Scale-Aware Trident Networks for Object Detection

In this paper, we present a comprehensive review of the imbalance problems in object detection. To analyze the problems in a systematic manner, we introduce two taxonomies; one for the problems and the other for the proposed solutions. Following the taxonomy for the problems, we discuss each problem in depth and present a unifying yet critical perspective on the solutions in the literature. In addition, we identify major open issues regarding the existing imbalance problems as well as imbalance problems that have not been discussed before. Moreover, in order to keep our review up to date, we provide an accompanying webpage which categorizes papers addressing imbalance problems, according to our problem-based taxonomy. Researchers can track newer studies on this webpage available at: https://github.com/kemaloksuz/ObjectDetectionImbalance.

show abstract

“…Each T corresponds to a trident feature map (e.g. Scale Aware Trident Network [70]). making predictions.…”

Section: Methods Based On Feature Pyramidsmentioning

confidence: 99%

“…Scale Aware Trident Networks [70] combine the advantages of the methods based on feature pyramids and image pyramids. In particular, image pyramid based methods are expected to perform better than feature pyramid based methods, since feature pyramid based methods are efficient approximations of such methods.…”

Section: Methods Combining Image and Feature Pyramidsmentioning

confidence: 99%

Imbalance Problems in Object Detection: A Review

Öksüz

Cam

Kalkan

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

412

171

View full text Add to dashboard Cite

show abstract

“…Another way to create features of multiple scales is to use dilated convolutions [24], which is adopted by TridentNet [25] to generate multi-scale features in several parallel branches with different dilation rates. Scale awareness is obtained by training the branches separately with objects within certain scale ranges.…”

Section: Introductionmentioning

confidence: 99%

Scale- and Context-Aware Convolutional Non-Intrusive Load Monitoring

Chen

Zhang

Wang

et al. 2020

IEEE Trans. Power Syst.

105

View full text Add to dashboard Cite

Non-intrusive load monitoring addresses the challenging task of decomposing the aggregate signal of a household's electricity consumption into appliance-level data without installing dedicated meters. By detecting load malfunction and recommending energy reduction programs, cost-effective nonintrusive load monitoring provides intelligent demand-side management for utilities and end users. In this paper, we boost the accuracy of energy disaggregation with a novel neural network structure named scale-and context-aware network, which exploits multi-scale features and contextual information. Specifically, we develop a multi-branch architecture with multiple receptive field sizes and branch-wise gates that connect the branches in the sub-networks. We build a self-attention module to facilitate the integration of global context, and we incorporate an adversarial loss and on-state augmentation to further improve the model's performance. Extensive simulation results tested on open datasets corroborate the merits of the proposed approach, which significantly outperforms state-of-the-art methods.

show abstract

“…The MSConv layer is inspired by ROI-pooling [1], and is closely related to Trident Network [5]. Trident Network uses shared convolutional kernels of different dilation rates to capture scale-invariant patterns.…”

Section: Introductionmentioning

confidence: 99%

Multi-Instance Multi-Scale CNN for Medical Image Classification

Liu

Sui

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Deep learning for medical image classification faces three major challenges: 1) the number of annotated medical images for training are usually small; 2) regions of interest (ROIs) are relatively small with unclear boundaries in the whole medical images, and may appear in arbitrary positions across the x, y (and also z in 3D images) dimensions. However often only labels of the whole images are annotated, and localized ROIs are unavailable; and 3) ROIs in medical images often appear in varying sizes (scales). We approach these three challenges with a Multi-Instance Multi-Scale (MIMS) CNN: 1) We propose a multi-scale convolutional layer, which extracts patterns of different receptive fields with a shared set of convolutional kernels, so that scale-invariant patterns are captured by this compact set of kernels. As this layer contains only a small number of parameters, training on small datasets becomes feasible; 2) We propose a "top-k pooling" to aggregate the feature maps in varying scales from multiple spatial dimensions, allowing the model to be trained using weak annotations within the multiple instance learning (MIL) framework. Our method is shown to perform well on three classification tasks involving two 3D and two 2D medical image datasets.

show abstract

Scale-Aware Trident Networks for Object Detection

Cited by 896 publications

References 39 publications

Imbalance Problems in Object Detection: A Review

Imbalance Problems in Object Detection: A Review

Scale- and Context-Aware Convolutional Non-Intrusive Load Monitoring

Multi-Instance Multi-Scale CNN for Medical Image Classification

Contact Info

Product

Resources

About