AutoCorrect: Deep Inductive Alignment of Noisy Geometric Annotations

08/14/2019
by   Honglie Chen, et al.
0

We propose AutoCorrect, a method to automatically learn object-annotation alignments from a dataset with annotations affected by geometric noise. The method is based on a consistency loss that enables deep neural networks to be trained, given only noisy annotations as input, to correct the annotations. When some noise-free annotations are available, we show that the consistency loss reduces to a stricter self-supervised loss. We also show that the method can implicitly leverage object symmetries to reduce the ambiguity arising in correcting noisy annotations. When multiple object-annotation pairs are present in an image, we introduce a spatial memory map that allows the network to correct annotations sequentially, one at a time, while accounting for all other annotations in the image and corrections performed so far. Through ablation, we show the benefit of these contributions, demonstrating excellent results on geo-spatial imagery. Specifically, we show results using a new Railway tracks dataset as well as the public INRIA Buildings benchmarks, achieving new state-of-the-art results for the latter.

READ FULL TEXT

page 2

page 4

page 6

page 10

research
10/07/2021

Adaptive Early-Learning Correction for Segmentation from Noisy Annotations

Deep learning in the presence of noisy annotations has been studied exte...
research
01/24/2019

Correcting rural building annotations in OpenStreetMap using convolutional neural networks

Rural building mapping is paramount to support demographic studies and p...
research
03/12/2019

Noisy Supervision for Correcting Misaligned Cadaster Maps Without Perfect Ground Truth Data

In machine learning the best performance on a certain task is achieved b...
research
05/30/2023

Deep Clustering with Incomplete Noisy Pairwise Annotations: A Geometric Regularization Approach

The recent integration of deep learning and pairwise similarity annotati...
research
12/06/2021

Adjusting the Ground Truth Annotations for Connectivity-Based Learning to Delineate

Deep learning-based approaches to delineating 3D structure depend on acc...
research
03/22/2021

Model-based 3D Hand Reconstruction via Self-Supervised Learning

Reconstructing a 3D hand from a single-view RGB image is challenging due...
research
04/11/2020

Learning to Manipulate Individual Objects in an Image

We describe a method to train a generative model with latent factors tha...

Please sign up or login with your details

Forgot password? Click here to reset