# FlexiGrad: Adaptive Gradient Modulation for Hierarchical Fine-Grained Classification

arXiv: https://arxiv.org/abs/2607.17563 · HTML: https://mlsanity.com/paper/2607.17563/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 32 references that are in the map.
- First posted on arXiv 20 Jul 2026.

## Builds on (most cited first, 18 of 18)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [Conflict-Averse Gradient Descent for Multi-task Learning](https://mlsanity.com/paper/2110.14048/) (2021)
- [Learning to Navigate for Fine-grained Classification](https://mlsanity.com/paper/1809.00287/) (2018)
- [Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches](https://mlsanity.com/paper/2003.03836/) (2020)
- [The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification](https://mlsanity.com/paper/2002.04264/) (2020)
- [CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generation](https://mlsanity.com/paper/2505.15145/) (2025)
- [Pareto Set Learning for Multi-Objective Reinforcement Learning](https://mlsanity.com/paper/2501.06773/) (2025)
- [Toward Generalizable Forgery Detection and Reasoning](https://mlsanity.com/paper/2503.21210/) (2025)
- [Hierarchical Cross-modal Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2507.14976/) (2025)
- [A Multi-task Supervised Compression Model for Split Computing](https://mlsanity.com/paper/2501.01420/) (2025)
- [Multimodal Conditional Information Bottleneck for Generalizable AI-Generated Image Detection](https://mlsanity.com/paper/2505.15217/) (2025)
- [IncreFA: Breaking the Static Wall of Generative Model Attribution](https://mlsanity.com/paper/2604.17736/) (2026)
- [Seeing as Experts Do: A Knowledge-Augmented Agent for Open-Set Fine-Grained Visual Understanding](https://mlsanity.com/paper/2603.03762/) (2026)
- [DetailVerifyBench: A Benchmark for Dense Hallucination Localization in Long Image Captions](https://mlsanity.com/paper/2604.05623/) (2026)
- [Cross-Hierarchical Bidirectional Consistency Learning for Fine-Grained Visual Classification](https://mlsanity.com/paper/2504.13608/) (2025)
- [Direct Routing Gradient (DRGrad): A Personalized Information Surgery for Multi-Task Learning (MTL) Recommendations](https://mlsanity.com/paper/2510.09643/) (2025)

## Abstract (arXiv)

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.