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.
Joint 3D Point Cloud Segmentation using Real-Sim Loop: From Panels to Trees and Branches
Understanding the Limits of Lifelong Knowledge Editing in LLMs
Safe LLM-Controlled Robots with Formal Guarantees via Reachability Analysis
Semi-Supervised Audio-Visual Video Action Recognition with Audio Source Localization Guided Mixup
Controllable Motion Generation via Diffusion Modal Coupling
ZAPBench: A Benchmark for Whole-Brain Activity Prediction in Zebrafish
MindBridge: Scalable and Cross-Model Knowledge Editing via Memory-Augmented Modality
Precise Localization of Memories: A Fine-grained Neuron-level Knowledge Editing Technique for LLMs
A Zero-Shot Learning Approach for Ephemeral Gully Detection from Remote Sensing using Vision Language Models
OFF-CLIP: Improving Normal Detection Confidence in Radiology CLIP with Simple Off-Diagonal Term Auto-Adjustment
Unmasking Digital Falsehoods: A Comparative Analysis of LLM-Based Misinformation Detection Strategies
A Simple and Efficient Baseline for Video Action Recognition
An Efficient and Uncertainty-aware Reinforcement Learning Framework for Quality Assurance in Extrusion Additive Manufacturing
Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning
CRUPL: A Semi-Supervised Cyber Attack Detection with Consistency Regularization and Uncertainty-aware Pseudo-Labeling in Smart Grid
Asynchronous Personalized Federated Learning through Global Memorization
Retrieval Backward Attention without Additional Training: Enhance Embeddings of Large Language Models via Repetition
BST: Badminton Stroke-type Transformer for Skeleton-based Action Recognition in Racket Sports
SuPreME: A Supervised Pre-training Framework for Multimodal ECG Representation Learning
Analyzing CLIP's Performance Limitations in Multi-Object Scenarios: A Controlled High-Resolution Study
CLIP Under the Microscope: A Fine-Grained Analysis of Multi-Object Representation
MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge
GeoEdit: Geometric Knowledge Editing for Large Language Models
Visual Adaptive Prompting for Compositional Zero-Shot Learning
Forecasting Whole-Brain Neuronal Activity from Volumetric Video
A Causal Lens for Evaluating Faithfulness Metrics
A Survey on Foundation-Model-Based Industrial Defect Detection
UniGS: Unified Language-Image-3D Pretraining with Gaussian Splatting
Knowledge-enhanced Multimodal ECG Representation Learning with Arbitrary-Lead Inputs
Progressive Local Alignment for Medical Multimodal Pre-training
CLIPure: Purification in Latent Space via CLIP for Adversarially Robust Zero-Shot Classification
Interpretable Data-Driven Ship Dynamics Model: Enhancing Physics-Based Motion Prediction with Parameter Optimization
HVIS: A Human-like Vision and Inference System for Human Motion Prediction
Audio-FLAN: A Preliminary Release
Anatomical grounding pre-training for medical phrase grounding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.