|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
In this work, we revisit the global average pooling layer proposed in , and shed light on how it explicitly enables the convolutional neural network to have remarkable localization ability despite being trained on image-level labels.
#2 best model for Weakly-Supervised Object Localization on Tiny ImageNet
Accurate detection of objects in 3D point clouds is a central problem in many applications, such as autonomous navigation, housekeeping robots, and augmented/virtual reality.
Convolutional networks for image classification progressively reduce resolution until the image is represented by tiny feature maps in which the spatial structure of the scene is no longer discernible.
Over the last decade, Convolutional Neural Network (CNN) models have been highly successful in solving complex vision problems.
Based on deep snake, we develop a two-stage pipeline for instance segmentation: initial contour proposal and contour deformation, which can handle errors in object localization.
Large-scale object detection datasets (e. g., MS-COCO) try to define the ground truth bounding boxes as clear as possible.
#22 best model for Object Detection on PASCAL VOC 2007
Regional dropout strategies have been proposed to enhance the performance of convolutional neural network classifiers.
SOTA for Image Captioning on COCO
To address (a), we design the reverse connection, which enables the network to detect objects on multi-levels of CNNs.