GenView++: Unifying Adaptive Generative Augmentation and Quality-Driven Supervision for Contrastive Representation Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Xiaojie, Wang, Bei, Liu, Wei, Wu, Jianlong, Yu, Yue, Nie, Liqiang, Zhang, Min
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918296328077312
author Li, Xiaojie
Wang, Bei
Liu, Wei
Wu, Jianlong
Yu, Yue
Nie, Liqiang
Zhang, Min
author_facet Li, Xiaojie
Wang, Bei
Liu, Wei
Wu, Jianlong
Yu, Yue
Nie, Liqiang
Zhang, Min
contents The success of contrastive learning depends on the construction and utilization of high-quality positive pairs. However, current methods face critical limitations on two fronts: on the construction side, both handcrafted and generative augmentations often suffer from limited diversity and risk semantic corruption; on the learning side, the absence of a quality assessment mechanism leads to suboptimal supervision where all pairs are treated equally. To tackle these challenges, we propose GenView++, a unified framework that addresses both fronts by introducing two synergistic innovations. To improve pair construction, GenView++ introduces a multi-source adaptive view generation mechanism to synthesize diverse yet semantically coherent views by dynamically modulating generative parameters across image-conditioned, text-conditioned, and image-text-conditioned strategies. Second, a quality-driven contrastive learning mechanism assesses each pair's semantic alignment and diversity to dynamically reweight their training contribution, prioritizing high-quality pairs while suppressing redundant or misaligned pairs. Extensive experiments demonstrate the effectiveness of GenView++ across both vision and vision-language tasks. For vision representation learning, it improves MoCov2 by +2.5% on ImageNet linear classification. For vision-language learning, it raises the average zero-shot classification accuracy by +12.31% over CLIP and +5.31% over SLIP across ten datasets, and further improves Flickr30k text retrieval R@5 by +3.2%.
format Preprint
id arxiv_https___arxiv_org_abs_2509_23770
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GenView++: Unifying Adaptive Generative Augmentation and Quality-Driven Supervision for Contrastive Representation Learning
Li, Xiaojie
Wang, Bei
Liu, Wei
Wu, Jianlong
Yu, Yue
Nie, Liqiang
Zhang, Min
Computer Vision and Pattern Recognition
The success of contrastive learning depends on the construction and utilization of high-quality positive pairs. However, current methods face critical limitations on two fronts: on the construction side, both handcrafted and generative augmentations often suffer from limited diversity and risk semantic corruption; on the learning side, the absence of a quality assessment mechanism leads to suboptimal supervision where all pairs are treated equally. To tackle these challenges, we propose GenView++, a unified framework that addresses both fronts by introducing two synergistic innovations. To improve pair construction, GenView++ introduces a multi-source adaptive view generation mechanism to synthesize diverse yet semantically coherent views by dynamically modulating generative parameters across image-conditioned, text-conditioned, and image-text-conditioned strategies. Second, a quality-driven contrastive learning mechanism assesses each pair's semantic alignment and diversity to dynamically reweight their training contribution, prioritizing high-quality pairs while suppressing redundant or misaligned pairs. Extensive experiments demonstrate the effectiveness of GenView++ across both vision and vision-language tasks. For vision representation learning, it improves MoCov2 by +2.5% on ImageNet linear classification. For vision-language learning, it raises the average zero-shot classification accuracy by +12.31% over CLIP and +5.31% over SLIP across ten datasets, and further improves Flickr30k text retrieval R@5 by +3.2%.
title GenView++: Unifying Adaptive Generative Augmentation and Quality-Driven Supervision for Contrastive Representation Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.23770