paper-with-me

홈 › Papers

Beyond Augmentation: Empowering Model Robustness under Extreme Capture Environments

2024-07-18 · Yunpeng Gong, Yongjie Hou, Chuangliang Zhang, Min Jiang

Person Re-identification (re-ID) in computer vision aims to recognize and track individuals across different cameras. While previous research has mainly focused on challenges like pose variations and lighting changes, the impact of extreme capture conditions is often not adequately addressed. These extreme conditions, including varied lighting, camera styles, angles, and image distortions, can significantly affect data distribution and re-ID accuracy. Current research typically improves model generalization under normal shooting conditions through data augmentation techniques such as adjusting brightness and contrast. However, these methods pay less attention to the robustness of models under extreme shooting conditions. To tackle this, we propose a multi-mode synchronization learning (MMSL) strategy . This approach involves dividing images into grids, randomly selecting grid blocks, and applying data augmentation methods like contrast and brightness adjustments. This process introduces diverse transformations without altering the original image structure, helping the model adapt to extreme variations. This method improves the model's generalization under extreme conditions and enables learning diverse features, thus better addressing the challenges in re-ID. Extensive experiments on a simulated test set under extreme conditions have demonstrated the effectiveness of our method. This approach is crucial for enhancing model robustness and adaptability in real-world scenarios, supporting the future development of person re-identification technology.

📄 PDF Abstract BibTeX arXiv:2407.13640

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationPerson Re-Identification

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

TDNetGen: Empowering Complex Network Resilience Prediction with Generative Augmentation of Topology and Dynamics

2024-08-19 · Chang Liu, Jingtao Ding, Yiwen Song, Yong Li

Predicting the resilience of complex networks, which represents the ability to retain fundamental functionality amidst external perturbations or internal failures, plays a critical role in understanding and improving rea…

Data AugmentationPrediction

Empowering Large Language Models for Textual Data Augmentation

2024-04-26 · Yichuan Li, Kaize Ding, Jianling Wang, Kyumin Lee

With the capabilities of understanding and executing natural language instructions, Large language models (LLMs) can potentially act as a powerful tool for textual data augmentation. However, the quality of augmented dat…

Data AugmentationDiversityFew-Shot Learning

Understanding Data Augmentation from a Robustness Perspective

2023-09-07 · Zhendong Liu, Jie Zhang, Qiangqiang He, Chongjun Wang

In the realm of visual recognition, data augmentation stands out as a pivotal technique to amplify model robustness. Yet, a considerable number of existing methodologies lean heavily on heuristic foundations, rendering t…

Data Augmentation

BeyondRPC: A Contrastive and Augmentation-Driven Framework for Robust Point Cloud Understanding

2025-06-15 · International Journal of Intelligent Engineering and Systems 2025 6 · Oddy Virgantara Putra, Hanugra Aulia Sidharta, Diah Risqiwati, Moch. Iskandar Riansyah 외

Robust perception of 3D point clouds remains a significant challenge in real-world environments where sensor data is often corrupted. While recent models and augmentation strategies have improved robustness individually,…

Point Cloud ClassificationRepresentation Learning

Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learning

2023-03-02 · Rundong Luo, Yifei Wang, Yisen Wang

Recent works have shown that self-supervised learning can achieve remarkable robustness when integrated with adversarial training (AT). However, the robustness gap between supervised AT (sup-AT) and self-supervised AT (s…

Contrastive LearningData AugmentationSelf-Supervised Learning