# Targeted Attention for Generalized- and Zero-Shot Learning

arXiv: https://arxiv.org/abs/2211.09322 · HTML: https://mlsanity.com/paper/2211.09322/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 23 references that are in the map.
- First posted on arXiv 17 Nov 2022.

## Builds on (most cited first, 14 of 14)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Deep Metric Learning via Lifted Structured Feature Embedding](https://mlsanity.com/paper/1511.06452/) (2015)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [Adversarial Autoencoders](https://mlsanity.com/paper/1511.05644/) (2015)
- [Feature Generating Networks for Zero-Shot Learning](https://mlsanity.com/paper/1712.00981/) (2017)
- [No Fuss Distance Metric Learning using Proxies](https://mlsanity.com/paper/1703.07464/) (2017)
- [Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders](https://mlsanity.com/paper/1812.01784/) (2018)
- [Multi-modal Cycle-consistent Generalized Zero-Shot Learning](https://mlsanity.com/paper/1808.00136/) (2018)
- [Learning Robust Visual-Semantic Embeddings](https://mlsanity.com/paper/1703.05908/) (2017)
- [Generating Visual Representations for Zero-Shot Classification](https://mlsanity.com/paper/1708.06975/) (2017)
- [Zero-Shot Learning via Class-Conditioned Deep Generative Models](https://mlsanity.com/paper/1711.05820/) (2017)
- [Concept Drift Adaptive Physical Event Detection for Social Media Streams](https://mlsanity.com/paper/1911.05494/) (2019)

## Abstract (arXiv)

The Zero-Shot Learning (ZSL) task attempts to learn concepts without any labeled data. Unlike traditional classification/detection tasks, the evaluation environment is provided unseen classes never encountered during training. As such, it remains both challenging, and promising on a variety of fronts, including unsupervised concept learning, domain adaptation, and dataset drift detection. Recently, there have been a variety of approaches towards solving ZSL, including improved metric learning methods, transfer learning, combinations of semantic and image domains using, e.g. word vectors, and generative models to model the latent space of known classes to classify unseen classes. We find many approaches require intensive training augmentation with attributes or features that may be commonly unavailable (attribute-based learning) or susceptible to adversarial attacks (generative learning). We propose combining approaches from the related person re-identification task for ZSL, with key modifications to ensure sufficiently improved performance in the ZSL setting without the need for feature or training dataset augmentation. We are able to achieve state-of-the-art performance on the CUB200 and Cars196 datasets in the ZSL setting compared to recent works, with NMI (normalized mutual inference) of 63.27 and top-1 of 61.04 for CUB200, and NMI 66.03 with top-1 82.75% in Cars196. We also show state-of-the-art results in the Generalized Zero-Shot Learning (GZSL) setting, with Harmonic Mean R-1 of 66.14% on the CUB200 dataset.