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.
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations
A Comprehensive Study of Deep Video Action Recognition
Probing Few-Shot Generalization with Attributes
Learning Portrait Style Representations
Long Term Motion Prediction Using Keyposes
VideoMix: Rethinking Data Augmentation for Video Classification
Multi Scale Temporal Graph Networks For Skeleton-based Action Recognition
Learning Class-Transductive Intent Representations for Zero-shot Intent Detection
Sparse Semi-Supervised Action Recognition with Active Learning
Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains
A New Action Recognition Framework for Video Highlights Summarization in Sporting Events
CPM: A Large-scale Generative Chinese Pre-trained Language Model
Just Ask: Learning to Answer Questions from Millions of Narrated Videos
We are More than Our Joints: Predicting how 3D Bodies Move
Annotation-Efficient Untrimmed Video Action Recognition
Video Self-Stitching Graph Network for Temporal Action Localization
Forecasting Characteristic 3D Poses of Human Actions
Direct Evolutionary Optimization of Variational Autoencoders With Binary Latents
Group-Skeleton-Based Human Action Recognition in Complex Events
Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition
Fine-Grained Re-Identification
Zero-Shot Audio Classification with Factored Linear and Nonlinear Acoustic-Semantic Projections
A Review of Open-World Learning and Steps Toward Open-World Learning Without Labels
KShapeNet: Riemannian network on Kendall shape space for Skeleton based Action Recognition
Zero-Shot Audio Classification via Semantic Embeddings
A3D: Adaptive 3D Networks for Video Action Recognition
Independent Sign Language Recognition with 3D Body, Hands, and Face Reconstruction
Attentional-GCNN: Adaptive Pedestrian Trajectory Prediction towards Generic Autonomous Vehicle Use Cases
Adversarial Refinement Network for Human Motion Prediction
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks
Boundary-sensitive Pre-training for Temporal Localization in Videos
Zero-Shot Learning with Knowledge Enhanced Visual Semantic Embeddings
Open-Vocabulary Object Detection Using Captions
A Multi-class Approach -- Building a Visual Classifier based on Textual Descriptions using Zero-Shot Learning
Generalized Continual Zero-Shot Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.