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.
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach
Meta Transfer of Self-Supervised Knowledge: Foundation Model in Action for Post-Traumatic Epilepsy Prediction
Retrieval-augmented Multilingual Knowledge Editing
SEER-ZSL: Semantic Encoder-Enhanced Representations for Generalized Zero-Shot Learning
SADA: Semantic adversarial unsupervised domain adaptation for Temporal Action Localization
MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA
GCNext: Towards the Unity of Graph Convolutions for Human Motion Prediction
GazeMoDiff: Gaze-guided Diffusion Model for Stochastic Human Motion Prediction
Neuron-Level Knowledge Attribution in Large Language Models
EDA: Evolving and Distinct Anchors for Multimodal Motion Prediction
ParsNets: A Parsimonious Orthogonal and Low-Rank Linear Networks for Zero-Shot Learning
Generative Model-based Feature Knowledge Distillation for Action Recognition
CLIP-guided Federated Learning on Heterogeneous and Long-Tailed Data
Deep Learning-Based Cyber-Attack Detection Model for Smart Grids
A Cyber-Physical Architecture for Microgrids based on Deep learning and LORA Technology
Knowledge-Driven Modulation of Neural Networks with Attention Mechanism for Next Activity Prediction
Motion Flow Matching for Human Motion Synthesis and Editing
Online Action Recognition for Human Risk Prediction with Anticipated Haptic Alert via Wearables
Semi-Supervised Class-Agnostic Motion Prediction with Pseudo Label Regeneration and BEVMix
EZ-CLIP: Efficient Zeroshot Video Action Recognition
G-MEMP: Gaze-Enhanced Multimodal Ego-Motion Prediction in Driving
Open-Pose 3D Zero-Shot Learning: Benchmark and Challenges
CSI-Based Cross-Domain Activity Recognition via Zero-Shot Prototypical Networks
Visual Self-paced Iterative Learning for Unsupervised Temporal Action Localization
Towards a geometric understanding of Spatio Temporal Graph Convolution Networks
Recent Advances in Deterministic Human Motion Prediction: A Review
Navigating Open Set Scenarios for Skeleton-based Action Recognition
History Matters: Temporal Knowledge Editing in Large Language Model
Physical-Layer Semantic-Aware Network for Zero-Shot Wireless Sensing
Kraken: enabling joint trajectory prediction by utilizing Mode Transformer and Greedy Mode Processing
A Review of Machine Learning Methods Applied to Video Analysis Systems
Neuron Patching: Semantic-based Neuron-level Language Model Repair for Code Generation
DemoCaricature: Democratising Caricature Generation with a Rough Sketch
Short-term prediction of construction waste transport activities using AI-Truck
STEP CATFormer: Spatial-Temporal Effective Body-Part Cross Attention Transformer for Skeleton-based Action Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.