Skip to content

Latest commit

 

History

History
76 lines (59 loc) · 5.02 KB

REMAIN_SORTED_PAPER.md

File metadata and controls

76 lines (59 loc) · 5.02 KB

No Paper

  • [NIPS 2019] (code) Metal-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognition
  • [NIPS 2019] Online-Within-Online Meta-Learning
  • [NIPS 2019] Reconciling meta-learning and continual learning with online mixtures of tasks
  • [NIPS 2019] Neural Relational Inference with Fast Modular Meta-learning

Arxiv

  • [arXiv 2019] MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets

  • [arXiv 2019] Dont Even Look Once: Synthesizing Features for Zero-Shot Detection

  • [arXiv 2019] Knowledge Graph Transfer Network for Few-Shot Recognition

    • Knowledge Graph Transfer Network for Few-Shot Recognition 把prototypes构建成一个图，然后搞的，可以留个记录，他的测试主要在ImageNet FS和ImageNet 6K，但是显示的是PN本身就能到80%的情况下，他到了83%

  • [arXiv 2019] Learning Generalizable Representations via Diverse Supervision

  • [arXiv 2019] One-Shot Object Detection with Co-Attention and Co-Excitation

    • senet的迁移

  • [arXiv 2019] Auxiliary Learning for Deep Multi-task Learning

    • 解决multitask 参数共享问题的

  • [arXiv 2019] All you need is a good representation: A multi-level and classifier-centric representation for few-shot learning (一般)

  • [arXiv 2019] A Multi-Task Gradient Descent Method for Multi-Label Learning

  • [arXiv 2019] Lifelong Spectral Clustering

    • 连续学习、聚类后期对信息的存储

  • [arXiv 2019] CNN-based Dual-Chain Models for Knowledge Graph Learning

  • [arXiv 2019] MetAdapt: Meta-Learned Task-Adaptive Architecture for Few-Shot Classification

    • 使用模型搜索搜出来的结构，号称 SOTA 在 mini-imagenet （存疑）

  • [arXiv 2019] Charting the Right Manifold: Manifold Mixup for Few-shot Learning

    • 这个是在feature上动文章的，关键词是self-supervised 和 regularization technique。This work investigates the role of learning relevant feature manifold for few-shot tasks using self-supervision and regularization techniques.

  • [arXiv 2019] MetaFun: Meta-Learning with Iterative Functional Updates

    • 用了无限的特征长度，还有一个什么东西，效果很好83%

Application

  • [arXiv 2019] Learning Predicates as Functions to Enable Few-shot Scene Graph Prediction
  • [arXiv 2019] Few-Shot Knowledge Graph Completion (关系抽取)
  • [arXiv 2019] Few Shot Network Compression via Cross Distillation (模型压缩)
  • [arXiv 2019] Real-Time Object Tracking via Meta-Learning: Efficient Model Adaptation and One-Shot Channel Pruning （目标跟踪）

New Comming

  • [NIPS 2018] Meta-Learning MCMC Proposals

  • [ACMMM 2019] TGG: Transferable Graph Generation for Zero-shot and Few-shot Learning

  • [ACMMM 2019] Fewer-Shots and Lower-Resolutions: Towards Ultrafast Face Recognition in the Wild

  • [ICML 2019] Online Meta-Learning

  • [ICML 2019] Provable Guarantees for Gradient-Based Meta-Learning

  • [ICML 2019] Hierarchically Structured Meta-learning

  • [ICML 2019] Meta-Learning Neural Bloom Filters

  • [ICML 2018] MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning

  • [ICML 2018] Bilevel Programming for Hyperparameter Optimization and Meta-Learning

  • [ICML 2018] Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory

  • [ICML 2018] Been There, Done That: Meta-Learning with Episodic Recall

  • [ICML 2018] Gradient-Based Meta-learning with learned layerwise metric and subspace

  • [CVPR 2019] Coloring With Limited Data: Few-Shot Colorization via Memory Augmented Networks

  • [CVPR 2019] Improving Few-Shot User-Specific Gaze Adaptation via Gaze Redirection Synthesis

  • [CVPR 2019] Task Agnostic Meta-Learning for Few-Shot Learning

  • [CVPR 2019] Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning

  • [CVPR 2019] Meta-Learning With Differentiable Convex Optimization

  • [CVPR 2019] Meta-Learning Convolutional Neural Architectures for Multi-Target Concrete Defect Classification With the COncrete DEfect BRidge IMage Dataset

  • [CVPR 2018] Few-Shot Image Recognition by Predicting Parameters From Activations

  • [CVPR 2017] Few-Shot Object Recognition From Machine-Labeled Web Images

  • [ICLR 2019] Meta-Learning Probabilistic Inference for Prediction

  • [ECCV 2018] Few-Shot Human Motion Prediction via Meta-Learning

  • [ECCV 2018] Dynamic Conditional Networks for Few-Shot Learning

  • [ECCV 2018] Compound Memory Networks for Few-shot Video Classification

CIKM Paper Collation for few-shot Learning and meta-learning

  • [CIKM 2019] (paper) Meta-GNN: On Few-shot Node Classification in Graph Meta-learning
  • [CIKM 2019] (paper) Large Margin Prototypical Network for Few-shot Relation Classification with Fine-grained Features