# Bridging the Projection Gap: Overcoming Projection Bias Through Parameterized Distance Learning

arXiv: https://arxiv.org/abs/2309.01390 · HTML: https://mlsanity.com/paper/2309.01390/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 50 references that are in the map.
- First posted on arXiv 4 Sep 2023.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [Feature Generating Networks for Zero-Shot Learning](https://mlsanity.com/paper/1712.00981/) (2017)
- [Zero-Shot Learning Through Cross-Modal Transfer](https://mlsanity.com/paper/1301.3666/) (2013)
- [Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders](https://mlsanity.com/paper/1812.01784/) (2018)
- [Label-Embedding for Image Classification](https://mlsanity.com/paper/1503.08677/) (2015)
- [f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning](https://mlsanity.com/paper/1903.10132/) (2019)
- [DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis](https://mlsanity.com/paper/2008.05865/) (2020)
- [Learning a Deep Embedding Model for Zero-Shot Learning](https://mlsanity.com/paper/1611.05088/) (2016)
- [Synthesized Classifiers for Zero-Shot Learning](https://mlsanity.com/paper/1603.00550/) (2016)
- [Contrastive Embedding for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2103.16173/) (2021)
- [Leveraging the Invariant Side of Generative Zero-Shot Learning](https://mlsanity.com/paper/1904.04092/) (2019)
- [Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networks](https://mlsanity.com/paper/1712.01928/) (2017)
- [Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot Learning](https://mlsanity.com/paper/2007.09549/) (2020)
- [HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning](https://mlsanity.com/paper/2109.15163/) (2021)
- [Transductive Multi-view Zero-Shot Learning](https://mlsanity.com/paper/1501.04560/) (2015)
- [Transductive Zero-Shot Learning for 3D Point Cloud Classification](https://mlsanity.com/paper/1912.07161/) (2019)
- [Zero-shot Generative Model Adaptation via Image-specific Prompt Learning](https://mlsanity.com/paper/2304.03119/) (2023)
- [Zero-Shot Learning and its Applications from Autonomous Vehicles to COVID-19 Diagnosis: A Review](https://mlsanity.com/paper/2004.14143/) (2020)
- [Towards Effective Deep Embedding for Zero-Shot Learning](https://mlsanity.com/paper/1808.10075/) (2018)
- [Synthetic Sample Selection for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2304.02846/) (2023)
- [Disentangling Semantic-to-visual Confusion for Zero-shot Learning](https://mlsanity.com/paper/2106.08605/) (2021)
- [Rebalanced Zero-shot Learning](https://mlsanity.com/paper/2210.07031/) (2022)
- [Zero-shot Learning via Shared-Reconstruction-Graph Pursuit](https://mlsanity.com/paper/1711.07302/) (2017)

## Built on by (most cited first, 3 of 3)

- [ZeroDiff: Solidified Visual-Semantic Correlation in Zero-Shot Learning](https://mlsanity.com/paper/2406.02929/) (2024)
- [ZeroDiff++: Substantial Unseen Visual-semantic Correlation in Zero-shot Learning](https://mlsanity.com/paper/2602.12401/) (2026)
- [CAST: Closed-form Analytic Semantic Transfer for Zero-Shot Classifier Extension](https://mlsanity.com/paper/2608.13751/) (2026)

## Abstract (arXiv)

Generalized zero-shot learning (GZSL) aims to recognize samples from both seen and unseen classes using only seen class samples for training. However, GZSL methods are prone to bias towards seen classes during inference due to the projection function being learned from seen classes. Most methods focus on learning an accurate projection, but bias in the projection is inevitable. We address this projection bias by proposing to learn a parameterized Mahalanobis distance metric for robust inference. Our key insight is that the distance computation during inference is critical, even with a biased projection. We make two main contributions - (1) We extend the VAEGAN (Variational Autoencoder & Generative Adversarial Networks) architecture with two branches to separately output the projection of samples from seen and unseen classes, enabling more robust distance learning. (2) We introduce a novel loss function to optimize the Mahalanobis distance representation and reduce projection bias. Extensive experiments on four datasets show that our approach outperforms state-of-the-art GZSL techniques with improvements of up to 3.5 % on the harmonic mean metric.