Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

MS COCO minival2014

MS COCO minival2014 is a standardized validation subset consisting of 5,000 images selected from the original validation split of the 2014 Microsoft Common Objects in Context dataset. The original 2014 release contained more than 40,000 validation images, which was unnecessarily large for routine local validation during model development, while annotations for the official test set were kept private for benchmark server evaluation. To facilitate rapid evaluation and expand available training data, researchers created minival2014 by reserving 5,000 images exclusively for evaluation and combining the remaining approximately 35,000 validation images with the official training set to form the trainval35k training set. This partition became a standard benchmark across computer vision tasks, including object detection, instance segmentation, and image captioning, and it directly served as the official validation set in subsequent releases of the dataset.

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