Zero-shot-Segmentation

This repo mainly records my research pipeline in zero-shot segmentation. Other tasks including zero-shot classification and zero-shot detection are also involved.

1. Related Knowledge

1.1 Zero-shot Classification

1.1.1 Attribute-based classification

1. Attribute-Based Classification for Zero-Shot Visual Object Categorization

• From 2013 TPAMI
• main contribution: propose AWA dataset

2. Zero-Shot Learning - A Comprehensive Evaluation of the Good, the Bad and the Ugly

• From 2018 TPAMI
• main contribution: propose AWA-2 dataset

3. Learning to detect unseen object classes by between-class attribute transfer

• From 2009 CVPR
• main contribution: propose attribute-based classification

4. Attribute-based classification for zero-shot visual object categorization

• From 2014 TPAMI
• Main contribution:

1.1.2 Gating methods

1. Adaptive confidence smoothing for generalized zero-shot learning

• From 2019 CVPR
• Main contribution: incorporates a gating mechanism with two experts to handle the unseen and seen domains separately.

2. Zero-shot learning through cross-modal transfer

• From 2013 nips
• Main contribution: incorporates a gating mechanism with two experts to handle the unseen and seen domains separately.

1.2 Zero-shot Object Detection

2. Zero-shot Segmentation

2.1 Zero-shot Semantic Segmentation

2.1.1 Pixel-level Zero-shot Semantic Segmentation

1. Hang Zhao, Xavier Puig, Bolei Zhou, Sanja Fidler, and Antonio Torralba. Open vocabulary scene parsing. In ICCV, pages 2002–2010, 2017.
2. Yongqin Xian, Subhabrata Choudhury, Yang He, Bernt Schiele, and Zeynep Akata. Semantic projection network for zero-and few-label semantic segmentation. In CVPR, pages 8256–8265, 2019.
3. Zero-shot semantic segmentation

• From 2019 NeurIPS

4. Jingwei Ji, Shyamal Buch, Alvaro Soto, and Juan Carlos Niebles. End-to-end joint semantic segmentation of actors and actions in video. In ECCV, pages 702–717, 2018.

2.1.2 Segment-level Zero-shot Semantic Segmentation