FlexiGrad: Adaptive Gradient Modulation for Hierarchical Fine-Grained Classification
2026-07-20 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address a problem in tasks where objects are labeled at different detail levels, like family and species. They found that training a model on all levels at once can confuse it because coarse and fine details give mixed signals. To fix this, they created FlexiGrad, a method that adjusts how learning signals combine, keeping helpful parts and removing conflicts. This makes training smoother and improves accuracy on tasks like recognizing bird species and car models without changing existing models.
fine-grained recognitionhierarchical labelsgradient conflictbackpropagationmulti-task learningcoarse-to-fine representationoptimization stabilityCUB-200-2011FGVC-AircraftStanford Cars
Authors
Zilu Zhou, Dongliang Chang, Junhan Chen, Zhanyu Ma
Abstract
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.