paper-with-me

Papers

CAMAL: Context-Aware Multi-layer Attention framework for Lightweight Environment Invariant Visual Place Recognition

2019-09-18 · Ahmad Khaliq, Shoaib Ehsan, Michael Milford, Klaus McDonald-Maier

In the last few years, Deep Convolutional Neural Networks (D-CNNs) have shown state-of-the-art (SOTA) performance for Visual Place Recognition (VPR), a pivotal component of long-term intelligent robotic vision (vision-aware localization and navigation systems). The prestigious generalization power of D-CNNs gained upon training on large scale places datasets and learned persistent image regions which are found to be robust for specific place recognition under changing conditions and camera viewpoints. However, against the computation and power intensive D-CNNs based VPR algorithms that are employed to determine the approximate location of resource-constrained mobile robots, lightweight VPR techniques are preferred. This paper presents a computation- and energy-efficient CAMAL framework that captures place-specific multi-layer convolutional attentions efficient for environment invariant-VPR. At 4x lesser power consumption, evaluating the proposed VPR framework on challenging benchmark place recognition datasets reveal better and comparable Area under Precision-Recall (AUC-PR) curves with approximately 4x improved image retrieval performance over the contemporary VPR methodologies.

📄 PDF Abstract BibTeX arXiv:1909.08153

Code (0)

등록된 구현이 없습니다.

Tasks

Image RetrievalRetrievalVisual Place Recognition

Similar Papers 제목 키워드 기반

CAMAL: Improving Attention Alignment and Faithfulness with Segmentation Masks

2026-05-08 · Rajdeep Singh Hundal, Yan Xiao, Jin Song Dong, Manuel Rigger arxiv

Many vision datasets now provide segmentation masks in addition to annotated images to support a wide range of tasks. In this work, we propose Class Activation Map Attention Learning (CAMAL), an efficient and scalable me…

Reinforcement Learning

CAMAL: Optimizing LSM-trees via Active Learning

2024-09-23 · Weiping Yu, Siqiang Luo, Zihao Yu, Gao Cong

We use machine learning to optimize LSM-tree structure, aiming to reduce the cost of processing various read/write operations. We introduce a new approach Camal, which boasts the following features: (1) ML-Aided: Camal i…

Active Learning

Few Labels are all you need: A Weakly Supervised Framework for Appliance Localization in Smart-Meter Series

2025-06-06 · Adrien Petralia, Paul Boniol, Philippe Charpentier, Themis Palpanas

Improving smart grid system management is crucial in the fight against climate change, and enabling consumers to play an active role in this effort is a significant challenge for electricity suppliers. In this regard, mi…

AllNon-Intrusive Load Monitoring

Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference

2026-04-08 · Quantong Qiu, Zhiyi Hong, Yi Yang, Haitian Wang 외 arxiv

The quadratic computational complexity of standard attention mechanisms presents a severe scalability bottleneck for LLMs in long-context scenarios. While hybrid attention mechanisms combining Full Attention (FA) and Spa…

Mathematical ReasoningInformation Retrieval

Hierarchical Classification of Financial Transactions Through Context-Fusion of Transformer-based Embeddings and Taxonomy-aware Attention Layer

2023-12-12 · Antonio J. G. Busson, Rafael Rocha, Rennan Gaio, Rafael Miceli 외

This work proposes the Two-headed DragoNet, a Transformer-based model for hierarchical multi-label classification of financial transactions. Our model is based on a stack of Transformers encoder layers that generate cont…

Hierarchical Multi-label ClassificationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATION