CORTEXA
← Browse
arxivcs.CV2026-07-20

FlexiGrad: Adaptive Gradient Modulation for Hierarchical Fine-Grained Classification

Zilu Zhou, Dongliang Chang, Junhan Chen, Zhanyu Ma

Many fine-grained recognition tasks contain hierarchical labels such as order, family and species. Although this supervision should be beneficial, jointly optimising all levels often leads to unstable training because coarse and fine classifiers impose inconsistent gradients on the shared backbone. This hierarchical gradient conflict prevents the model from learning a coherent coarse-to-fine representation. In this paper, we propose FlexiGrad, a simple and parameter-free method that regulates gradient interactions during backpropagation. FlexiGrad removes only the harmful conflicting component when tasks disagree and reinforces the shared direction when they partially agree through a smooth hierarchy-aware weighting function. This produces stable optimisation and preserves both global structure and fine-grained discriminative cues. FlexiGrad integrates into existing architectures without modification while improves multi-granularity accuracy on CUB-200-2011, FGVC-Aircraft and Stanford Cars. The code will be available at PRIS-CV/FlexiGrad.

View free PDFSource page

Related papers

arxivcs.CVcs.AI2026-07-05

HCSU: A Dataset and Benchmark for Fine-Grained Historical Calligraphy Style Understanding

Yinsheng Yao, Yan Liu, Chen Ye

Automated fine-grained perception of calligraphy styles--a task vital to cultural heritage preservation--remains a critical challenge for Large Vision-Language Models (LVLMs), largely constrained by existing datasets that suffer from modal mixture and flattened labels. To bridge…

View free PDFSource page
arxivcs.CVcs.MM2026-07-10

MAC 2026: Advancing Micro-Action Analysis Towards Fine-Grained Understanding

Kun Li, Dan Guo, Jihao Gu, Pengyu Liu, Xiaobai Li, Haoyu Chen, et al.

Micro-Actions (MAs) are subtle and spontaneous human behaviors that provide important non-verbal cues in social interaction and affective communication. However, their short duration, weak motion patterns, and fine-grained semantic differences make them difficult to annotate, mod…

View free PDFSource page
arxivcs.CV2026-07-07

Structured-Condensed Prompt Tuning in Vision-Language Models for Fine-grained Image Recognition

Xinda Liu, Qinyu Zhang, Weiqing Min, Guohua Geng, Shuqiang Jiang

Fine-grained image recognition poses a significant challenge due to the substantial expertise and effort required for manual annotation. Vision-language models (VLMs) like CLIP provide a compelling zero-shot alternative, reducing reliance on extensive labeled data. However, their…

View free PDFSource page
arxivcs.CV2026-07-02

Multimodal Fusion for Fine-Grained Classification of Breast Fibroadenoma and Phyllodes Tumors

Chuxi Nan, Di Wu, Hongming Guo, Ning Cao, Xiaohui Zhu, Zhaoting Shi, et al.

Breast fibroadenoma (FA) and phyllodes tumor (PT) are fibroepithelial breast lesions with highly overlapping appearances on B-mode ultrasound, making benign and borderline PT prone to being misclassified as FA and complicating preoperative decision-making. Existing computer-aided…

View free PDFSource page