REVIEW 3 cited by
Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks
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
abstract
The Convolutional Neural Networks (CNNs) generate the feature representation of complex objects by collecting hierarchical and different parts of semantic sub-features. These sub-features can usually be distributed in grouped form in the feature vector of each layer, representing various semantic entities. However, the activation of these sub-features is often spatially affected by similar patterns and noisy backgrounds, resulting in erroneous localization and identification. We propose a Spatial Group-wise Enhance (SGE) module that can adjust the importance of each sub-feature by generating an attention factor for each spatial location in each semantic group, so that every individual group can autonomously enhance its learnt expression and suppress possible noise. The attention factors are only guided by the similarities between the global and local feature descriptors inside each group, thus the design of SGE module is extremely lightweight with \emph{almost no extra parameters and calculations}. Despite being trained with only category supervisions, the SGE component is extremely effective in highlighting multiple active areas with various high-order semantics (such as the dog's eyes, nose, etc.). When integrated with popular CNN backbones, SGE can significantly boost the performance of image recognition tasks. Specifically, based on ResNet50 backbones, SGE achieves 1.2\% Top-1 accuracy improvement on the ImageNet benchmark and 1.0$\sim$2.0\% AP gain on the COCO benchmark across a wide range of detectors (Faster/Mask/Cascade RCNN and RetinaNet). Codes and pretrained models are available at https://github.com/implus/PytorchInsight.
Forward citations
Cited by 3 Pith papers
-
IPDiff: Diffusion-driven ORSI Salient Object Detection with Information Reconstruction and Multi-Prior Guidance
IPDiff formulates ORSI salient-object detection as multi-prior-guided conditional diffusion and iteratively optimizes saliency maps to new state-of-the-art scores on ORSSD, EORSSD and ORSI-4199.
-
MRC-DETR: An Adaptive Multi-Residual Coupled Transformer for Bare Board PCB Defect Detection
A modified RT-DETR architecture with two new feature modules achieves mAP 0.956 on a new 800-image bare PCB dataset, at 17M parameters and 48.2G FLOPs.
-
A Time-Enhanced Data Disentanglement Network for Traffic Flow Forecasting
TEDDN combines learned time embeddings, a sigmoid disentangle gate, channel attention, and residual dynamic graph convolution to forecast 60-minute traffic flow on four PEMS datasets.
Discussion (0). Sign in to comment.