-
Objectness-Aware One-Shot Semantic Segmentation
While deep convolutional neural networks have led to great progress in i...
read it
-
RGB-D Object Detection and Semantic Segmentation for Autonomous Manipulation in Clutter
Autonomous robotic manipulation in clutter is challenging. A large varie...
read it
-
SegICP: Integrated Deep Semantic Segmentation and Pose Estimation
Recent robotic manipulation competitions have highlighted that sophistic...
read it
-
SegSort: Segmentation by Discriminative Sorting of Segments
Almost all existing deep learning approaches for semantic segmentation t...
read it
-
Learning Pixel-wise Labeling from the Internet without Human Interaction
Deep learning stands at the forefront in many computer vision tasks. How...
read it
-
Semi Supervised Deep Quick Instance Detection and Segmentation
In this paper, we present a semi supervised deep quick learning framewor...
read it
-
Stillleben: Realistic Scene Synthesis for Deep Learning in Robotics
Training data is the key ingredient for deep learning approaches, but di...
read it
Semantic Segmentation from Limited Training Data
We present our approach for robotic perception in cluttered scenes that led to winning the recent Amazon Robotics Challenge (ARC) 2017. Next to small objects with shiny and transparent surfaces, the biggest challenge of the 2017 competition was the introduction of unseen categories. In contrast to traditional approaches which require large collections of annotated data and many hours of training, the task here was to obtain a robust perception pipeline with only few minutes of data acquisition and training time. To that end, we present two strategies that we explored. One is a deep metric learning approach that works in three separate steps: semantic-agnostic boundary detection, patch classification and pixel-wise voting. The other is a fully-supervised semantic segmentation approach with efficient dataset collection. We conduct an extensive analysis of the two methods on our ARC 2017 dataset. Interestingly, only few examples of each class are sufficient to fine-tune even very deep convolutional neural networks for this specific task.
READ FULL TEXT
Comments
There are no comments yet.