REVIEW 6 cited by
BAM: Bottleneck Attention Module
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
BAM: Bottleneck Attention Module
read the original abstract
Recent advances in deep neural networks have been developed via architecture search for stronger representational power. In this work, we focus on the effect of attention in general deep neural networks. We propose a simple and effective attention module, named Bottleneck Attention Module (BAM), that can be integrated with any feed-forward convolutional neural networks. Our module infers an attention map along two separate pathways, channel and spatial. We place our module at each bottleneck of models where the downsampling of feature maps occurs. Our module constructs a hierarchical attention at bottlenecks with a number of parameters and it is trainable in an end-to-end manner jointly with any feed-forward models. We validate our BAM through extensive experiments on CIFAR-100, ImageNet-1K, VOC 2007 and MS COCO benchmarks. Our experiments show consistent improvement in classification and detection performances with various models, demonstrating the wide applicability of BAM. The code and models will be publicly available.
Forward citations
Cited by 6 Pith papers
-
Generalized Synthetic Image Detection with Enhanced RGB-Noise Representation Learning
RNSIDNet detects synthetic images by using CLIP RGB features to dynamically modulate Bayar-convolution noise residuals, trained with a hard-sample-aware contrastive loss.
-
ClinReadNet: A clinical reading-inspired network for low-dose abdominal CT image quality assessment
ClinReadNet introduces SOQN, (S)W-MTMSA, and HRPS loss to achieve SOTA no-reference IQA on LDCTIQAG2023 with PLCC 0.9507, SROCC 0.9554, KROCC 0.8629.
-
Attention-Based Segmentation of WMHs and Differentiation of Vascular vs. Demyelinating Lesions
Attention-augmented U-Nets segment multi-etiology WMHs on public FLAIR datasets; morphological features from the masks classify vascular versus demyelinating origin at accuracy close to ground-truth masks.
-
Hybrid Swin Attention Networks for Simultaneously Low-Dose PET and CT Denoising
HSANet uses Efficient Global Attention and hybrid upsampling in a Swin-based architecture to achieve better simultaneous denoising of low-dose PET/CT images than prior methods with a compact model.
-
Phase-shifted remote photoplethysmography for estimating heart rate and blood pressure from facial video
DRP-Net extracts phase-shifted rPPG signals from facial and acral regions for heart rate; BBP-Net uses their temporal and phase features plus a bounded sigmoid to estimate SBP/DBP, reporting MAEs of 1.78 BPM / 10.19 m...
-
Improved Reinforcement Learning through Imitation Learning Pretraining Towards Image-based Autonomous Driving
Imitation learning pretraining of a ResNet-34 DDPG agent improves performance on image-based autonomous driving in simulation over pure IL or pure RL.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.