# Zero-shot Image Recognition Using Relational Matching, Adaptation and Calibration

arXiv: https://arxiv.org/abs/1903.11701 · HTML: https://mlsanity.com/paper/1903.11701/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Mar 2019.

## Built on by (most cited first, 7 of 7)

- [Subspace Regularizers for Few-Shot Class Incremental Learning](https://mlsanity.com/paper/2110.07059/) (2021)
- [Primitive Generation and Semantic-related Alignment for Universal Zero-Shot Segmentation](https://mlsanity.com/paper/2306.11087/) (2023)
- [Semantic-Promoted Debiasing and Background Disambiguation for Zero-Shot Instance Segmentation](https://mlsanity.com/paper/2305.13173/) (2023)
- [Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2101.03292/) (2021)
- [Region Semantically Aligned Network for Zero-Shot Learning](https://mlsanity.com/paper/2110.07130/) (2021)
- [An Iterative Co-Training Transductive Framework for Zero Shot Learning](https://mlsanity.com/paper/2203.16041/) (2022)
- [Perception and Semantic Aware Regularization for Sequential Confidence Calibration](https://mlsanity.com/paper/2305.19498/) (2023)

## Abstract (arXiv)

Zero-shot learning (ZSL) for image classification focuses on recognizing novel categories that have no labeled data available for training. The learning is generally carried out with the help of mid-level semantic descriptors associated with each class. This semantic-descriptor space is generally shared by both seen and unseen categories. However, ZSL suffers from hubness, domain discrepancy and biased-ness towards seen classes. To tackle these problems, we propose a three-step approach to zero-shot learning. Firstly, a mapping is learned from the semantic-descriptor space to the image-feature space. This mapping learns to minimize both one-to-one and pairwise distances between semantic embeddings and the image features of the corresponding classes. Secondly, we propose test-time domain adaptation to adapt the semantic embedding of the unseen classes to the test data. This is achieved by finding correspondences between the semantic descriptors and the image features. Thirdly, we propose scaled calibration on the classification scores of the seen classes. This is necessary because the ZSL model is biased towards seen classes as the unseen classes are not used in the training. Finally, to validate the proposed three-step approach, we performed experiments on four benchmark datasets where the proposed method outperformed previous results. We also studied and analyzed the performance of each component of our proposed ZSL framework.