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.
DIEKAE: Difference Injection for Efficient Knowledge Augmentation and Editing of Large Language Models
Knowledge Editing in Language Models via Adapted Direct Preference Optimization
Zero-Shot Learning Over Large Output Spaces : Utilizing Indirect Knowledge Extraction from Large Language Models
REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space
Exploring the Spectrum of Visio-Linguistic Compositionality and Recognition
RWKV-CLIP: A Robust Vision-Language Representation Learner
D-GRIL: End-to-End Topological Learning with 2-parameter Persistence
Understanding Visual Concepts Across Models
iMotion-LLM: Motion Prediction Instruction Tuning
STAR: Skeleton-aware Text-based 4D Avatar Generation with In-Network Motion Retargeting
SMART: Scene-motion-aware human action recognition framework for mental disorder group
BAMO at SemEval-2024 Task 9: BRAINTEASER: A Novel Task Defying Common Sense
CPLIP: Zero-Shot Learning for Histopathology with Comprehensive Vision-Language Alignment
Understanding Information Storage and Transfer in Multi-modal Large Language Models
Time Sensitive Knowledge Editing through Efficient Finetuning
Outdated Issue Aware Decoding for Reasoning Questions on Edited Knowledge
Exploring Data Efficiency in Zero-Shot Learning with Diffusion Models
Attend and Enrich: Enhanced Visual Prompt for Zero-Shot Learning
CountCLIP -- [Re] Teaching CLIP to Count to Ten
Description Boosting for Zero-Shot Entity and Relation Classification
DL-KDD: Dual-Light Knowledge Distillation for Action Recognition in the Dark
Spatial and social situation-aware transformer-based trajectory prediction of autonomous systems
Editing the Mind of Giants: An In-Depth Exploration of Pitfalls of Knowledge Editing in Large Language Models
SLANT: Spurious Logo ANalysis Toolkit
An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognition
RNNs, CNNs and Transformers in Human Action Recognition: A Survey and a Hybrid Model
DAFNet: Dynamic Auxiliary Fusion for Sequential Model Editing in Large Language Models
Vision-Language Meets the Skeleton: Progressively Distillation with Cross-Modal Knowledge for 3D Action Representation Learning
Skeleton-OOD: An End-to-End Skeleton-Based Model for Robust Out-of-Distribution Human Action Detection
Hard Cases Detection in Motion Prediction by Vision-Language Foundation Models
SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation
Multi-Condition Latent Diffusion Network for Scene-Aware Neural Human Motion Prediction
MEMoE: Enhancing Model Editing with Mixture of Experts Adaptors
Matrix Manifold Neural Networks++
Multi-Modal Generative Embedding Model
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.