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.
Learning Spatio-Temporal Representation with Local and Global Diffusion
Detecting Photoshopped Faces by Scripting Photoshop
Joint Concept Matching based Learning for Zero-Shot Recognition
Semantics to Space(S2S): Embedding semantics into spatial space for zero-shot verb-object query inferencing
Temporal Transformer Networks: Joint Learning of Invariant and Discriminative Time Warping
Attention-based Multi-Input Deep Learning Architecture for Biological Activity Prediction: An Application in EGFR Inhibitors
Task-Aware Feature Generation for Zero-Shot Compositional Learning
From Fully Supervised to Zero Shot Settings for Twitter Hashtag Recommendation
Zero-Shot Image Classification Using Coupled Dictionary Embedding
A Generative Framework for Zero-Shot Learning with Adversarial Domain Adaptation
HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips
Large-Scale Multi-Label Text Classification on EU Legislation
GAMMA: A General Agent Motion Model for Autonomous Driving
A Natural Language-Inspired Multi-label Video Streaming Traffic Classification Method Based on Deep Neural Networks
Zero-Shot Semantic Segmentation
Mining YouTube - A dataset for learning fine-grained action concepts from webly supervised video data
ZstGAN: An Adversarial Approach for Unsupervised Zero-Shot Image-to-Image Translation
CLAREL: Classification via retrieval loss for zero-shot learning
Rethinking Full Connectivity in Recurrent Neural Networks
Hierarchical Feature Aggregation Networks for Video Action Recognition
What Makes Training Multi-Modal Classification Networks Hard?
Improving Action Localization by Progressive Cross-stream Cooperation
Efficient Amortised Bayesian Inference for Hierarchical and Nonlinear Dynamical Systems
ODE$^2$VAE: Deep generative second order ODEs with Bayesian neural networks
Extreme Multi-Label Legal Text Classification: A case study in EU Legislation
Exploring Feature Representation and Training strategies in Temporal Action Localization
What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention
Marginalized Average Attentional Network for Weakly-Supervised Learning
Lightweight Network Architecture for Real-Time Action Recognition
Leveraging Semantic Embeddings for Safety-Critical Applications
Representation Learning on Visual-Symbolic Graphs for Video Understanding
Learning Visually Consistent Label Embeddings for Zero-Shot Learning
Richly Activated Graph Convolutional Network for Action Recognition with Incomplete Skeletons
Task-Driven Modular Networks for Zero-Shot Compositional Learning
Towards a Skeleton-Based Action Recognition For Realistic Scenarios
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.