Dual-level Progressive Hardness-Aware Reweighting for Cross-View Geo-Localization

2025-10-31 · Guozheng Zheng, Jian Guan, Mingjie Xie, Xuanjia Zhao, Congyi Fan, Shiheng Zhang, Pengming Feng arxiv

Cross-view geo-localization (CVGL) between drone and satellite imagery remains challenging due to severe viewpoint gaps and the presence of hard negatives, which are visually similar but geographically mismatched samples. Existing mining or reweighting strategies often use static weighting, which is sensitive to distribution shifts and prone to overemphasizing difficult samples too early, leading to noisy gradients and unstable convergence. In this paper, we present a Dual-level Progressive Hardness-aware Reweighting (DPHR) strategy. At the sample level, a Ratio-based Difficulty-Aware (RDA) module evaluates relative difficulty and assigns fine-grained weights to negatives. At the batch level, a Progressive Adaptive Loss Weighting (PALW) mechanism exploits a training-progress signal to attenuate noisy gradients during early optimization and progressively enhance hard-negative mining as training matures. Experiments on the University-1652 and SUES-200 benchmarks demonstrate the effectiveness and robustness of the proposed DPHR, achieving consistent improvements over state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:2510.27181

Code (0)

등록된 구현이 없습니다.

Mitigating Individual Skin Tone Bias in Skin Lesion Classification through Distribution-Aware Reweighting

2025-12-09 · Kuniko Paxton, Zeinab Dehghani, Koorosh Aslansefat, Dhavalkumar Thakker 외 arxiv

Skin color has historically been a focal point of discrimination, yet fairness research in machine learning for medical imaging often relies on coarse subgroup categories, overlooking individual-level variations. Such gr…

Skin Lesion Classification Density Estimation

DARS: Dual-Level Credit Assignment RL with Structured Reasoning for Instruction-Based Image Editing

2026-08-20 · Haoxiang Cao, Jiajiong Cao, Xuanpu Zhang, Changqian Yu 외 arxiv

Instruction-based image editing uses a planner-renderer pipeline: a vision-language model (VLM) first converts the instruction into an edit plan, and a diffusion model then executes that plan. Training such systems with …

Reinforcement Learning Image Editing

Adaptive Hardness-driven Augmentation and Alignment Strategies for Multi-Source Domain Adaptations

2025-01-02 · Yang Yuxiang, Zeng Xinyi, Zeng Pinxian, Zu Chen 외

Multi-source Domain Adaptation (MDA) aims to transfer knowledge from multiple labeled source domains to an unlabeled target domain. Nevertheless, traditional methods primarily focus on achieving inter-domain alignment th…

Data Augmentation Domain Adaptation

Disentangling Hardness from Noise: An Uncertainty-Driven Model-Agnostic Framework for Long-Tailed Remote Sensing Classification

2026-01-01 · Chi Ding, Junxiao Xue, Xinyi Yin, Shi Chen 외 arxiv

Long-Tailed distributions are pervasive in remote sensing due to the inherently imbalanced occurrence of grounded objects. However, a critical challenge remains largely overlooked, i.e., disentangling hard tail data samp…

NightLab: A Dual-level Architecture with Hardness Detection for Segmentation at Night

2022-04-12 · CVPR 2022 1 · Xueqing Deng, Peng Wang, Xiaochen Lian, Shawn Newsam

The semantic segmentation of nighttime scenes is a challenging problem that is key to impactful applications like self-driving cars. Yet, it has received little attention compared to its daytime counterpart. In this pape…

Segmentation Self-Driving Cars Semantic Segmentation