Pith. sign in

REVIEW 9 cited by

CBAM: Convolutional Block 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

arxiv 1807.06521 v2 pith:M6GY76FX submitted 2018-07-17 cs.CV

CBAM: Convolutional Block Attention Module

classification cs.CV
keywords attentioncbammoduleconvolutionaldetectionfeaturealongblock
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We propose Convolutional Block Attention Module (CBAM), a simple yet effective attention module for feed-forward convolutional neural networks. Given an intermediate feature map, our module sequentially infers attention maps along two separate dimensions, channel and spatial, then the attention maps are multiplied to the input feature map for adaptive feature refinement. Because CBAM is a lightweight and general module, it can be integrated into any CNN architectures seamlessly with negligible overheads and is end-to-end trainable along with base CNNs. We validate our CBAM through extensive experiments on ImageNet-1K, MS~COCO detection, and VOC~2007 detection datasets. Our experiments show consistent improvements in classification and detection performances with various models, demonstrating the wide applicability of CBAM. The code and models will be publicly available.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Architecture-Aware Explanation Auditing for Industrial Visual Inspection

    cs.LG 2026-05 conditional novelty 7.0

    Explanation faithfulness for deep classifiers on wafer maps is highest when the explainer matches the model's native readout structure, with ViT-Tiny plus Attention Rollout achieving lower Deletion AUC than mismatched...

  2. Architecture-Aware Explanation Auditing for Industrial Visual Inspection

    cs.LG 2026-05 unverdicted novelty 7.0

    An audit protocol on wafer maps finds that ViT-Tiny with Attention Rollout achieves better deletion faithfulness than other models and explainers, with readout structure as the key factor and RISE outperforming native...

  3. MB-Loc: Multi-planar Bird's-eye-view Localization in outdoor LiDAR scenes

    cs.CV 2026-06 unverdicted novelty 6.0

    MB-Loc projects LiDAR point clouds into multi-planar BEV images, applies 2D CNNs with a KL-regularized latent bottleneck and 3D augmentations, and reports real-time state-of-the-art localization accuracy on the NCLT dataset.

  4. Architecture-Aware Explanation Auditing for Industrial Visual Inspection

    cs.LG 2026-05 unverdicted novelty 6.0

    The paper proposes an architecture-aware explanation audit protocol demonstrating that perturbation-based faithfulness is bounded by structural compatibility between explainer and model readout rather than architectur...

  5. Restore3D: Breathing Life into Broken Objects with Shape and Texture Restoration

    cs.CV 2026-07 unverdicted novelty 5.0

    Restore3D restores shape and texture of broken 3D objects via multi-view image refinement with a Mask Self-Perceiver and coarse-to-fine mesh reconstruction, outperforming baselines on synthetic and real benchmarks.

  6. Characterizing Orbital Parameters of Hot Subdwarf Binaries with Multiple Spectroscopic Surveys

    astro-ph.SR 2026-06 unverdicted novelty 4.0

    Multi-survey analysis of 157 hot subdwarf binaries yields 23 orbital solutions (11 new) whose mass-period distribution matches post-common-envelope systems, supporting a common-envelope origin.

  7. A Wasserstein GAN-based climate scenario generator for risk management and insurance: the case of soil subsidence

    cs.LG 2026-04 unverdicted novelty 4.0

    A conditional Wasserstein GAN generates plausible future SWI drought trajectories for French insurance risk management under climate change.

  8. Attention mechanisms and transfer learning for robust peach leaf damage classification under domain shift

    cs.CV 2026-06 unverdicted novelty 3.0

    EfficientNetB5 with CBAM reaches 93.3% accuracy on a 1,366-image peach leaf damage dataset and EfficientNetB3 with CBAM reaches 93% macro F1 after transfer to a 180-image local domain.

  9. Improved Reinforcement Learning through Imitation Learning Pretraining Towards Image-based Autonomous Driving

    cs.LG 2019-07 unverdicted novelty 3.0

    Imitation learning pretraining of a ResNet-34 DDPG agent improves performance on image-based autonomous driving in simulation over pure IL or pure RL.