Soft labelling for semantic segmentation: Bringing coherence to label down-sampling

02/27/2023
by   Roberto Alcover-Couso, et al.
0

In semantic segmentation, training data down-sampling is commonly performed because of limited resources, adapting image size to the model input, or improving data augmentation. This down-sampling typically employs different strategies for the image data and the annotated labels. Such discrepancy leads to mismatches between the down-sampled pixels and labels. Hence, training performance significantly decreases as the down-sampling factor increases. In this paper, we bring together the downsampling strategies for the image data and annotated labels. To that aim, we propose a soft-labeling method for label down-sampling that takes advantage of structural content prior to down-sampling. Thereby, fully aligning softlabels with image data to keep the distribution of the sampled pixels. This proposal also produces richer annotations for under-represented semantic classes. Altogether, it permits training competitive models at lower resolutions. Experiments show that the proposal outperforms other downsampling strategies. Moreover, state of the art performance is achieved for reference benchmarks, but employing significantly less computational resources than other approaches. This proposal enables competitive research for semantic segmentation under resource constraints.

READ FULL TEXT

page 3

page 4

page 6

research
04/21/2021

A Closer Look at Self-training for Zero-Label Semantic Segmentation

Being able to segment unseen classes not observed during training is an ...
research
03/14/2023

AutoEnsemble: Automated Ensemble Search Framework for Semantic Segmentation Using Image Labels

A key bottleneck of employing state-of-the-art semantic segmentation net...
research
10/31/2021

Smart(Sampling)Augment: Optimal and Efficient Data Augmentation for Semantic Segmentation

Data augmentation methods enrich datasets with augmented data to improve...
research
07/07/2021

Hierarchical Semantic Segmentation using Psychometric Learning

Assigning meaning to parts of image data is the goal of semantic image s...
research
07/20/2023

Label Calibration for Semantic Segmentation Under Domain Shift

Performance of a pre-trained semantic segmentation model is likely to su...
research
09/28/2021

Warp-Refine Propagation: Semi-Supervised Auto-labeling via Cycle-consistency

Deep learning models for semantic segmentation rely on expensive, large-...
research
08/17/2016

Scene Labeling Through Knowledge-Based Rules Employing Constrained Integer Linear Programing

Scene labeling task is to segment the image into meaningful regions and ...

Please sign up or login with your details

Forgot password? Click here to reset