in Language Models
Related Knowledge Perturbation Matters: Rethinking Multiple Pieces of Knowledge Editing in Same-Subject
Cross-Encoder Rediscovers a Semantic Variant of BM25
DCFormer: Efficient 3D Vision-Language Modeling with Decomposed Convolutions
LR0.FM: Low-Res Benchmark and Improving Robustness for Zero-Shot Classification in Foundation Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.