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.
Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders
Multimodal Explanations by Predicting Counterfactuality in Videos
Content Authentication for Neural Imaging Pipelines: End-to-end Optimization of Photo Provenance in Complex Distribution Channels
SUSiNet: See, Understand and Summarize it
MS-ASL: A Large-Scale Data Set and Benchmark for Understanding American Sign Language
Graph-Based Global Reasoning Networks
Optimized Skeleton-based Action Recognition via Sparsified Graph Regression
Iterative Projection and Matching: Finding Structure-preserving Representatives and Its Application to Computer Vision
Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction
Multi-granularity Generator for Temporal Action Proposal
Unrepresentative video data: A review and evaluation
Adversarial Attacks for Optical Flow-Based Action Recognition Classifiers
Real-time high speed motion prediction using fast aperture-robust event-driven visual flow
Stacked Spatio-Temporal Graph Convolutional Networks for Action Segmentation
LSTA: Long Short-Term Attention for Egocentric Action Recognition
Privacy-Preserving Action Recognition for Smart Hospitals using Low-Resolution Depth Images
Temporal Bilinear Networks for Video Action Recognition
Learning Conditional Random Fields with Augmented Observations for Partially Observed Action Recognition
Generate, Segment and Refine: Towards Generic Manipulation Segmentation
Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles
RGB-D Based Action Recognition with Light-weight 3D Convolutional Networks
Polarity Loss for Zero-shot Object Detection
Bi-Adversarial Auto-Encoder for Zero-Shot Learning
Multi-Task Learning of Generalizable Representations for Video Action Recognition
TSM: Temporal Shift Module for Efficient Video Understanding
Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations
Compressing Recurrent Neural Networks with Tensor Ring for Action Recognition
Fine-grained Classification using Heterogeneous Web Data and Auxiliary Categories
Beyond Attributes: Adversarial Erasing Embedding Network for Zero-shot Learning
Generalized Zero-Shot Recognition based on Visually Semantic Embedding
Not just a matter of semantics: the relationship between visual similarity and semantic similarity
Relational Long Short-Term Memory for Video Action Recognition
Generative Dual Adversarial Network for Generalized Zero-shot Learning
Skeleton-Based Action Recognition with Synchronous Local and Non-local Spatio-temporal Learning and Frequency Attention
Cross and Learn: Cross-Modal Self-Supervision
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.