# Generating Visual Representations for Zero-Shot Classification

arXiv: https://arxiv.org/abs/1708.06975 · HTML: https://mlsanity.com/paper/1708.06975/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Aug 2017.

## Built on by (most cited first, 30 of 37)

- [DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort](https://mlsanity.com/paper/2104.06490/) (2021)
- [CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP](https://mlsanity.com/paper/2301.04926/) (2023)
- [Contrastive Embedding for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2103.16173/) (2021)
- [FREE: Feature Refinement for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2107.13807/) (2021)
- [A Closer Look at Self-training for Zero-Label Semantic Segmentation](https://mlsanity.com/paper/2104.11692/) (2021)
- [Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/2108.06230/) (2021)
- [I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification](https://mlsanity.com/paper/2212.02291/) (2022)
- [Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/2108.06536/) (2021)
- [Introducing Language Guidance in Prompt-based Continual Learning](https://mlsanity.com/paper/2308.15827/) (2023)
- [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)
- [Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual Information](https://mlsanity.com/paper/2401.08732/) (2024)
- [See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data](https://mlsanity.com/paper/2307.10782/) (2023)
- [Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL](https://mlsanity.com/paper/2106.02193/) (2021)
- [Zero-shot causal learning](https://mlsanity.com/paper/2301.12292/) (2023)
- [ZeroC: A Neuro-Symbolic Model for Zero-shot Concept Recognition and Acquisition at Inference Time](https://mlsanity.com/paper/2206.15049/) (2022)
- [Learning from Multiple Noisy Partial Labelers](https://mlsanity.com/paper/2106.04530/) (2021)
- [Text-centric Alignment for Multi-Modality Learning](https://mlsanity.com/paper/2402.08086/) (2024)
- [Domain Disentangled Generative Adversarial Network for Zero-Shot Sketch-Based 3D Shape Retrieval](https://mlsanity.com/paper/2202.11948/) (2022)
- [HandsOff: Labeled Dataset Generation With No Additional Human Annotations](https://mlsanity.com/paper/2212.12645/) (2022)
- [How Robust are Discriminatively Trained Zero-Shot Learning Models?](https://mlsanity.com/paper/2201.10972/) (2022)
- [Zero-shot-Learning Cross-Modality Data Translation Through Mutual Information Guided Stochastic Diffusion](https://mlsanity.com/paper/2301.13743/) (2023)
- [Telling Stories for Common Sense Zero-Shot Action Recognition](https://mlsanity.com/paper/2309.17327/) (2023)
- [Visual-Semantic Decomposition and Partial Alignment for Document-based Zero-Shot Learning](https://mlsanity.com/paper/2407.15613/) (2024)
- [An Integral Projection-based Semantic Autoencoder for Zero-Shot Learning](https://mlsanity.com/paper/2306.14628/) (2023)
- [Learning Semantic Ambiguities for Zero-Shot Learning](https://mlsanity.com/paper/2201.01823/) (2022)
- [Compositional Fine-Grained Low-Shot Learning](https://mlsanity.com/paper/2105.10438/) (2021)
- [Caption Generation on Scenes with Seen and Unseen Object Categories](https://mlsanity.com/paper/2108.06165/) (2021)
- [Aligned Weight Regularizers for Pruning Pretrained Neural Networks](https://mlsanity.com/paper/2204.01385/) (2022)
- [Semantic Borrowing for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2102.04969/) (2021)

## Abstract (arXiv)

This paper addresses the task of learning an image clas-sifier when some categories are defined by semantic descriptions only (e.g. visual attributes) while the others are defined by exemplar images as well. This task is often referred to as the Zero-Shot classification task (ZSC). Most of the previous methods rely on learning a common embedding space allowing to compare visual features of unknown categories with semantic descriptions. This paper argues that these approaches are limited as i) efficient discrimi-native classifiers can't be used ii) classification tasks with seen and unseen categories (Generalized Zero-Shot Classification or GZSC) can't be addressed efficiently. In contrast , this paper suggests to address ZSC and GZSC by i) learning a conditional generator using seen classes ii) generate artificial training examples for the categories without exemplars. ZSC is then turned into a standard supervised learning problem. Experiments with 4 generative models and 5 datasets experimentally validate the approach, giving state-of-the-art results on both ZSC and GZSC.