# Diversity-boosted Generalization-Specialization Balancing for Zero-shot Learning

arXiv: https://arxiv.org/abs/2201.01961 · HTML: https://mlsanity.com/paper/2201.01961/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 69 references that are in the map.
- First posted on arXiv 6 Jan 2022.

## Builds on (most cited first, 30 of 36)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Overcoming catastrophic forgetting with hard attention to the task](https://mlsanity.com/paper/1801.01423/) (2018)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [DER: Dynamically Expandable Representation for Class Incremental Learning](https://mlsanity.com/paper/2103.16788/) (2021)
- [Evaluation of Output Embeddings for Fine-Grained Image Classification](https://mlsanity.com/paper/1409.8403/) (2014)
- [f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning](https://mlsanity.com/paper/1903.10132/) (2019)
- [Attribute Prototype Network for Zero-Shot Learning](https://mlsanity.com/paper/2008.08290/) (2020)
- [Learning a Deep Embedding Model for Zero-Shot Learning](https://mlsanity.com/paper/1611.05088/) (2016)
- [An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild](https://mlsanity.com/paper/1605.04253/) (2016)
- [Meta-Transfer Learning for Zero-Shot Super-Resolution](https://mlsanity.com/paper/2002.12213/) (2020)
- [Multi-modal Cycle-consistent Generalized Zero-Shot Learning](https://mlsanity.com/paper/1808.00136/) (2018)
- [Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networks](https://mlsanity.com/paper/1712.01928/) (2017)
- [Zero-Shot Cross-Lingual Transfer with Meta Learning](https://mlsanity.com/paper/2003.02739/) (2020)
- [Transferable Contrastive Network for Generalized Zero-Shot Learning](https://mlsanity.com/paper/1908.05832/) (2019)
- [Semantic-Guided Multi-Attention Localization for Zero-Shot Learning](https://mlsanity.com/paper/1903.00502/) (2019)
- [Ridge Regression, Hubness, and Zero-Shot Learning](https://mlsanity.com/paper/1507.00825/) (2015)
- [A Simple Exponential Family Framework for Zero-Shot Learning](https://mlsanity.com/paper/1707.08040/) (2017)
- [TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning](https://mlsanity.com/paper/1904.05967/) (2019)
- [A Novel Perspective to Zero-shot Learning: Towards an Alignment of Manifold Structures via Semantic Feature Expansion](https://mlsanity.com/paper/2004.14795/) (2020)
- [Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning](https://mlsanity.com/paper/1605.08151/) (2016)
- [Locality and compositionality in zero-shot learning](https://mlsanity.com/paper/1912.12179/) (2019)
- [Attribute Propagation Network for Graph Zero-shot Learning](https://mlsanity.com/paper/2009.11816/) (2020)
- [Rethinking Generative Zero-Shot Learning: An Ensemble Learning Perspective for Recognising Visual Patches](https://mlsanity.com/paper/2007.13314/) (2020)
- [Zero-Shot Task Transfer](https://mlsanity.com/paper/1903.01092/) (2019)
- [Progressive Ensemble Networks for Zero-Shot Recognition](https://mlsanity.com/paper/1805.07473/) (2018)
- [Zero-Shot Learning via Class-Conditioned Deep Generative Models](https://mlsanity.com/paper/1711.05820/) (2017)
- [Generalized Zero-Shot Recognition based on Visually Semantic Embedding](https://mlsanity.com/paper/1811.07993/) (2018)
- [Task Aligned Generative Meta-learning for Zero-shot Learning](https://mlsanity.com/paper/2103.02185/) (2021)
- [Isometric Propagation Network for Generalized Zero-shot Learning](https://mlsanity.com/paper/2102.02038/) (2021)

## Built on by (most cited first, 4 of 4)

- [Distilled Reverse Attention Network for Open-world Compositional Zero-Shot Learning](https://mlsanity.com/paper/2303.00404/) (2023)
- [Visual-Semantic Graph Matching Net for Zero-Shot Learning](https://mlsanity.com/paper/2411.11351/) (2024)
- [Few-Shot Inspired Generative Zero-Shot Learning](https://mlsanity.com/paper/2507.01026/) (2025)
- [Dynamic Visual-semantic Alignment for Zero-shot Learning with Ambiguous Labels](https://mlsanity.com/paper/2604.17710/) (2026)

## Abstract (arXiv)

Zero-Shot Learning (ZSL) aims to transfer classification capability from seen to unseen classes. Recent methods have proved that generalization and specialization are two essential abilities to achieve good performance in ZSL. However, focusing on only one of the abilities may result in models that are either too general with degraded classification ability or too specialized to generalize to unseen classes. In this paper, we propose an end-to-end network, termed as BGSNet, which equips and balances generalization and specialization abilities at the instance and dataset level. Specifically, BGSNet consists of two branches: the Generalization Network (GNet), which applies episodic meta-learning to learn generalized knowledge, and the Balanced Specialization Network (BSNet), which adopts multiple attentive extractors to extract discriminative features and achieve instance-level balance. A novel self-adjusted diversity loss is designed to optimize BSNet with redundancy reduced and diversity boosted. We further propose a differentiable dataset-level balance and update the weights in a linear annealing schedule to simulate network pruning and thus obtain the optimal structure for BSNet with dataset-level balance achieved. Experiments on four benchmark datasets demonstrate our model's effectiveness. Sufficient component ablations prove the necessity of integrating and balancing generalization and specialization abilities.