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.
Sequential Editing for Lifelong Training of Speech Recognition Models
Multilingual Knowledge Editing with Language-Agnostic Factual Neurons
GIM: A Million-scale Benchmark for Generative Image Manipulation Detection and Localization
Evaluation of Language Models in the Medical Context Under Resource-Constrained Settings
At First Sight: Zero-Shot Classification of Astronomical Images with Large Multimodal Models
neuROSym: Deployment and Evaluation of a ROS-based Neuro-Symbolic Model for Human Motion Prediction
Serial Position Effects of Large Language Models
A Simple Framework for Open-Vocabulary Zero-Shot Segmentation
Review of Zero-Shot and Few-Shot AI Algorithms in The Medical Domain
CLIP-Decoder : ZeroShot Multilabel Classification using Multimodal CLIP Aligned Representation
Contextual Interaction via Primitive-based Adversarial Training For Compositional Zero-shot Learning
Real-Time Hand Gesture Recognition: Integrating Skeleton-Based Data Fusion and Multi-Stream CNN
SVFormer: A Direct Training Spiking Transformer for Efficient Video Action Recognition
Open-Vocabulary Temporal Action Localization using Multimodal Guidance
A Data-Driven Guided Decoding Mechanism for Diagnostic Captioning
FutureNet-LOF: Joint Trajectory Prediction and Lane Occupancy Field Prediction with Future Context Encoding
Factual Dialogue Summarization via Learning from Large Language Models
MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality Consistency
Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition
Using Multimodal Large Language Models for Automated Detection of Traffic Safety Critical Events
Retrieval Meets Reasoning: Dynamic In-Context Editing for Long-Text Understanding
Adaptive Token Biaser: Knowledge Editing via Biasing Key Entities
FuseGen: PLM Fusion for Data-generation based Zero-shot Learning
Stealth edits to large language models
BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversity
MAC: A Benchmark for Multiple Attributes Compositional Zero-Shot Learning
Unsupervised explainable activity prediction in competitive Nordic Walking from experimental data
Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance
In-Context Editing: Learning Knowledge from Self-Induced Distributions
Understanding the Collapse of LLMs in Model Editing
Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments
BAMBINO-LM: (Bilingual-)Human-Inspired Continual Pretraining of BabyLM
MEMLA: Enhancing Multilingual Knowledge Editing with Neuron-Masked Low-Rank Adaptation
RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuning
Identifying Query-Relevant Neurons in Large Language Models for Long-Form Texts
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.