Built independently by an author, for readers. Read the story and support ChapterPal

keyword

Deformable CNN

A deformable CNN, or deformable convolutional neural network, is a deep learning architecture designed to improve visual recognition by dynamically adjusting its sampling locations to accommodate geometric transformations. Unlike conventional convolutional neural networks that sample feature maps using rigid, regular grids, a deformable CNN introduces learnable spatial offsets to standard convolutional and pooling operations. These offsets are predicted directly from the input features during training without additional supervision, allowing the receptive field to freely deform and align with the actual scale, pose, and boundary of non-rigid objects. By enabling adaptive spatial sampling, deformable CNNs enhance feature extraction for complex computer vision tasks such as object detection, instance segmentation, and pose estimation.

1 item

Receptive Field Block Net for Accurate and Fast Object Detection

Receptive Field Block Net for Accurate and Fast Object Detection

Songtao Liu, Di Huang, Yunhong Wang

OrganizationsAdvanced Innovation Center for Big Data and Brain ComputingBeihang University

Why you should read this

Introduces RFB Net, an object detector that incorporates biologically inspired receptive field structures into lightweight networks to match the accuracy of deep models at real-time speeds.

Current top-performing object detectors depend on deep CNN backbones, such as ResNet-101 and Inception, benefiting from their powerful feature representations but suffering from high computational costs. Conversely, some lightweight model based detectors fulfil real time processing, while their accuracies are often criticized. In this paper, we explore an alternative to build a fast and accurate detector by strengthening lightweight features using a hand-crafted mechanism. Inspired by the structure of Receptive Fields (RFs) in human visual systems, we propose a novel RF Block (RFB) module, which takes the relationship between the size and eccentricity of RFs into account, to enhance the feature discriminability and robustness. We further assemble RFB to the top of SSD, constructing the RFB Net detector. To evaluate its effectiveness, experiments are conducted on two major benchmarks and the results show that RFB Net is able to reach the performance of advanced very deep detectors while keeping the real-time speed. Code is available at this https URL.

Added

2026-09-24