A statistical approach to bias in zero-shot learning: the lens of handwriting recognition

• URL: http://arxiv.org/abs/2609.10084v1
• Date: Wed, 09 Sep 2026 12:06:49 GMT
• Title: A statistical approach to bias in zero-shot learning: the lens of handwriting recognition
• Abstract summary: Generalized zero-shot learning (GZSL) has emerged as an important paradigm for visual recognition systems.<n>We propose a statistical approach to rectifying this bias, which views any classical GZSL feature learner as a black box mechanism.<n>We achieve relative accuracy improvements of over 20% in the classification of unseen words compared to established techniques.
• Score: 5.701736491817928
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generalized zero-shot learning (GZSL) has emerged as an important paradigm for visual recognition systems that must generalize to classes that were not observed during training. Traditional GZSL techniques are limited by their applicability to a relatively small number of such unseen classes, scalability beyond which is challenging due to its well-known misclassification bias towards classes observed during training. In this work, we investigate the GZSL paradigm through the lens of zero-shot handwritten word recognition over extremely large vocabularies. We propose a statistical approach to rectifying this bias, which views any classical GZSL feature learner as a black box mechanism whose intrinsic bias in identifying the training status (seen vs. unseen) of a typical data point we aim to correct, similar to an out of distribution inferential problem. Our method leverages a simple two-stage hierarchical architecture, combining a classical GZSL blackbox in the first stage and an ensemble of lightweight Monte Carlo bias-correctors in the second. Once debiased, the classification of test data is undertaken only restricted to its predicted training status via well-founded statistical methods (eg nearest neighbour, logistic regression and random forests). We achieve relative accuracy improvements of over 20% in the classification of unseen words compared to established techniques. A key outcome is that word recognition over large scale vocabularies is amenable to a much lower dimensional representation (~15 dimensions). Our approach is underpinned by mathematical analysis that captures the essence of the statistical approach to bias correction. Our approach to bias rectification can be combined in a turn-key fashion with any classical GZSL learner as a blackbox, thereby suggesting a wide scope of applicability of this method for a wide variety of GZSL implementations in different domains.

Related papers

• Interpretable Zero-Shot Learning with Locally-Aligned Vision-Language Model [56.573203512455706]
  Large-scale vision-language models (VLMs) have achieved remarkable success in zero-shot learning (ZSL) by leveraging large-scale visual-text pair datasets.<n>One approach to address this issue is to develop interpretable models by integrating language.<n>We propose LaZSL, a locally-aligned vision-language model for interpretable ZSL.
  arXiv  Detail & Related papers  (2025-06-30T13:14:46Z)
• Probably Approximately Precision and Recall Learning [60.00180898830079]
  A key challenge in machine learning is the prevalence of one-sided feedback.<n>We introduce a Probably Approximately Correct (PAC) framework in which hypotheses are set functions that map each input to a set of labels.<n>We develop new algorithms that learn from positive data alone, achieving optimal sample complexity in the realizable case.
  arXiv  Detail & Related papers  (2024-11-20T04:21:07Z)
• Semi-Supervised Learning in the Few-Shot Zero-Shot Scenario [14.916971861796384]
  Semi-Supervised Learning (SSL) is a framework that utilizes both labeled and unlabeled data to enhance model performance. We propose a general approach to augment existing SSL methods, enabling them to handle situations where certain classes are missing. Our experimental results reveal significant improvements in accuracy when compared to state-of-the-art SSL, open-set SSL, and open-world SSL methods.
  arXiv  Detail & Related papers  (2023-08-27T14:25:07Z)
• Bi-directional Distribution Alignment for Transductive Zero-Shot Learning [48.80413182126543]
  We propose a novel zero-shot learning model (TZSL) called Bi-VAEGAN. It largely improves the shift by a strengthened distribution alignment between the visual and auxiliary spaces. In benchmark evaluation, Bi-VAEGAN achieves the new state of the arts under both the standard and generalized TZSL settings.
  arXiv  Detail & Related papers  (2023-03-15T15:32:59Z)
• Rebalanced Zero-shot Learning [18.52913434532522]
  Zero-shot learning (ZSL) aims to identify unseen classes with zero samples during training. We introduce an imbalanced learning framework into ZSL. We then propose a re-weighted loss termed Re-balanced Mean-Squared Error (ReMSE)
  arXiv  Detail & Related papers  (2022-10-13T13:43:40Z)
• Federated Zero-Shot Learning for Visual Recognition [55.65879596326147]
  We propose a novel Federated Zero-Shot Learning FedZSL framework. FedZSL learns a central model from the decentralized data residing on edge devices. The effectiveness and robustness of FedZSL are demonstrated by extensive experiments conducted on three zero-shot benchmark datasets.
  arXiv  Detail & Related papers  (2022-09-05T14:49:34Z)
• Unseen Classes at a Later Time? No Problem [17.254973125515402]
  We propose a new Online-CGZSL setting which is more practical and flexible. We introduce a unified feature-generative framework for CGZSL that leverages bi-directional incremental alignment to dynamically adapt to addition of new classes, with or without labeled data, that arrive over time in any of these CGZSL settings.
  arXiv  Detail & Related papers  (2022-03-30T17:52:16Z)
• A Gating Model for Bias Calibration in Generalized Zero-shot Learning [18.32369721322249]
  Generalized zero-shot learning (GZSL) aims at training a model that can generalize to unseen class data by only using auxiliary information. One of the main challenges in GZSL is a biased model prediction toward seen classes caused by overfitting on only available seen class data during training. We propose a two-stream autoencoder-based gating model for GZSL.
  arXiv  Detail & Related papers  (2022-03-08T16:41:06Z)
• OntoZSL: Ontology-enhanced Zero-shot Learning [19.87808305218359]
  Key to implementing Zero-shot Learning (ZSL) is to leverage the prior knowledge of classes which builds the semantic relationship between classes. In this paper, we explore richer and more competitive prior knowledge to model the inter-class relationship for ZSL. To address the data imbalance between seen classes and unseen classes, we developed a generative ZSL framework with Generative Adversarial Networks (GANs)
  arXiv  Detail & Related papers  (2021-02-15T04:39:58Z)
• Information Bottleneck Constrained Latent Bidirectional Embedding for Zero-Shot Learning [59.58381904522967]
  We propose a novel embedding based generative model with a tight visual-semantic coupling constraint. We learn a unified latent space that calibrates the embedded parametric distributions of both visual and semantic spaces. Our method can be easily extended to transductive ZSL setting by generating labels for unseen images.
  arXiv  Detail & Related papers  (2020-09-16T03:54:12Z)
• Boosting Few-Shot Learning With Adaptive Margin Loss [109.03665126222619]
  This paper proposes an adaptive margin principle to improve the generalization ability of metric-based meta-learning approaches for few-shot learning problems. Extensive experiments demonstrate that the proposed method can boost the performance of current metric-based meta-learning approaches.
  arXiv  Detail & Related papers  (2020-05-28T07:58:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.