Salvato in:
Dettagli Bibliografici
Autori principali: Shohag, Md Shakil Ahamed, Wu, Q. M. Jonathan, Pourpanah, Farhad
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2507.01026
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915368303329280
author Shohag, Md Shakil Ahamed
Wu, Q. M. Jonathan
Pourpanah, Farhad
author_facet Shohag, Md Shakil Ahamed
Wu, Q. M. Jonathan
Pourpanah, Farhad
contents Generative zero-shot learning (ZSL) methods typically synthesize visual features for unseen classes using predefined semantic attributes, followed by training a fully supervised classification model. While effective, these methods require substantial computational resources and extensive synthetic data, thereby relaxing the original ZSL assumptions. In this paper, we propose FSIGenZ, a few-shot-inspired generative ZSL framework that reduces reliance on large-scale feature synthesis. Our key insight is that class-level attributes exhibit instance-level variability, i.e., some attributes may be absent or partially visible, yet conventional ZSL methods treat them as uniformly present. To address this, we introduce Model-Specific Attribute Scoring (MSAS), which dynamically re-scores class attributes based on model-specific optimization to approximate instance-level variability without access to unseen data. We further estimate group-level prototypes as clusters of instances based on MSAS-adjusted attribute scores, which serve as representative synthetic features for each unseen class. To mitigate the resulting data imbalance, we introduce a Dual-Purpose Semantic Regularization (DPSR) strategy while training a semantic-aware contrastive classifier (SCC) using these prototypes. Experiments on SUN, AwA2, and CUB benchmarks demonstrate that FSIGenZ achieves competitive performance using far fewer synthetic features.
format Preprint
id arxiv_https___arxiv_org_abs_2507_01026
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Few-Shot Inspired Generative Zero-Shot Learning
Shohag, Md Shakil Ahamed
Wu, Q. M. Jonathan
Pourpanah, Farhad
Machine Learning
Generative zero-shot learning (ZSL) methods typically synthesize visual features for unseen classes using predefined semantic attributes, followed by training a fully supervised classification model. While effective, these methods require substantial computational resources and extensive synthetic data, thereby relaxing the original ZSL assumptions. In this paper, we propose FSIGenZ, a few-shot-inspired generative ZSL framework that reduces reliance on large-scale feature synthesis. Our key insight is that class-level attributes exhibit instance-level variability, i.e., some attributes may be absent or partially visible, yet conventional ZSL methods treat them as uniformly present. To address this, we introduce Model-Specific Attribute Scoring (MSAS), which dynamically re-scores class attributes based on model-specific optimization to approximate instance-level variability without access to unseen data. We further estimate group-level prototypes as clusters of instances based on MSAS-adjusted attribute scores, which serve as representative synthetic features for each unseen class. To mitigate the resulting data imbalance, we introduce a Dual-Purpose Semantic Regularization (DPSR) strategy while training a semantic-aware contrastive classifier (SCC) using these prototypes. Experiments on SUN, AwA2, and CUB benchmarks demonstrate that FSIGenZ achieves competitive performance using far fewer synthetic features.
title Few-Shot Inspired Generative Zero-Shot Learning
topic Machine Learning
url https://arxiv.org/abs/2507.01026