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.
MSSTNet: A Multi-Scale Spatio-Temporal CNN-Transformer Network for Dynamic Facial Expression Recognition
OTTER: Effortless Label Distribution Adaptation of Zero-shot Models
`Eyes of a Hawk and Ears of a Fox': Part Prototype Network for Generalized Zero-Shot Learning
Fine-Grained Side Information Guided Dual-Prompts for Zero-Shot Skeleton Action Recognition
Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning
Connecting NeRFs, Images, and Text
SparseAD: Sparse Query-Centric Paradigm for Efficient End-to-End Autonomous Driving
DyKnow: Dynamically Verifying Time-Sensitive Factual Knowledge in LLMs
ActNetFormer: Transformer-ResNet Hybrid Method for Semi-Supervised Action Recognition in Videos
Anchor-based Robust Finetuning of Vision-Language Models
Audio-Visual Generalized Zero-Shot Learning using Pre-Trained Large Multi-Modal Models
Test-Time Adaptation with SaLIP: A Cascade of SAM and CLIP for Zero shot Medical Image Segmentation
Test-Time Zero-Shot Temporal Action Localization
Two-Person Interaction Augmentation with Skeleton Priors
Localizing Moments of Actions in Untrimmed Videos of Infants with Autism Spectrum Disorder
Condition Monitoring with Incomplete Data: An Integrated Variational Autoencoder and Distance Metric Framework
UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection
Bootstrapping Chest CT Image Understanding by Distilling Knowledge from X-ray Expert Models
High-Discriminative Attribute Feature Learning for Generalized Zero-Shot Learning
MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models
Forget NLI, Use a Dictionary: Zero-Shot Topic Classification for Low-Resource Languages with Application to Luxembourgish
Label Propagation for Zero-shot Classification with Vision-Language Models
Reliable Feature Selection for Adversarially Robust Cyber-Attack Detection
PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videos
UniAV: Unified Audio-Visual Perception for Multi-Task Video Event Localization
Towards more realistic human motion prediction with attention to motion coordination
Locating and Editing Factual Associations in Mamba
SC4D: Sparse-Controlled Video-to-4D Generation and Motion Transfer
Quantifying Uncertainty in Motion Prediction with Variational Bayesian Mixture
Towards Large Language Model driven Reference-less Translation Evaluation for English and Indian Languages
Multi-Scale Spatial-Temporal Self-Attention Graph Convolutional Networks for Skeleton-based Action Recognition
Scalable Model Editing via Customized Expert Networks
Deep Image Composition Meets Image Forgery
Language Model Guided Interpretable Video Action Reasoning
PhysORD: A Neuro-Symbolic Approach for Physics-infused Motion Prediction in Off-road Driving
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.