1 code implementation • 17 Jun 2021 • Mark Weber, Huiyu Wang, Siyuan Qiao, Jun Xie, Maxwell D. Collins, Yukun Zhu, Liangzhe Yuan, Dahun Kim, Qihang Yu, Daniel Cremers, Laura Leal-Taixe, Alan L. Yuille, Florian Schroff, Hartwig Adam, Liang-Chieh Chen
DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a state-of-the-art and easy-to-use TensorFlow codebase for general dense pixel prediction problems in computer vision.
We view this work as a notable step towards building a simple procedure to harness unlabeled video sequences and extra images to surpass state-of-the-art performance on core computer vision tasks.
In this work, we introduce Panoptic-DeepLab, a simple, strong, and fast system for panoptic segmentation, aiming to establish a solid baseline for bottom-up methods that can achieve comparable performance of two-stage methods while yielding fast inference speed.
Ranked #3 on Instance Segmentation on Cityscapes test (using extra training data)
The proposed SegSort further produces an interpretable result, as each choice of label can be easily understood from the retrieved nearest segments.
Ranked #8 on Unsupervised Semantic Segmentation on PASCAL VOC 2012 val (using extra training data)
The semantic segmentation branch is the same as the typical design of any semantic segmentation model (e. g., DeepLab), while the instance segmentation branch is class-agnostic, involving a simple instance center regression.
We present a single-shot, bottom-up approach for whole image parsing.
Ranked #32 on Panoptic Segmentation on Cityscapes val
Recent progress has demonstrated that such meta-learning methods may exceed scalable human-invented architectures on image classification tasks.
Ranked #1 on Human Part Segmentation on PASCAL-Person-Part
Visual relationships provide higher-level information of objects and their relations in an image â this enables a semantic understanding of the scene and helps downstream applications.
We present a new Frank-Wolfe (FW) type algorithm that is applicable to minimization problems with a nonsmooth convex objective.
This paper proposes a deep learning architecture based on Residual Network that dynamically adjusts the number of executed layers for the regions of the image.
There is a great deal of interest in using large scale brain imaging studies to understand how brain connectivity evolves over time for an individual and how it varies over different levels/quantiles of cognitive function.
Eigenvalue problems are ubiquitous in computer vision, covering a very broad spectrum of applications ranging from estimation problems in multi-view geometry to image segmentation.
In this paper, we present an algorithm for optimizing the split functions at all levels of the tree jointly with the leaf parameters, based on a global objective.
We develop a convex-concave upper bound on the classification loss for a one-level decision tree, and optimize the bound by stochastic gradient descent at each internal node of the tree.
Linear regression is a parametric model which is ubiquitous in scientific analysis.
We study the problem of interactive segmentation and contour completion for multiple objects.