# Zero-Shot Learning by Convex Combination of Semantic Embeddings

arXiv: https://arxiv.org/abs/1312.5650 · HTML: https://mlsanity.com/paper/1312.5650/

## Key facts

- Cited by 135 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Dec 2013.

## Built on by (most cited first, 30 of 135)

- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [Decoupling Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/2112.07910/) (2021)
- [Combined Scaling for Zero-shot Transfer Learning](https://mlsanity.com/paper/2111.10050/) (2021)
- [F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models](https://mlsanity.com/paper/2209.15639/) (2022)
- [Align and Prompt: Video-and-Language Pre-training with Entity Prompts](https://mlsanity.com/paper/2112.09583/) (2021)
- [Simple multi-dataset detection](https://mlsanity.com/paper/2102.13086/) (2021)
- [Aligning Bag of Regions for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2302.13996/) (2023)
- [DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations](https://mlsanity.com/paper/2206.09541/) (2022)
- [Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers](https://mlsanity.com/paper/2305.07011/) (2023)
- [Debiased Learning from Naturally Imbalanced Pseudo-Labels](https://mlsanity.com/paper/2201.01490/) (2022)
- [ML-Decoder: Scalable and Versatile Classification Head](https://mlsanity.com/paper/2111.12933/) (2021)
- [Open-Vocabulary One-Stage Detection with Hierarchical Visual-Language Knowledge Distillation](https://mlsanity.com/paper/2203.10593/) (2022)
- [Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/2108.06230/) (2021)
- [Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/2108.06536/) (2021)
- [Opening up Open-World Tracking](https://mlsanity.com/paper/2104.11221/) (2021)
- [Zero-Shot Day-Night Domain Adaptation with a Physics Prior](https://mlsanity.com/paper/2108.05137/) (2021)
- [ZS-BERT: Towards Zero-Shot Relation Extraction with Attribute Representation Learning](https://mlsanity.com/paper/2104.04697/) (2021)
- [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)
- [SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation](https://mlsanity.com/paper/2108.12517/) (2021)
- [True Few-Shot Learning with Prompts -- A Real-World Perspective](https://mlsanity.com/paper/2111.13440/) (2021)
- [Data Efficient Language-supervised Zero-shot Recognition with Optimal Transport Distillation](https://mlsanity.com/paper/2112.09445/) (2021)
- [Large Language Models Are Zero-Shot Text Classifiers](https://mlsanity.com/paper/2312.01044/) (2023)
- [Contrastive Feature Masking Open-Vocabulary Vision Transformer](https://mlsanity.com/paper/2309.00775/) (2023)
- [TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learning](https://mlsanity.com/paper/2112.08643/) (2021)
- [Discriminative Region-based Multi-Label Zero-Shot Learning](https://mlsanity.com/paper/2108.09301/) (2021)
- [I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification](https://mlsanity.com/paper/2209.10304/) (2022)
- [Semantics-Guided Contrastive Network for Zero-Shot Object detection](https://mlsanity.com/paper/2109.06062/) (2021)
- [Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition](https://mlsanity.com/paper/2101.11530/) (2021)
- [Semantic Diversity Learning for Zero-Shot Multi-label Classification](https://mlsanity.com/paper/2105.05926/) (2021)

## Abstract (arXiv)

Several recent publications have proposed methods for mapping images into continuous semantic embedding spaces. In some cases the embedding space is trained jointly with the image transformation. In other cases the semantic embedding space is established by an independent natural language processing task, and then the image transformation into that space is learned in a second stage. Proponents of these image embedding systems have stressed their advantages over the traditional nway classification framing of image understanding, particularly in terms of the promise for zero-shot learning -- the ability to correctly annotate images of previously unseen object categories. In this paper, we propose a simple method for constructing an image embedding system from any existing nway image classifier and a semantic word embedding model, which contains the n class labels in its vocabulary. Our method maps images into the semantic embedding space via convex combination of the class label embedding vectors, and requires no additional training. We show that this simple and direct method confers many of the advantages associated with more complex image embedding schemes, and indeed outperforms state of the art methods on the ImageNet zero-shot learning task.