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.
SkeleTR: Towrads Skeleton-based Action Recognition in the Wild
DreamLLM: Synergistic Multimodal Comprehension and Creation
Auto-ACD: A Large-scale Dataset for Audio-Language Representation Learning
Revisiting Kernel Temporal Segmentation as an Adaptive Tokenizer for Long-form Video Understanding
PolicyGPT: Automated Analysis of Privacy Policies with Large Language Models
Harnessing the Zero-Shot Power of Instruction-Tuned Large Language Model in End-to-End Speech Recognition
A Novel Deep Neural Network for Trajectory Prediction in Automated Vehicles Using Velocity Vector Field
Selective Volume Mixup for Video Action Recognition
Fabricator: An Open Source Toolkit for Generating Labeled Training Data with Teacher LLMs
Multi-Semantic Fusion Model for Generalized Zero-Shot Skeleton-Based Action Recognition
A Discussion on Generalization in Next-Activity Prediction
Cross-Lingual Knowledge Editing in Large Language Models
RMP: A Random Mask Pretrain Framework for Motion Prediction
Sub-action Prototype Learning for Point-level Weakly-supervised Temporal Action Localization
hear-your-action: human action recognition by ultrasound active sensing
Using Large Language Model to Solve and Explain Physics Word Problems Approaching Human Level
Exploring Meta Information for Audio-based Zero-shot Bird Classification
Sparse Autoencoders Find Highly Interpretable Features in Language Models
TAP: Targeted Prompting for Task Adaptive Generation of Textual Training Instances for Visual Classification
TransNet: A Transfer Learning-Based Network for Human Action Recognition
Instance Adaptive Prototypical Contrastive Embedding for Generalized Zero Shot Learning
Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Prompting
Large Language Models Can Infer Psychological Dispositions of Social Media Users
Enhancing Representation in Radiography-Reports Foundation Model: A Granular Alignment Algorithm Using Masked Contrastive Learning
Zero-Shot Visual Classification with Guided Cropping
SAF: Smart Aggregation Framework for Revealing Atoms Importance Rank and Improving Prediction Rates in Drug Discovery
ImitationNet: Unsupervised Human-to-Robot Motion Retargeting via Shared Latent Space
Zero-shot Learning with Minimum Instruction to Extract Social Determinants and Family History from Clinical Notes using GPT Model
Temporal Action Localization with Enhanced Instant Discriminability
SCD-Net: Spatiotemporal Clues Disentanglement Network for Self-supervised Skeleton-based Action Recognition
Mitigating Word Bias in Zero-shot Prompt-based Classifiers
Unified Contrastive Fusion Transformer for Multimodal Human Action Recognition
Context-Aware Prompt Tuning for Vision-Language Model with Dual-Alignment
CDFSL-V: Cross-Domain Few-Shot Learning for Videos
Efficient Baselines for Motion Prediction in Autonomous Driving
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.