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.
Prompt-Guided Zero-Shot Anomaly Action Recognition using Pretrained Deep Skeleton Features
Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning
Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling
Gazeformer: Scalable, Effective and Fast Prediction of Goal-Directed Human Attention
Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot Learning
ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Box
Collaborative Multi-Object Tracking with Conformal Uncertainty Propagation
Multi-view knowledge distillation transformer for human action recognition
Prompt-Guided Transformers for End-to-End Open-Vocabulary Object Detection
3Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognition
Toward Open-domain Slot Filling via Self-supervised Co-training
Explore the Power of Synthetic Data on Few-shot Object Detection
The effectiveness of MAE pre-pretraining for billion-scale pretraining
A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition
Frozen Language Model Helps ECG Zero-Shot Learning
Weakly-Supervised Temporal Action Localization by Inferring Salient Snippet-Feature
Multi-modal Prompting for Low-Shot Temporal Action Localization
Large Language Models Can Be Used to Estimate the Latent Positions of Politicians
ProphNet: Efficient Agent-Centric Motion Forecasting with Anchor-Informed Proposals
PanGu-Σ: Towards Trillion Parameter Language Model with Sparse Heterogeneous Computing
EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning
Explicit Visual Prompting for Low-Level Structure Segmentations
Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition
HMC: Hierarchical Mesh Coarsening for Skeleton-free Motion Retargeting
MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Tracking
Video Action Recognition with Attentive Semantic Units
Exploiting Semantic Attributes for Transductive Zero-Shot Learning
Dual-path Adaptation from Image to Video Transformers
Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performances
TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization
DiffBEV: Conditional Diffusion Model for Bird's Eye View Perception
Real-time Multi-Object Tracking Based on Bi-directional Matching
Co-Occurrence Matters: Learning Action Relation for Temporal Action Localization
Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometry
Bi-directional Distribution Alignment for Transductive Zero-Shot Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.