# Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networks

arXiv: https://arxiv.org/abs/1712.01928 · HTML: https://mlsanity.com/paper/1712.01928/

## Key facts

- Cited by 66 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Dec 2017.

## Built on by (most cited first, 30 of 66)

- [Counterfactual Zero-Shot and Open-Set Visual Recognition](https://mlsanity.com/paper/2103.00887/) (2021)
- [Contrastive Embedding for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2103.16173/) (2021)
- [Goal-Oriented Gaze Estimation for Zero-Shot Learning](https://mlsanity.com/paper/2103.03433/) (2021)
- [FREE: Feature Refinement for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2107.13807/) (2021)
- [Zero-shot Object Counting](https://mlsanity.com/paper/2303.02001/) (2023)
- [Semantics for Robotic Mapping, Perception and Interaction: A Survey](https://mlsanity.com/paper/2101.00443/) (2021)
- [TransZero: Attribute-guided Transformer for Zero-Shot Learning](https://mlsanity.com/paper/2112.01683/) (2021)
- [MSDN: Mutually Semantic Distillation Network for Zero-Shot Learning](https://mlsanity.com/paper/2203.03137/) (2022)
- [Self-Supervised Learning Disentangled Group Representation as Feature](https://mlsanity.com/paper/2110.15255/) (2021)
- [SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation](https://mlsanity.com/paper/2108.12517/) (2021)
- [Transporting Causal Mechanisms for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2107.11055/) (2021)
- [Partner-Assisted Learning for Few-Shot Image Classification](https://mlsanity.com/paper/2109.07607/) (2021)
- [A Survey of Unsupervised Domain Adaptation for Visual Recognition](https://mlsanity.com/paper/2112.06745/) (2021)
- [TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learning](https://mlsanity.com/paper/2112.08643/) (2021)
- [Dual Progressive Prototype Network for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2111.02073/) (2021)
- [Domain Adaptation for Time-Series Classification to Mitigate Covariate Shift](https://mlsanity.com/paper/2204.03342/) (2022)
- [Zero-Shot Learning by Harnessing Adversarial Samples](https://mlsanity.com/paper/2308.00313/) (2023)
- [Counterfactual Samples Synthesizing and Training for Robust Visual Question Answering](https://mlsanity.com/paper/2110.01013/) (2021)
- [Emergent Discrete Communication in Semantic Spaces](https://mlsanity.com/paper/2108.01828/) (2021)
- [Fine-Grained Zero-Shot Learning with DNA as Side Information](https://mlsanity.com/paper/2109.14133/) (2021)
- [Hybrid Routing Transformer for Zero-Shot Learning](https://mlsanity.com/paper/2203.15310/) (2022)
- [Task Aligned Generative Meta-learning for Zero-shot Learning](https://mlsanity.com/paper/2103.02185/) (2021)
- [Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognition](https://mlsanity.com/paper/2108.04603/) (2021)
- [Learning Robust Visual-semantic Mapping for Zero-shot Learning](https://mlsanity.com/paper/2104.05668/) (2021)
- [Domain Adaptation Meets Zero-Shot Learning: An Annotation-Efficient Approach to Multi-Modality Medical Image Segmentation](https://mlsanity.com/paper/2203.10332/) (2022)
- [Rectification-based Knowledge Retention for Continual Learning](https://mlsanity.com/paper/2103.16597/) (2021)
- [Aligning Visual Prototypes with BERT Embeddings for Few-Shot Learning](https://mlsanity.com/paper/2105.10195/) (2021)
- [Non-generative Generalized Zero-shot Learning via Task-correlated Disentanglement and Controllable Samples Synthesis](https://mlsanity.com/paper/2203.05335/) (2022)
- [Zero-Shot Object Counting with Language-Vision Models](https://mlsanity.com/paper/2309.13097/) (2023)
- [Attribute-Modulated Generative Meta Learning for Zero-Shot Classification](https://mlsanity.com/paper/2104.10857/) (2021)

## Abstract (arXiv)

We propose a novel framework called Semantics-Preserving Adversarial Embedding Network (SP-AEN) for zero-shot visual recognition (ZSL), where test images and their classes are both unseen during training. SP-AEN aims to tackle the inherent problem --- semantic loss --- in the prevailing family of embedding-based ZSL, where some semantics would be discarded during training if they are non-discriminative for training classes, but could become critical for recognizing test classes. Specifically, SP-AEN prevents the semantic loss by introducing an independent visual-to-semantic space embedder which disentangles the semantic space into two subspaces for the two arguably conflicting objectives: classification and reconstruction. Through adversarial learning of the two subspaces, SP-AEN can transfer the semantics from the reconstructive subspace to the discriminative one, accomplishing the improved zero-shot recognition of unseen classes. Comparing with prior works, SP-AEN can not only improve classification but also generate photo-realistic images, demonstrating the effectiveness of semantic preservation. On four popular benchmarks: CUB, AWA, SUN and aPY, SP-AEN considerably outperforms other state-of-the-art methods by an absolute performance difference of 12.2%, 9.3%, 4.0%, and 3.6% in terms of harmonic mean values