# Selective Zero-Shot Classification with Augmented Attributes

arXiv: https://arxiv.org/abs/1807.07437 · HTML: https://mlsanity.com/paper/1807.07437/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2018.

## Built on by (most cited first, 9 of 9)

- [I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification](https://mlsanity.com/paper/2212.02291/) (2022)
- [Attention Diversification for Domain Generalization](https://mlsanity.com/paper/2210.04206/) (2022)
- [VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning](https://mlsanity.com/paper/2203.10444/) (2022)
- [I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification](https://mlsanity.com/paper/2209.10304/) (2022)
- [Disentangling Semantic-to-visual Confusion for Zero-shot Learning](https://mlsanity.com/paper/2106.08605/) (2021)
- [A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculture](https://mlsanity.com/paper/2210.11318/) (2022)
- [Visual-Semantic Decomposition and Partial Alignment for Document-based Zero-Shot Learning](https://mlsanity.com/paper/2407.15613/) (2024)
- [MADS: Multi-Attribute Document Supervision for Zero-Shot Image Classification](https://mlsanity.com/paper/2503.06847/) (2025)
- [Interpretable Zero-shot Learning with Infinite Class Concepts](https://mlsanity.com/paper/2505.03361/) (2025)

## Abstract (arXiv)

In this paper, we introduce a selective zero-shot classification problem: how can the classifier avoid making dubious predictions? Existing attribute-based zero-shot classification methods are shown to work poorly in the selective classification scenario. We argue the under-complete human defined attribute vocabulary accounts for the poor performance. We propose a selective zero-shot classifier based on both the human defined and the automatically discovered residual attributes. The proposed classifier is constructed by firstly learning the defined and the residual attributes jointly. Then the predictions are conducted within the subspace of the defined attributes. Finally, the prediction confidence is measured by both the defined and the residual attributes. Experiments conducted on several benchmarks demonstrate that our classifier produces a superior performance to other methods under the risk-coverage trade-off metric.