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.
Zero-shot Classification using Hyperdimensional Computing
Active Generation Network of Human Skeleton for Action Recognition
Performance Assessment of ChatGPT vs Bard in Detecting Alzheimer's Dementia
M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining
Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization
FIMP: Future Interaction Modeling for Multi-Agent Motion Prediction
Cutup and Detect: Human Fall Detection on Cutup Untrimmed Videos Using a Large Foundational Video Understanding Model
SNAP: Semantic Stories for Next Activity Prediction
Data-Free Generalized Zero-Shot Learning
A Nonparametric Bayes Approach to Online Activity Prediction
A comparative study of zero-shot inference with large language models and supervised modeling in breast cancer pathology classification
ConstraintChecker: A Plugin for Large Language Models to Reason on Commonsense Knowledge Bases
Unsupervised Spatial-Temporal Feature Enrichment and Fidelity Preservation Network for Skeleton based Action Recognition
On generalisability of segment anything model for nuclear instance segmentation in histology images
MEDs for PETs: Multilingual Euphemism Disambiguation for Potentially Euphemistic Terms
TEPI: Taxonomy-aware Embedding and Pseudo-Imaging for Scarcely-labeled Zero-shot Genome Classification
Enhancing Image Retrieval : A Comprehensive Study on Photo Search using the CLIP Mode
How Good is ChatGPT at Face Biometrics? A First Look into Recognition, Soft Biometrics, and Explainability
The Neglected Tails in Vision-Language Models
From Understanding to Utilization: A Survey on Explainability for Large Language Models
Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models
Zoom-shot: Fast and Efficient Unsupervised Zero-Shot Transfer of CLIP to Vision Encoders with Multimodal Loss
M2-CLIP: A Multimodal, Multi-task Adapting Framework for Video Action Recognition
NLCG-Net: A Model-Based Zero-Shot Learning Framework for Undersampled Quantitative MRI Reconstruction
Adversarial Augmentation Training Makes Action Recognition Models More Robust to Realistic Video Distribution Shifts
Self-Supervised Bird's Eye View Motion Prediction with Cross-Modality Signals
DeepEdit: Knowledge Editing as Decoding with Constraints
Enhancing medical vision-language contrastive learning via inter-matching relation modelling
Cross-lingual Editing in Multilingual Language Models
Understanding Biases in ChatGPT-based Recommender Systems: Provider Fairness, Temporal Stability, and Recency
Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models
Unsupervised Motion Retargeting for Human-Robot Imitation
ADCNet: a unified framework for predicting the activity of antibody-drug conjugates
Contrastive Perplexity for Controlled Generation: An Application in Detoxifying Large Language Models
Model Editing at Scale leads to Gradual and Catastrophic Forgetting
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.