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.
Understanding prompt engineering may not require rethinking generalization
The WayHome: Long-term Motion Prediction on Dynamically Scaled
Enhanced Human-Robot Collaboration using Constrained Probabilistic Human-Motion Prediction
Investigating the Limitation of CLIP Models: The Worst-Performing Categories
Multi-Resolution Audio-Visual Feature Fusion for Temporal Action Localization
Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks
Zero-shot Learning of Drug Response Prediction for Preclinical Drug Screening
Time-LLM: Time Series Forecasting by Reprogramming Large Language Models
Unveiling the Pitfalls of Knowledge Editing for Large Language Models
Editing Personality for Large Language Models
Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP
DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detection
An easy zero-shot learning combination: Texture Sensitive Semantic Segmentation IceHrNet and Advanced Style Transfer Learning Strategy
Black-box Attacks on Image Activity Prediction and its Natural Language Explanations
Telling Stories for Common Sense Zero-Shot Action Recognition
Improving Trajectory Prediction in Dynamic Multi-Agent Environment by Dropping Waypoints
Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks
One for All: Towards Training One Graph Model for All Classification Tasks
MotionLM: Multi-Agent Motion Forecasting as Language Modeling
Robust Internal Representations for Domain Generalization
MKRAG: Medical Knowledge Retrieval Augmented Generation for Medical Question Answering
Are Human-generated Demonstrations Necessary for In-context Learning?
Semantic Map Learning of Traffic Light to Lane Assignment based on Motion Data
VPA: Fully Test-Time Visual Prompt Adaptation
SEPT: Towards Efficient Scene Representation Learning for Motion Prediction
M$^{3}$3D: Learning 3D priors using Multi-Modal Masked Autoencoders for 2D image and video understanding
Boundary-Aware Proposal Generation Method for Temporal Action Localization
Dual Feature Augmentation Network for Generalized Zero-shot Learning
CLIP-DIY: CLIP Dense Inference Yields Open-Vocabulary Semantic Segmentation For-Free
Rewrite Caption Semantics: Bridging Semantic Gaps for Language-Supervised Semantic Segmentation
DROP: Dynamics Responses from Human Motion Prior and Projective Dynamics
Elevating Skeleton-Based Action Recognition with Efficient Multi-Modality Self-Supervision
Exploring Self-supervised Skeleton-based Action Recognition in Occluded Environments
Survey of Action Recognition, Spotting and Spatio-Temporal Localization in Soccer -- Current Trends and Research Perspectives
Exploiting CLIP-based Multi-modal Approach for Artwork Classification and Retrieval
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.