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.
FJMP: Factorized Joint Multi-Agent Motion Prediction over Learned Directed Acyclic Interaction Graphs
Re^2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization
BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction
Hierarchical Consistent Contrastive Learning for Skeleton-Based Action Recognition with Growing Augmentations
Video Test-Time Adaptation for Action Recognition
Dynamic Appearance: A Video Representation for Action Recognition with Joint Training
Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foreground
Evolutionary Generalized Zero-Shot Learning
On the Transferability of Visual Features in Generalized Zero-Shot Learning
Slow Motion Matters: A Slow Motion Enhanced Network for Weakly Supervised Temporal Action Localization
Auto-Focus Contrastive Learning for Image Manipulation Detection
Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
Mutual Balancing in State-Object Components for Compositional Zero-Shot Learning
Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learning
ProCC: Progressive Cross-primitive Compatibility for Open-World Compositional Zero-Shot Learning
Language-Assisted Deep Learning for Autistic Behaviors Recognition
Targeted Attention for Generalized- and Zero-Shot Learning
ReLER@ZJU Submission to the Ego4D Moment Queries Challenge 2022
Hypergraph Transformer for Skeleton-based Action Recognition
HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors
R-Pred: Two-Stage Motion Prediction Via Tube-Query Attention-Based Trajectory Refinement
A Simple Transformer-Based Model for Ego4D Natural Language Queries Challenge
Where a Strong Backbone Meets Strong Features -- ActionFormer for Ego4D Moment Queries Challenge
edBB-Demo: Biometrics and Behavior Analysis for Online Educational Platforms
AdaptKeyBERT: An Attention-Based approach towards Few-Shot & Zero-Shot Domain Adaptation of KeyBERT
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
Renewing Iterative Self-labeling Domain Adaptation with Application to the Spine Motion Prediction
Visual Semantic Segmentation Based on Few/Zero-Shot Learning: An Overview
Soft-Landing Strategy for Alleviating the Task Discrepancy Problem in Temporal Action Localization Tasks
Prior-enhanced Temporal Action Localization using Subject-aware Spatial Attention
Contrastive Self-Supervised Learning for Skeleton Representations
Extending Temporal Data Augmentation for Video Action Recognition
Prompting Large Pre-trained Vision-Language Models For Compositional Concept Learning
Training self-supervised peptide sequence models on artificially chopped proteins
Hyperparameter optimization in deep multi-target prediction
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.