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.
MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge
RE-MOVE: An Adaptive Policy Design for Robotic Navigation Tasks in Dynamic Environments via Language-Based Feedback
Editing Implicit Assumptions in Text-to-Image Diffusion Models
ODIN: On-demand Data Formulation to Mitigate Dataset Lock-in
Robust Contrastive Language-Image Pre-training against Data Poisoning and Backdoor Attacks
Large Language Models in the Workplace: A Case Study on Prompt Engineering for Job Type Classification
TriDet: Temporal Action Detection with Relative Boundary Modeling
SPOTR: Spatio-temporal Pose Transformers for Human Motion Prediction
ZeroNLG: Aligning and Autoencoding Domains for Zero-Shot Multimodal and Multilingual Natural Language Generation
Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perception
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations
Exploiting the Textual Potential from Vision-Language Pre-training for Text-based Person Search
Approach to Learning Generalized Audio Representation Through Batch Embedding Covariance Regularization and Constant-Q Transforms
Learning Discriminative Representations for Skeleton Based Action Recognition
Describe me an Aucklet: Generating Grounded Perceptual Category Descriptions
TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction
Faster Learning of Temporal Action Proposal via Sparse Multilevel Boundary Generator
Enhancing Activity Prediction Models in Drug Discovery with the Ability to Understand Human Language
MITFAS: Mutual Information based Temporal Feature Alignment and Sampling for Aerial Video Action Recognition
Zero-Shot Self-Supervised Joint Temporal Image and Sensitivity Map Reconstruction via Linear Latent Space
Adopting the Multi-answer Questioning Task with an Auxiliary Metric for Extreme Multi-label Text Classification Utilizing the Label Hierarchy
Predicting Motion Plans for Articulating Everyday Objects
AZTR: Aerial Video Action Recognition with Auto Zoom and Temporal Reasoning
Sketch2Cloth: Sketch-based 3D Garment Generation with Unsigned Distance Fields
Distilled Reverse Attention Network for Open-world Compositional Zero-Shot Learning
Can We Use Diffusion Probabilistic Models for 3D Motion Prediction?
Edit at your own risk: evaluating the robustness of edited models to distribution shifts
Texture-Based Input Feature Selection for Action Recognition
LLaMA: Open and Efficient Foundation Language Models
Spatial-temporal Transformer-guided Diffusion based Data Augmentation for Efficient Skeleton-based Action Recognition
Temporal-Channel Topology Enhanced Network for Skeleton-Based Action Recognition
Teaching CLIP to Count to Ten
Active Prompting with Chain-of-Thought for Large Language Models
K-Diag: Knowledge-enhanced Disease Diagnosis in Radiographic Imaging
ACE: Zero-Shot Image to Image Translation via Pretrained Auto-Contrastive-Encoder
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.