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.
Weakly-Supervised Action Localization by Hierarchically-structured Latent Attention Modeling
Eva-KELLM: A New Benchmark for Evaluating Knowledge Editing of LLMs
DiffDis: Empowering Generative Diffusion Model with Cross-Modal Discrimination Capability
BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine
PMET: Precise Model Editing in a Transformer
Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction
Action Class Relation Detection and Classification Across Multiple Video Datasets
Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognition
CASPNet++: Joint Multi-Agent Motion Prediction
Leveraging Codebook Knowledge with NLI and ChatGPT for Zero-Shot Political Relation Classification
Masked Motion Predictors are Strong 3D Action Representation Learners
FOLT: Fast Multiple Object Tracking from UAV-captured Videos Based on Optical Flow
UniWorld: Autonomous Driving Pre-training via World Models
EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models
Semantics2Hands: Transferring Hand Motion Semantics between Avatars
Compositional Learning in Transformer-Based Human-Object Interaction Detection
Versatile Face Animator: Driving Arbitrary 3D Facial Avatar in RGBD Space
TrainFors: A Large Benchmark Training Dataset for Image Manipulation Detection and Localization
Robustifying Point Cloud Networks by Refocusing
Exploring Linguistic Similarity and Zero-Shot Learning for Multilingual Translation of Dravidian Languages
Breaking Language Barriers with MMTweets: Advancing Cross-Lingual Debunked Narrative Retrieval for Fact-Checking
Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed Gradient
Leverage Weakly Annotation to Pixel-wise Annotation via Zero-shot Segment Anything Model for Molecular-empowered Learning
Joint-Relation Transformer for Multi-Person Motion Prediction
JEDI: Joint Expert Distillation in a Semi-Supervised Multi-Dataset Student-Teacher Scenario for Video Action Recognition
Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning
Vehicle Motion Forecasting using Prior Information and Semantic-assisted Occupancy Grid Maps
Facial Prior Based First Order Motion Model for Micro-expression Generation
ViLP: Knowledge Exploration using Vision, Language, and Pose Embeddings for Video Action Recognition
Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization
SURE-Val: Safe Urban Relevance Extension and Validation
ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain Adaptation
Supply chain emission estimation using large language models
Push the Boundary of SAM: A Pseudo-label Correction Framework for Medical Segmentation
TS-RGBD Dataset: a Novel Dataset for Theatre Scenes Description for People with Visual Impairments
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.