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.
Florence: A New Foundation Model for Computer Vision
Representing Prior Knowledge Using Randomly, Weighted Feature Networks for Visual Relationship Detection
Action Recognition with Domain Invariant Features of Skeleton Image
Evaluating Transformers for Lightweight Action Recognition
M2A: Motion Aware Attention for Accurate Video Action Recognition
Solving Linear Algebra by Program Synthesis
$AIR^2$ for Interaction Prediction
Real-time 3D human action recognition based on Hyperpoint sequence
Multimodal Generalized Zero Shot Learning for Gleason Grading using Self-Supervised Learning
Zero-Shot Learning in Named-Entity Recognition with External Knowledge
A Central Difference Graph Convolutional Operator for Skeleton-Based Action Recognition
Dance In the Wild: Monocular Human Animation with Neural Dynamic Appearance Synthesis
Multi-Scale Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition
KORSAL: Key-point Detection based Online Real-Time Spatio-Temporal Action Localization
Dual Progressive Prototype Network for Generalized Zero-Shot Learning
An Entropy-guided Reinforced Partial Convolutional Network for Zero-Shot Learning
Zero-Shot Translation using Diffusion Models
Trajectory Prediction with Graph-based Dual-scale Context Fusion
Relational Self-Attention: What's Missing in Attention for Video Understanding
Equivariant Deep Dynamical Model for Motion Prediction
LSTA-Net: Long short-term Spatio-Temporal Aggregation Network for Skeleton-based Action Recognition
Gradient Frequency Modulation for Visually Explaining Video Understanding Models
Skeleton-Based Mutually Assisted Interacted Object Localization and Human Action Recognition
IIP-Transformer: Intra-Inter-Part Transformer for Skeleton-Based Action Recognition
Logsig-RNN: a novel network for robust and efficient skeleton-based action recognition
Logical Activation Functions: Logit-space equivalents of Probabilistic Boolean Operators
Fast Model Editing at Scale
AEI: Actors-Environment Interaction with Adaptive Attention for Temporal Action Proposals Generation
MixNorm: Test-Time Adaptation Through Online Normalization Estimation
Wav2CLIP: Learning Robust Audio Representations From CLIP
GTM: Gray Temporal Model for Video Recognition
Few-Shot Temporal Action Localization with Query Adaptive Transformer
Spatial-Temporal Transformer for 3D Point Cloud Sequences
TIP: Task-Informed Motion Prediction for Intelligent Vehicles
TEAM-Net: Multi-modal Learning for Video Action Recognition with Partial Decoding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.