IJCAI 2020 小样本、零样本、领域自适应、元学习论文汇总

风流意气都作罢 提交于 2020-08-05 09:16:57

小样本学习(few-shot learning)

SimPropNet: Improved Similarity Propagation for Few-shot Image Segmentation

Learning Task-aware Local Representations for Few-shot Learning

Transductive Relation-Propagation Network for Few-shot Learning

Few-shot Visual Learning with Contextual Memory and Fine-grained Calibration

Few-shot Human Motion Prediction via Learning Novel Motion Dynamics

Weakly Supervised Few-shot Object Segmentation using Co-Attention with Visual and Semantic Embeddings

Self-Supervised Tuning for Few-Shot Segmentation

Multi-attention Meta Learning for Few-shot Fine-grained Image Recognition

Asymmetric Distribution Measure for Few-shot Learning


零样本(zero-shot learning)

Lifelong Zero-Shot Learning

Zero-Shot Object Detection via Learning an Embedding from Semantic Space to Visual Space

Progressive Domain-Independent Feature Decomposition Network for Zero-Shot Sketch-Based Image Retrieval

CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLP

Generalized Zero-Shot Text Classification for ICD Coding


领域自适应(domain adaptation)

domain adaptation:

Bidirectional Adversarial Training for Semi-Supervised Domain Adaptation

Metric Learning in Optimal Transport for Domain Adaptation

Towards Accurate and Robust Domain Adaptation under Noisy Environments

Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation

Joint Partial Optimal Transport for Open Set Domain Adaptation

Self-adaptive Re-weighted Adversarial Domain Adaptation

Unsupervised Domain Adaptation with Dual-Scheme Fusion Network for Medical Image Segmentation

Unsupervised Domain Adaptation of a Pretrained Cross-Lingual Language Model

Domain Adaptation for Semantic Parsing

Bridging Cross-Tasks Gap for Cognitive Assessment via Fine-Grained Domain Adaptation

Consistent Domain Structure Learning and Domain Alignment for 2D Image-Based 3D Objects Retrieval


元学习(meta-learning)

Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning

Federated Meta-Learning for Fraudulent Credit Card Detection


推荐阅读:

易学教程内所有资源均来自网络或用户发布的内容,如有违反法律规定的内容欢迎反馈
该文章没有解决你所遇到的问题?点击提问,说说你的问题,让更多的人一起探讨吧!