# Less is more: zero-shot learning from online textual documents with noise suppression

arXiv: https://arxiv.org/abs/1604.01146 · HTML: https://mlsanity.com/paper/1604.01146/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Apr 2016.

## Built on by (most cited first, 30 of 40)

- [DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection](https://mlsanity.com/paper/2209.09407/) (2022)
- [K-LITE: Learning Transferable Visual Models with External Knowledge](https://mlsanity.com/paper/2204.09222/) (2022)
- [Elaborative Rehearsal for Zero-shot Action Recognition](https://mlsanity.com/paper/2108.02833/) (2021)
- [Debiased Contrastive Learning of Unsupervised Sentence Representations](https://mlsanity.com/paper/2205.00656/) (2022)
- [I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification](https://mlsanity.com/paper/2212.02291/) (2022)
- [OntoZSL: Ontology-enhanced Zero-shot Learning](https://mlsanity.com/paper/2102.07339/) (2021)
- [Knowledge-aware Zero-Shot Learning: Survey and Perspective](https://mlsanity.com/paper/2103.00070/) (2021)
- [On Guiding Visual Attention with Language Specification](https://mlsanity.com/paper/2202.08926/) (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)
- [Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey](https://mlsanity.com/paper/2112.10006/) (2021)
- [Whitening-based Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2305.17746/) (2023)
- [Fine-Grained Zero-Shot Learning with DNA as Side Information](https://mlsanity.com/paper/2109.14133/) (2021)
- [Few-shot Named Entity Recognition with Self-describing Networks](https://mlsanity.com/paper/2203.12252/) (2022)
- [Towards Zero-shot Sign Language Recognition](https://mlsanity.com/paper/2201.05914/) (2022)
- [Revisiting Document Representations for Large-Scale Zero-Shot Learning](https://mlsanity.com/paper/2104.10355/) (2021)
- [Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2101.03292/) (2021)
- [Rebalanced Zero-shot Learning](https://mlsanity.com/paper/2210.07031/) (2022)
- [The Curious Layperson: Fine-Grained Image Recognition without Expert Labels](https://mlsanity.com/paper/2111.03651/) (2021)
- [CIZSL++: Creativity Inspired Generative Zero-Shot Learning](https://mlsanity.com/paper/2101.00173/) (2021)
- [Cross Knowledge-based Generative Zero-Shot Learning Approach with Taxonomy Regularization](https://mlsanity.com/paper/2101.09892/) (2021)
- [Field-Guide-Inspired Zero-Shot Learning](https://mlsanity.com/paper/2108.10967/) (2021)
- [Visual-Semantic Decomposition and Partial Alignment for Document-based Zero-Shot Learning](https://mlsanity.com/paper/2407.15613/) (2024)
- [An Iterative Co-Training Transductive Framework for Zero Shot Learning](https://mlsanity.com/paper/2203.16041/) (2022)
- [Imaginative Walks: Generative Random Walk Deviation Loss for Improved Unseen Learning Representation](https://mlsanity.com/paper/2104.09757/) (2021)
- [HardBoost: Boosting Zero-Shot Learning with Hard Classes](https://mlsanity.com/paper/2201.05479/) (2022)
- [SemSup: Semantic Supervision for Simple and Scalable Zero-shot Generalization](https://mlsanity.com/paper/2202.13100/) (2022)
- [Learning by Asking Questions for Knowledge-based Novel Object Recognition](https://mlsanity.com/paper/2210.05879/) (2022)
- [Continual Zero-Shot Learning through Semantically Guided Generative Random Walks](https://mlsanity.com/paper/2308.12366/) (2023)
- [MADS: Multi-Attribute Document Supervision for Zero-Shot Image Classification](https://mlsanity.com/paper/2503.06847/) (2025)

## Abstract (arXiv)

Classifying a visual concept merely from its associated online textual source, such as a Wikipedia article, is an attractive research topic in zero-shot learning because it alleviates the burden of manually collecting semantic attributes. Several recent works have pursued this approach by exploring various ways of connecting the visual and text domains. This paper revisits this idea by stepping further to consider one important factor: the textual representation is usually too noisy for the zero-shot learning application. This consideration motivates us to design a simple-but-effective zero-shot learning method capable of suppressing noise in the text. More specifically, we propose an l2,1-norm based objective function which can simultaneously suppress the noisy signal in the text and learn a function to match the text document and visual features. We also develop an optimization algorithm to efficiently solve the resulting problem. By conducting experiments on two large datasets, we demonstrate that the proposed method significantly outperforms the competing methods which rely on online information sources but without explicit noise suppression. We further make an in-depth analysis of the proposed method and provide insight as to what kind of information in documents is useful for zero-shot learning.