Loss Max-Pooling for Semantic Image Segmentation

04/10/2017
by   Samuel Rota Bulò, et al.
0

We introduce a novel loss max-pooling concept for handling imbalanced training data distributions, applicable as alternative loss layer in the context of deep neural networks for semantic image segmentation. Most real-world semantic segmentation datasets exhibit long tail distributions with few object categories comprising the majority of data and consequently biasing the classifiers towards them. Our method adaptively re-weights the contributions of each pixel based on their observed losses, targeting under-performing classification results as often encountered for under-represented object classes. Our approach goes beyond conventional cost-sensitive learning attempts through adaptive considerations that allow us to indirectly address both, inter- and intra-class imbalances. We provide a theoretical justification of our approach, complementary to experimental analyses on benchmark datasets. In our experiments on the Cityscapes and Pascal VOC 2012 segmentation datasets we find consistently improved results, demonstrating the efficacy of our approach.

READ FULL TEXT
research
02/23/2018

Locally Adaptive Learning Loss for Semantic Image Segmentation

We propose a novel locally adaptive learning estimator for enhancing the...
research
03/12/2020

EDC3: Ensemble of Deep-Classifiers using Class-specific Copula functions to Improve Semantic Image Segmentation

In the literature, many fusion techniques are registered for the segment...
research
06/07/2018

Efficient semantic image segmentation with superpixel pooling

In this work, we evaluate the use of superpixel pooling layers in deep n...
research
07/29/2022

Class-Difficulty Based Methods for Long-Tailed Visual Recognition

Long-tailed datasets are very frequently encountered in real-world use c...
research
01/28/2023

ProtoSeg: Interpretable Semantic Segmentation with Prototypical Parts

We introduce ProtoSeg, a novel model for interpretable semantic image se...
research
04/05/2018

Multi-level Activation for Segmentation of Hierarchically-nested Classes

For a number of biomedical image segmentation tasks, including topologic...
research
02/21/2023

Non-pooling Network for medical image segmentation

Existing studies tend tofocus onmodel modifications and integration with...

Please sign up or login with your details

Forgot password? Click here to reset