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.
Event Log Sampling for Predictive Monitoring
HiT-DVAE: Human Motion Generation via Hierarchical Transformer Dynamical VAE
TALLFormer: Temporal Action Localization with a Long-memory Transformer
Interpretable Saliency Maps And Self-Supervised Learning For Generalized Zero Shot Medical Image Classification
SpatioTemporal Focus for Skeleton-based Action Recognition
Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localization
Do Vision-Language Pretrained Models Learn Composable Primitive Concepts?
An Iterative Co-Training Transductive Framework for Zero Shot Learning
Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction
OPD: Single-view 3D Openable Part Detection
Foveation-based Deep Video Compression without Motion Search
Unseen Classes at a Later Time? No Problem
Practical Aspects of Zero-Shot Learning
ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localization
Hybrid Routing Transformer for Zero-Shot Learning
Proactive Image Manipulation Detection
Zero-shot meta-learning for small-scale data from human subjects
ObjectFormer for Image Manipulation Detection and Localization
Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities
ZS4IE: A toolkit for Zero-Shot Information Extraction with simple Verbalizations
Unsupervised Pre-training for Temporal Action Localization Tasks
mcBERT: Momentum Contrastive Learning with BERT for Zero-Shot Slot Filling
How well does CLIP understand texture?
Mixed Differential Privacy in Computer Vision
LocATe: End-to-end Localization of Actions in 3D with Transformers
Match the Script, Adapt if Multilingual: Analyzing the Effect of Multilingual Pretraining on Cross-lingual Transferability
Continual Spatio-Temporal Graph Convolutional Networks
No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time Surfaces
VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning
DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition
Domain Adaptation Meets Zero-Shot Learning: An Annotation-Efficient Approach to Multi-Modality Medical Image Segmentation
Semantic-diversity transfer network for generalized zero-shot learning via inner disagreement based OOD detector
MotionAug: Augmentation with Physical Correction for Human Motion Prediction
PreTR: Spatio-Temporal Non-Autoregressive Trajectory Prediction Transformer
The Analysis of Online Event Streams: Predicting the Next Activity for Anomaly Detection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.