Self-attention mechanisms are commonly included in a convolutional neural networks to achieve an improved efficiency performance balance. However, adding self-attention mechanisms adds additional hyperparameters to tu...
详细信息
In this paper, an unsupervised defect inspection method based on anomaly detection is proposed to inspect various kinds of surface defects in the field of industrial production. This method consists of two modules: (i...
详细信息
Lossy image compression strategies allow for more efficient storage and transmission of data by encoding data to a reduced form. This is essential enable training with larger datasets on less storage-equipped environm...
详细信息
ISBN:
(数字)9781665487399
ISBN:
(纸本)9781665487399
Lossy image compression strategies allow for more efficient storage and transmission of data by encoding data to a reduced form. This is essential enable training with larger datasets on less storage-equipped environments. However, such compression can cause severe decline in performance of deep Convolution Neural Network (CNN) architectures even when mild compression is applied and the resulting compressed imagery is visually identical. In this work, we apply the lossy JPEG compression method with six discrete levels of increasing compression {95, 75, 50, 15, 10, 5} to infrared band (thermal) imagery. Our study quantitatively evaluates the affect that increasing levels of lossy compression has upon the performance of characteristically diverse object detection architectures (Cascade-RCNN, FSAF and Deformable DETR) with respect to varying sizes of objects present in the dataset. When training and evaluating on uncompressed data as a baseline, we achieve maximal mean Average Precision (mAP) of 0.823 with Cascade R-CNN across the FLIR dataset, outperforming prior work. The impact of the lossy compression is more extreme at higher compression levels (15, 10, 5) across all three CNN architectures. However, re-training models on lossy compressed imagery notably ameliorated performances for all three CNN models with an average increment of similar to 76% (at higher compression level 5). Additionally, we demonstrate the relative sensitivity of differing object areas {tiny, small, medium, large} with respect to the compression level. We show that tiny and small objects are more sensitive to compression than medium and large objects. Overall, Cascade R-CNN attains the maximal mAP across most of the object area categories.
Modern agricultural applications rely more and more on deep learning solutions. However, training well-performing deep networks requires a large amount of annotated data that may not be available and in the case of 3D...
详细信息
Dynamic light fields provide a richer, more realistic 3D representation of a moving scene. However, this leads to higher data rates since excess storage and transmission requirements are needed. We propose a novel app...
详细信息
We introduce S2VS, a video similarity learning approach with self-supervision. Self-Supervised Learning (SSL) is typically used to train deep models on a proxy task so as to have strong transferability on target tasks...
详细信息
Image fusion is a significant problem in many fields including digital photography, computational imaging and remote sensing, to name but a few. Recently, deep learning has emerged as an important tool for image fusio...
详细信息
Over the past few years, high-definition videos and images in 720p (HD), 1080p (FHD), and 4K (UHD) resolution have become standard. While higher resolutions offer improved visual quality for users, they pose a signifi...
详细信息
Recent developments in Artificial Intelligence techniques have enabled their successful application across a spectrum of commercial and industrial settings. However, these techniques require large volumes of data to b...
详细信息
Class-incremental learning is one of the most important settings for the study of Continual Learning, as it closely resembles real-world application scenarios. With constrained memory sizes, catastrophic forgetting ar...
详细信息
暂无评论