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.
Zero-shot-Learning Cross-Modality Data Translation Through Mutual Information Guided Stochastic Diffusion
Action Capsules: Human Skeleton Action Recognition
Language-Driven Anchors for Zero-Shot Adversarial Robustness
Skeleton-based Action Recognition through Contrasting Two-Stream Spatial-Temporal Networks
Graph Contrastive Learning for Skeleton-based Action Recognition
Editing Language Model-based Knowledge Graph Embeddings
Transformer-Patcher: One Mistake worth One Neuron
RF+clust for Leave-One-Problem-Out Performance Prediction
Improving Zero-Shot Action Recognition using Human Instruction with Text Description
Transfer Knowledge from Natural Language to Electrocardiography: Can We Detect Cardiovascular Disease Through Language Models?
Temporal Perceiving Video-Language Pre-training
Learning Customized Visual Models with Retrieval-Augmented Knowledge
CMAE-V: Contrastive Masked Autoencoders for Video Action Recognition
CNN-Based Action Recognition and Pose Estimation for Classifying Animal Behavior from Videos: A Survey
CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP
Failure Detection for Motion Prediction of Autonomous Driving: An Uncertainty Perspective
Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models
Leveraging Contextual Relatedness to Identify Suicide Documentation in Clinical Notes through Zero Shot Learning
Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training
Look, Listen, and Attack: Backdoor Attacks Against Video Action Recognition
Vocabulary-informed Zero-shot and Open-set Learning
Ego-Only: Egocentric Action Detection without Exocentric Transferring
Hierarchical Explanations for Video Action Recognition
DiRaC-I: Identifying Diverse and Rare Training Classes for Zero-Shot Learning
HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training
UBIWEAR: An end-to-end, data-driven framework for intelligent physical activity prediction to empower mHealth interventions
From Single-Visit to Multi-Visit Image-Based Models: Single-Visit Models are Enough to Predict Obstructive Hydronephrosis
Semantic Enhanced Knowledge Graph for Large-Scale Zero-Shot Learning
Modeling Time-Series and Spatial Data for Recommendations and Other Applications
Few-shot human motion prediction for heterogeneous sensors
Interaction-Aware Motion Planning for Autonomous Vehicles with Multi-Modal Obstacle Uncertainty Predictions
When are Lemons Purple? The Concept Association Bias of Vision-Language Models
Zero-shot Triplet Extraction by Template Infilling
MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning
TruFor: Leveraging all-round clues for trustworthy image forgery detection and localization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.