# Hardness Sampling for Self-Training Based Transductive Zero-Shot Learning

arXiv: https://arxiv.org/abs/2106.00264 · HTML: https://mlsanity.com/paper/2106.00264/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 55 references that are in the map.
- First posted on arXiv 1 Jun 2021.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [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)
- [Evaluation of Output Embeddings for Fine-Grained Image Classification](https://mlsanity.com/paper/1409.8403/) (2014)
- [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)
- [Learning a Deep Embedding Model for Zero-Shot Learning](https://mlsanity.com/paper/1611.05088/) (2016)
- [Semantic Autoencoder for Zero-Shot Learning](https://mlsanity.com/paper/1704.08345/) (2017)
- [Latent Embeddings for Zero-shot Classification](https://mlsanity.com/paper/1603.08895/) (2016)
- [A Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts](https://mlsanity.com/paper/1712.01381/) (2017)
- [Leveraging the Invariant Side of Generative Zero-Shot Learning](https://mlsanity.com/paper/1904.04092/) (2019)
- [Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2003.13261/) (2020)
- [Episode-based Prototype Generating Network for Zero-Shot Learning](https://mlsanity.com/paper/1909.03360/) (2019)
- [Transferable Contrastive Network for Generalized Zero-Shot Learning](https://mlsanity.com/paper/1908.05832/) (2019)
- [Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot Learning](https://mlsanity.com/paper/2007.09549/) (2020)
- [Generative Dual Adversarial Network for Generalized Zero-shot Learning](https://mlsanity.com/paper/1811.04857/) (2018)
- [Semantic-Guided Multi-Attention Localization for Zero-Shot Learning](https://mlsanity.com/paper/1903.00502/) (2019)
- [Generalized Zero-Shot Learning Via Over-Complete Distribution](https://mlsanity.com/paper/2004.00666/) (2020)
- [Transductive Multi-view Zero-Shot Learning](https://mlsanity.com/paper/1501.04560/) (2015)
- [Transductive Unbiased Embedding for Zero-Shot Learning](https://mlsanity.com/paper/1803.11320/) (2018)
- [Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective](https://mlsanity.com/paper/1909.05995/) (2019)
- [A Simple Exponential Family Framework for Zero-Shot Learning](https://mlsanity.com/paper/1707.08040/) (2017)
- [Learning Feature-to-Feature Translator by Alternating Back-Propagation for Generative Zero-Shot Learning](https://mlsanity.com/paper/1904.10056/) (2019)
- [Transductive Zero-Shot Learning with Visual Structure Constraint](https://mlsanity.com/paper/1901.01570/) (2019)
- [A Boundary Based Out-of-Distribution Classifier for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2008.04872/) (2020)
- [Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning](https://mlsanity.com/paper/1605.08151/) (2016)
- [Attribute Propagation Network for Graph Zero-shot Learning](https://mlsanity.com/paper/2009.11816/) (2020)

## Built on by (most cited first, 12 of 12)

- [Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuning](https://mlsanity.com/paper/2306.01669/) (2023)
- [Language-Level Semantics Conditioned 3D Point Cloud Segmentation](https://mlsanity.com/paper/2107.00430/) (2021)
- [Bi-directional Distribution Alignment for Transductive Zero-Shot Learning](https://mlsanity.com/paper/2303.08698/) (2023)
- [A Survey on Open-Set Image Recognition](https://mlsanity.com/paper/2312.15571/) (2023)
- [An Iterative Co-Training Transductive Framework for Zero Shot Learning](https://mlsanity.com/paper/2203.16041/) (2022)
- [Evolutionary Generalized Zero-Shot Learning](https://mlsanity.com/paper/2211.13174/) (2022)
- [HardBoost: Boosting Zero-Shot Learning with Hard Classes](https://mlsanity.com/paper/2201.05479/) (2022)
- [Generate, Transduct, Adapt: Iterative Transduction with VLMs](https://mlsanity.com/paper/2501.06031/) (2025)
- [Learning Compositional Representations for Effective Low-Shot Generalization](https://mlsanity.com/paper/2204.08090/) (2022)
- [Optimizing Three Critical Factors for Practical and Effective OOD Detection Fine-Tuning](https://mlsanity.com/paper/2308.01030/) (2023)
- [Heuristic Self-Paced Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions](https://mlsanity.com/paper/2603.24322/) (2026)
- [Orthogonal-Coding-Based Feature Generation for Transductive Open-Set Recognition via Dual-Space Consistent Sampling](https://mlsanity.com/paper/2207.05957/) (2022)

## Abstract (arXiv)

Transductive zero-shot learning (T-ZSL) which could alleviate the domain shift problem in existing ZSL works, has received much attention recently. However, an open problem in T-ZSL: how to effectively make use of unseen-class samples for training, still remains. Addressing this problem, we first empirically analyze the roles of unseen-class samples with different degrees of hardness in the training process based on the uneven prediction phenomenon found in many ZSL methods, resulting in three observations. Then, we propose two hardness sampling approaches for selecting a subset of diverse and hard samples from a given unseen-class dataset according to these observations. The first one identifies the samples based on the class-level frequency of the model predictions while the second enhances the former by normalizing the class frequency via an approximate class prior estimated by an explored prior estimation algorithm. Finally, we design a new Self-Training framework with Hardness Sampling for T-ZSL, called STHS, where an arbitrary inductive ZSL method could be seamlessly embedded and it is iteratively trained with unseen-class samples selected by the hardness sampling approach. We introduce two typical ZSL methods into the STHS framework and extensive experiments demonstrate that the derived T-ZSL methods outperform many state-of-the-art methods on three public benchmarks. Besides, we note that the unseen-class dataset is separately used for training in some existing transductive generalized ZSL (T-GZSL) methods, which is not strict for a GZSL task. Hence, we suggest a more strict T-GZSL data setting and establish a competitive baseline on this setting by introducing the proposed STHS framework to T-GZSL.