从不平衡数据中学习是一项具有挑战性的任务。在进行不平衡数据训练时，标准分类算法的性能往往差。需要通过修改数据分布或重新设计基础分类算法以实现理想的性能来采用一些特殊的策略。现实世界数据集中不平衡的流行率导致为班级不平衡问题创造了多种策略。但是，并非所有策略在不同的失衡情况下都有用或提供良好的性能。处理不平衡的数据有许多方法，但是尚未进行此类技术的功效或这些技术之间的实验比较。在这项研究中，我们对26种流行抽样技术进行了全面分析，以了解它们在处理不平衡数据方面的有效性。在50个数据集上进行了严格的实验，具有不同程度的不平衡，以彻底研究这些技术的性能。已经提出了对技术的优势和局限性的详细讨论，以及如何克服此类局限性。我们确定了影响采样策略的一些关键因素，并提供有关如何为特定应用选择合适的采样技术的建议。

类不平衡是分类任务中经常发生的情况。从不平衡数据中学习提出了一个重大挑战，这在该领域引起了很多研究。使用采样技术进行数据预处理是处理数据中存在的不平衡的标准方法。由于标准分类算法在不平衡数据上的性能不佳，因此在培训之前，数据集需要足够平衡。这可以通过过度采样少数族裔级别或对多数级别的采样来实现。在这项研究中，已经提出了一种新型的混合采样算法。为了克服采样技术的局限性，同时确保保留采样数据集的质量，已经开发了一个复杂的框架来正确结合三种不同的采样技术。首先应用邻里清洁规则以减少失衡。然后从策略上与SMOTE算法策略性地采样，以在数据集中获得最佳平衡。该提出的混合方法学称为“ smote-rus-nc”，已与其他最先进的采样技术进行了比较。该策略进一步合并到集合学习框架中，以获得更健壮的分类算法，称为“ SRN-BRF”。对26个不平衡数据集进行了严格的实验，并具有不同程度的失衡。在几乎所有数据集中，提出的两种算法在许多情况下都超过了现有的采样策略，其差额很大。尤其是在流行抽样技术完全失败的高度不平衡数据集中，他们实现了无与伦比的性能。获得的优越结果证明了所提出的模型的功效及其在不平衡域中具有强大采样算法的潜力。

This paper presents our solutions for the MediaEval 2022 task on DisasterMM. The task is composed of two subtasks, namely (i) Relevance Classification of Twitter Posts (RCTP), and (ii) Location Extraction from Twitter Texts (LETT). The RCTP subtask aims at differentiating flood-related and non-relevant social posts while LETT is a Named Entity Recognition (NER) task and aims at the extraction of location information from the text. For RCTP, we proposed four different solutions based on BERT, RoBERTa, Distil BERT, and ALBERT obtaining an F1-score of 0.7934, 0.7970, 0.7613, and 0.7924, respectively. For LETT, we used three models namely BERT, RoBERTa, and Distil BERTA obtaining an F1-score of 0.6256, 0.6744, and 0.6723, respectively.

Automatic medical image classification is a very important field where the use of AI has the potential to have a real social impact. However, there are still many challenges that act as obstacles to making practically effective solutions. One of those is the fact that most of the medical imaging datasets have a class imbalance problem. This leads to the fact that existing AI techniques, particularly neural network-based deep-learning methodologies, often perform poorly in such scenarios. Thus this makes this area an interesting and active research focus for researchers. In this study, we propose a novel loss function to train neural network models to mitigate this critical issue in this important field. Through rigorous experiments on three independently collected datasets of three different medical imaging domains, we empirically show that our proposed loss function consistently performs well with an improvement between 2%-10% macro f1 when compared to the baseline models. We hope that our work will precipitate new research toward a more generalized approach to medical image classification.

Conventional cameras capture image irradiance on a sensor and convert it to RGB images using an image signal processor (ISP). The images can then be used for photography or visual computing tasks in a variety of applications, such as public safety surveillance and autonomous driving. One can argue that since RAW images contain all the captured information, the conversion of RAW to RGB using an ISP is not necessary for visual computing. In this paper, we propose a novel $\rho$-Vision framework to perform high-level semantic understanding and low-level compression using RAW images without the ISP subsystem used for decades. Considering the scarcity of available RAW image datasets, we first develop an unpaired CycleR2R network based on unsupervised CycleGAN to train modular unrolled ISP and inverse ISP (invISP) models using unpaired RAW and RGB images. We can then flexibly generate simulated RAW images (simRAW) using any existing RGB image dataset and finetune different models originally trained for the RGB domain to process real-world camera RAW images. We demonstrate object detection and image compression capabilities in RAW-domain using RAW-domain YOLOv3 and RAW image compressor (RIC) on snapshots from various cameras. Quantitative results reveal that RAW-domain task inference provides better detection accuracy and compression compared to RGB-domain processing. Furthermore, the proposed \r{ho}-Vision generalizes across various camera sensors and different task-specific models. Additional advantages of the proposed $\rho$-Vision that eliminates the ISP are the potential reductions in computations and processing times.

Deep learning models require an enormous amount of data for training. However, recently there is a shift in machine learning from model-centric to data-centric approaches. In data-centric approaches, the focus is to refine and improve the quality of the data to improve the learning performance of the models rather than redesigning model architectures. In this paper, we propose CLIP i.e., Curriculum Learning with Iterative data Pruning. CLIP combines two data-centric approaches i.e., curriculum learning and dataset pruning to improve the model learning accuracy and convergence speed. The proposed scheme applies loss-aware dataset pruning to iteratively remove the least significant samples and progressively reduces the size of the effective dataset in the curriculum learning training. Extensive experiments performed on crowd density estimation models validate the notion behind combining the two approaches by reducing the convergence time and improving generalization. To our knowledge, the idea of data pruning as an embedded process in curriculum learning is novel.

Density estimation is one of the most widely used methods for crowd counting in which a deep learning model learns from head-annotated crowd images to estimate crowd density in unseen images. Typically, the learning performance of the model is highly impacted by the accuracy of the annotations and inaccurate annotations may lead to localization and counting errors during prediction. A significant amount of works exist on crowd counting using perfectly labelled datasets but none of these explore the impact of annotation errors on the model accuracy. In this paper, we investigate the impact of imperfect labels (both noisy and missing labels) on crowd counting accuracy. We propose a system that automatically generates imperfect labels using a deep learning model (called annotator) which are then used to train a new crowd counting model (target model). Our analysis on two crowd counting models and two benchmark datasets shows that the proposed scheme achieves accuracy closer to that of the model trained with perfect labels showing the robustness of crowd models to annotation errors.

The rapid outbreak of COVID-19 pandemic invoked scientists and researchers to prepare the world for future disasters. During the pandemic, global authorities on healthcare urged the importance of disinfection of objects and surfaces. To implement efficient and safe disinfection services during the pandemic, robots have been utilized for indoor assets. In this paper, we envision the use of drones for disinfection of outdoor assets in hospitals and other facilities. Such heterogeneous assets may have different service demands (e.g., service time, quantity of the disinfectant material etc.), whereas drones have typically limited capacity (i.e., travel time, disinfectant carrying capacity). To serve all the facility assets in an efficient manner, the drone to assets allocation and drone travel routes must be optimized. In this paper, we formulate the capacitated vehicle routing problem (CVRP) to find optimal route for each drone such that the total service time is minimized, while simultaneously the drones meet the demands of each asset allocated to it. The problem is solved using mixed integer programming (MIP). As CVRP is an NP-hard problem, we propose a lightweight heuristic to achieve sub-optimal performance while reducing the time complexity in solving the problem involving a large number of assets.

The increase in the number of unmanned aerial vehicles a.k.a. drones pose several threats to public privacy, critical infrastructure and cyber security. Hence, detecting unauthorized drones is a significant problem which received attention in the last few years. In this paper, we present our experimental work on three drone detection methods (i.e., acoustic detection, radio frequency (RF) detection, and visual detection) to evaluate their efficacy in both indoor and outdoor environments. Owing to the limitations of these schemes, we present a novel encryption-based drone detection scheme that uses a two-stage verification of the drone's received signal strength indicator (RSSI) and the encryption key generated from the drone's position coordinates to reliably detect an unauthorized drone in the presence of authorized drones.

The compute-intensive nature of neural networks (NNs) limits their deployment in resource-constrained environments such as cell phones, drones, autonomous robots, etc. Hence, developing robust sparse models fit for safety-critical applications has been an issue of longstanding interest. Though adversarial training with model sparsification has been combined to attain the goal, conventional adversarial training approaches provide no formal guarantee that the models would be robust against any rogue samples in a restricted space around a benign sample. Recently proposed verified local robustness techniques provide such a guarantee. This is the first paper that combines the ideas from verified local robustness and dynamic sparse training to develop `SparseVLR'-- a novel framework to search verified locally robust sparse networks. Obtained sparse models exhibit accuracy and robustness comparable to their dense counterparts at sparsity as high as 99%. Furthermore, unlike most conventional sparsification techniques, SparseVLR does not require a pre-trained dense model, reducing the training time by 50%. We exhaustively investigated SparseVLR's efficacy and generalizability by evaluating various benchmark and application-specific datasets across several models.