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.
Face-space Action Recognition by Face-Object Interactions
Dynamic Concept Composition for Zero-Example Event Detection
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs
Convolutional Architecture Exploration for Action Recognition and Image Classification
Multi-Instance Visual-Semantic Embedding
Do Less and Achieve More: Training CNNs for Action Recognition Utilizing Action Images from the Web
Harnessing the Deep Net Object Models for Enhancing Human Action Recognition
Origami: A 803 GOp/s/W Convolutional Network Accelerator
Action Recognition with Image Based CNN Features
RNN Fisher Vectors for Action Recognition and Image Annotation
VRFP: On-the-fly Video Retrieval using Web Images and Fast Fisher Vector Products
Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
Rank Pooling for Action Recognition
Prototypical Priors: From Improving Classification to Zero-Shot Learning
Actions ~ Transformations
Fine-Grain Annotation of Cricket Videos
What Happened to My Dog in That Network: Unraveling Top-down Generators in Convolutional Neural Networks
End-to-end Learning of Action Detection from Frame Glimpses in Videos
Delving Deeper into Convolutional Networks for Learning Video Representations
From Pose to Activity: Surveying Datasets and Introducing CONVERSE
Collecting and Annotating the Large Continuous Action Dataset
Hierarchical Spatial Sum-Product Networks for Action Recognition in Still Images
Structural-RNN: Deep Learning on Spatio-Temporal Graphs
Heterogeneous Knowledge Transfer in Video Emotion Recognition, Attribution and Summarization
Learning Mid-level Words on Riemannian Manifold for Action Recognition
Handcrafted Local Features are Convolutional Neural Networks
Zero-Shot Learning via Joint Latent Similarity Embedding
Transductive Zero-Shot Action Recognition by Word-Vector Embedding
Improving performance of recurrent neural network with relu nonlinearity
Hand-Object Interaction and Precise Localization in Transitive Action Recognition
Action Recognition using Visual Attention
Online Action Recognition based on Incremental Learning of Weighted Covariance Descriptors
Pooling the Convolutional Layers in Deep ConvNets for Action Recognition
Action recognition from depth maps using deep convolutional neural networks
A Novel Approach for Human Action Recognition from Silhouette Images
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.