However, this option traditionally hurts the detection performance much.
Separating 3D point clouds into individual instances is an important task for 3D vision.
In particular, Panoptic FCN encodes each object instance or stuff category with the proposed kernel generator and produces the prediction by convolving the high-resolution feature directly.
We introduce a new image segmentation task, termed Entity Segmentation (ES) with the aim to segment all visual entities in an image without considering semantic category labels.
Single image super-resolution (SISR) deals with a fundamental problem of upsampling a low-resolution (LR) image to its high-resolution (HR) version.
We propose Scale-aware AutoAug to learn data augmentation policies for object detection.
We consider the single image super-resolution (SISR) problem, where a high-resolution (HR) image is generated based on a low-resolution (LR) input.
Motivated by these findings, we propose a temporal multi-correspondence aggregation strategy to leverage similar patches across frames, and a cross-scale nonlocal-correspondence aggregation scheme to explore self-similarity of images across scales.
We propose a Dynamic Scale Training paradigm (abbreviated as DST) to mitigate scale variation challenge in object detection.
In this paper, we explore the mask representation in instance segmentation with Point-of-Interest (PoI) features.
We propose the network structure to reason invisible parts via a new multi-task framework with Multi-View Coding (MVC), which combines information in various recognition levels.
The way that information propagates in neural networks is of great importance.
Ranked #3 on Object Detection on iSAID
In general, the robustness and precision of recognition is one of the key problems for object recognition models.