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.
RemoteCLIP: A Vision Language Foundation Model for Remote Sensing
FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation
Developing Effective Educational Chatbots with ChatGPT prompts: Insights from Preliminary Tests in a Case Study on Social Media Literacy (with appendix)
Enlighten Anything: When Segment Anything Model Meets Low-Light Image Enhancement
Propagating Knowledge Updates to LMs Through Distillation
Seeing the Pose in the Pixels: Learning Pose-Aware Representations in Vision Transformers
R2-Diff: Denoising by diffusion as a refinement of retrieved motion for image-based motion prediction
Assessing the Effectiveness of GPT-3 in Detecting False Political Statements: A Case Study on the LIAR Dataset
Recognizing Unseen Objects via Multimodal Intensive Knowledge Graph Propagation
A Survey on Video Moment Localization
Action Recognition with Multi-stream Motion Modeling and Mutual Information Maximization
Improving Zero-Shot Detection of Low Prevalence Chest Pathologies using Domain Pre-trained Language Models
Pose-aware Attention Network for Flexible Motion Retargeting by Body Part
Evolving Semantic Prototype Improves Generative Zero-Shot Learning
A Brief Review of Hypernetworks in Deep Learning
LUT-GCE: Lookup Table Global Curve Estimation for Fast Low-light Image Enhancement
How Object Information Improves Skeleton-based Human Action Recognition in Assembly Tasks
Multi-level Protein Representation Learning for Blind Mutational Effect Prediction
Human Action Recognition in Egocentric Perspective Using 2D Object and Hands Pose
Analysis of the Fed's communication by using textual entailment model of Zero-Shot classification
PGformer: Proxy-Bridged Game Transformer for Multi-Person Highly Interactive Extreme Motion Prediction
MotionTrack: Learning Motion Predictor for Multiple Object Tracking
MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusion
Long-Range Feedback Spiking Network Captures Dynamic and Static Representations of the Visual Cortex under Movie Stimuli
On Knowledge Editing in Federated Learning: Perspectives, Challenges, and Future Directions
Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuning
PAGAR: Taming Reward Misalignment in Inverse Reinforcement Learning-Based Imitation Learning with Protagonist Antagonist Guided Adversarial Reward
Recent Advances of Local Mechanisms in Computer Vision: A Survey and Outlook of Recent Work
Layout and Task Aware Instruction Prompt for Zero-shot Document Image Question Answering
FaceDNeRF: Semantics-Driven Face Reconstruction, Prompt Editing and Relighting with Diffusion Models
UCAS-IIE-NLP at SemEval-2023 Task 12: Enhancing Generalization of Multilingual BERT for Low-resource Sentiment Analysis
SAM-helps-Shadow:When Segment Anything Model meet shadow removal
Label Embedding via Low-Coherence Matrices
Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning
fpgaHART: A toolflow for throughput-oriented acceleration of 3D CNNs for HAR onto FPGAs
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.