CBAM: Convolutional Block Attention Module

Woo, Sanghyun; Park, Jongchan; Lee, Joon-Young; Kweon, In So

doi:10.1007/978-3-030-01234-2_1

Cited by 13,087 publications

(8,906 citation statements)

References 38 publications

Supporting

Mentioning

7,033

Contrasting

Unclassified

Order By: Relevance

“…Zhang et al embedded edgeattention representations to guide the process of segmentation on optic disc, retinal vessel, and lung [40]. Attention modules incorporated in deep learning architectures have also shown their strengths in many computer vision based tasks [41], [42]. Schlemper et al encapsulated attention gates into a 3D U-Net architecture for abdominal organ segmentation [43].…”

Section: Previous Workmentioning

confidence: 99%

Bi-Directional Dermoscopic Feature Learning and Multi-Scale Consistent Decision Fusion for Skin Lesion Segmentation

Wang

Jiang

Ding

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Accurate segmentation of skin lesion from dermoscopic images is a crucial part of computer-aided diagnosis of melanoma. It is challenging due to the fact that dermoscopic images from different patients have non-negligible lesion variation, which causes difficulties in anatomical structure learning and consistent skin lesion delineation. In this paper, we propose a novel bi-directional dermoscopic feature learning (biDFL) framework to model the complex correlation between skin lesions and their informative context. By controlling feature information passing through two complementary directions, a substantially rich and discriminative feature representation is achieved. Specifically, we place biDFL module on the top of a CNN network to enhance high-level parsing performance. Furthermore, we propose a multi-scale consistent decision fusion (mCDF) that is capable of selectively focusing on the informative decisions generated from multiple classification layers. By analysis of the consistency of the decision at each position, mCDF automatically adjusts the reliability of decisions and thus allows a more insightful skin lesion delineation. The comprehensive experimental results show the effectiveness of the proposed method on skin lesion segmentation, achieving state-of-the-art performance consistently on two publicly available dermoscopic image databases.Index Terms-Skin lesion segmentation, dermoscopic images, bi-directional dermoscopic feature learning, multi-scale consistent decision fusion.

show abstract

Section: Previous Workmentioning

confidence: 99%

Bi-Directional Dermoscopic Feature Learning and Multi-Scale Consistent Decision Fusion for Skin Lesion Segmentation

Wang

Jiang

Ding

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…4, TIGN consists of three types of blocks, namely, attention, PN, and output blocks. Motivated by recent successful works on attention [43], [44], we introduce two attention blocks to focus on important appearance and motion features, individually. For each attention block, we adopt CBAM [44] and change the spatial attention to temporal attention.…”

Section: A Temporal Interval Generationmentioning

confidence: 99%

SRG: Snippet Relatedness-Based Temporal Action Proposal Generator

Eun

Lee

Moon

et al. 2020

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Recent temporal action proposal generation approaches have suggested integrating segment-and snippet scorebased methodologies to produce proposals with high recall and accurate boundaries. In this paper, different from such a hybrid strategy, we focus on the potential of the snippet score-based approach. Specifically, we propose a new snippet score-based method, named Snippet Relatedness-based Generator (SRG), with a novel concept of "snippet relatedness". Snippet relatedness represents which snippets are related to a specific action instance. To effectively learn this snippet relatedness, we present "pyramid non-local operations" for locally and globally capturing long-range dependencies among snippets. By employing these components, SRG first produces a 2D relatedness score map that enables the generation of various temporal intervals reliably covering most action instances with high overlap. Then, SRG evaluates the action confidence scores of these temporal intervals and refines their boundaries to obtain temporal action proposals. On THUMOS-14 and ActivityNet-1.3 datasets, SRG outperforms state-of-the-art methods for temporal action proposal generation. Furthermore, compared to competing proposal generators, SRG leads to significant improvements in temporal action detection.

show abstract

“…Indirect Supervision. We can also train the Selective Module in an unsupervised fashion [13,14]. Predicting detection results on each spatial location of specified feature maps is a key characteristic of one-stage detectors [1,12], and different gradients flow at different locations during training.…”

Section: Direct Supervision or Indirect Supervisionmentioning

confidence: 99%

“…Though DCN [12] uses the deformable convolution with spatial domain offsets to focus on the specific objects instead of the adjacent background, dispensable activations on the background locations will be also calculated. And many works [13,14,15] only use attention mechanisms to enhance certain features, which violates the original intention to decrease the size of search spaces.…”

Section: Introductionmentioning

confidence: 99%

Selective Convolutional Network: An Efficient Object Detector with Ignoring Background

Ling

Qin

Zhang

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

It is well known that attention mechanisms can effectively improve the performance of many CNNs including object detectors. Instead of refining feature maps prevalently, we reduce the prohibitive computational complexity by a novel attempt at attention. Therefore, we introduce an efficient object detector called Selective Convolutional Network (SCN), which selectively calculates only on the locations that contain meaningful and conducive information. The basic idea is to exclude the insignificant background areas, which effectively reduces the computational cost especially during the feature extraction. To solve it, we design an elaborate structure with negligible overheads to guide the network where to look next. It's end-to-end trainable and easy-embedding. Without additional segmentation datasets, we explores two different train strategies including direct supervision and indirect supervision. Extensive experiments assess the performance on PASCAL VOC2007 and MS COCO detection datasets. Results show that SSD and Pelee integrated with our method averagely reduce the calculations in a range of 1/5 and 1/3 with slight loss of accuracy, demonstrating the feasibility of SCN.

show abstract

CBAM: Convolutional Block Attention Module

Cited by 13,087 publications

References 38 publications

Bi-Directional Dermoscopic Feature Learning and Multi-Scale Consistent Decision Fusion for Skin Lesion Segmentation

Bi-Directional Dermoscopic Feature Learning and Multi-Scale Consistent Decision Fusion for Skin Lesion Segmentation

SRG: Snippet Relatedness-Based Temporal Action Proposal Generator

Selective Convolutional Network: An Efficient Object Detector with Ignoring Background

Contact Info

Product

Resources

About