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.
Shifts 2.0: Extending The Dataset of Real Distributional Shifts
Interpretability, Then What? Editing Machine Learning Models to Reflect Human Knowledge and Values
TENET: Transformer Encoding Network for Effective Temporal Flow on Motion Prediction
A New Adjacency Matrix Configuration in GCN-based Models for Skeleton-based Action Recognition
Conditioned Human Trajectory Prediction using Iterative Attention Blocks
Siamese Contrastive Embedding Network for Compositional Zero-Shot Learning
Taxonomy and evolution predicting using deep learning in images
Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition
A Zero-Shot Classification Approach for a Word-Guessing Challenge
ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning
PROTOtypical Logic Tensor Networks (PROTO-LTN) for Zero Shot Learning
Learn to Predict How Humans Manipulate Large-sized Objects from Interactive Motions
Learning to Refactor Action and Co-occurrence Features for Temporal Action Localization
ProtoCLIP: Prototypical Contrastive Language Image Pretraining
Weakly-Supervised Temporal Action Localization by Progressive Complementary Learning
Pyramid Region-based Slot Attention Network for Temporal Action Proposal Generation
MPA: MultiPath++ Based Architecture for Motion Prediction
0/1 Deep Neural Networks via Block Coordinate Descent
Unsupervised Kinematic Motion Detection for Part-segmented 3D Shape Collections
Self-Generated In-Context Learning: Leveraging Auto-regressive Language Models as a Demonstration Generator
Zero-Shot Video Question Answering via Frozen Bidirectional Language Models
VCT: A Video Compression Transformer
Zero-shot object goal visual navigation
Memory-Based Model Editing at Scale
From Human Days to Machine Seconds: Automatically Answering and Generating Machine Learning Final Exams
Zero-Shot Audio Classification using Image Embeddings
Learn2Augment: Learning to Composite Videos for Data Augmentation in Action Recognition
Disentangled Ontology Embedding for Zero-shot Learning
PrivHAR: Recognizing Human Actions From Privacy-preserving Lens
TadML: A fast temporal action detection with Mechanics-MLP
MotionCNN: A Strong Baseline for Motion Prediction in Autonomous Driving
A Simple Meta-learning Paradigm for Zero-shot Intent Classification with Mixture Attention Mechanism
3D Convolutional with Attention for Action Recognition
Recognition of Unseen Bird Species by Learning from Field Guides
GIN: Graph-based Interaction-aware Constraint Policy Optimization for Autonomous Driving
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.