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.
Adaptive Local-Component-aware Graph Convolutional Network for One-shot Skeleton-based Action Recognition
RNGDet++: Road Network Graph Detection by Transformer with Instance Segmentation and Multi-scale Features Enhancement
I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification
WeLM: A Well-Read Pre-trained Language Model for Chinese
DeepGraphONet: A Deep Graph Operator Network to Learn and Zero-shot Transfer the Dynamic Response of Networked Systems
MTR-A: 1st Place Solution for 2022 Waymo Open Dataset Challenge -- Motion Prediction
VDDB: a comprehensive resource and machine learning platform for antiviral drug discovery
OmniVL:One Foundation Model for Image-Language and Video-Language Tasks
STPOTR: Simultaneous Human Trajectory and Pose Prediction Using a Non-Autoregressive Transformer for Robot Following Ahead
Differentiable Frequency-based Disentanglement for Aerial Video Action Recognition
Natural Language Inference Prompts for Zero-shot Emotion Classification in Text across Corpora
Vision Transformers for Action Recognition: A Survey
DMMGAN: Diverse Multi Motion Prediction of 3D Human Joints using Attention-Based Generative Adverserial Network
VL-Taboo: An Analysis of Attribute-based Zero-shot Capabilities of Vision-Language Models
Multiple Object Tracking in Recent Times: A Literature Review
FETA: Towards Specializing Foundation Models for Expert Task Applications
Shifting Perspective to See Difference: A Novel Multi-View Method for Skeleton based Action Recognition
SIND: A Drone Dataset at Signalized Intersection in China
Depression Symptoms Modelling from Social Media Text: A Semi-supervised Learning Approach
Federated Zero-Shot Learning for Visual Recognition
Design of the topology for contrastive visual-textual alignment
Temporal Contrastive Learning with Curriculum
FLAME: Free-form Language-based Motion Synthesis & Editing
SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition
Active Learning with Effective Scoring Functions for Semi-Supervised Temporal Action Localization
ViA: View-invariant Skeleton Action Representation Learning via Motion Retargeting
SoMoFormer: Multi-Person Pose Forecasting with Transformers
Flexible Job Classification with Zero-Shot Learning
Exploring Semantic Attributes from A Foundation Model for Federated Learning of Disjoint Label Spaces
ProspectNet: Weighted Conditional Attention for Future Interaction Modeling in Behavior Prediction
Actor-identified Spatiotemporal Action Detection --- Detecting Who Is Doing What in Videos
Self-Supervised Face Presentation Attack Detection with Dynamic Grayscale Snippets
CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation
Adaptive Perception Transformer for Temporal Action Localization
Enabling Weakly-Supervised Temporal Action Localization from On-Device Learning of the Video Stream
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.