DeepAI AI Chat
Log In Sign Up

Adaptive Class Weight based Dual Focal Loss for Improved Semantic Segmentation

by   Md Sazzad Hossain, et al.

In this paper, we propose a Dual Focal Loss (DFL) function, as a replacement for the standard cross entropy (CE) function to achieve a better treatment of the unbalanced classes in a dataset. Our DFL method is an improvement on the recently reported Focal Loss (FL) cross-entropy function, which proposes a scaling method that puts more weight on the examples that are difficult to classify over those that are easy. However, the scaling parameter of FL is empirically set, which is problem-dependent. In addition, like other CE variants, FL only focuses on the loss of true classes. Therefore, no loss feedback is gained from the false classes. Although focusing only on true examples increases probability on true classes and correspondingly reduces probability on false classes due to the nature of the softmax function, it does not achieve the best convergence due to avoidance of the loss on false classes. Our DFL method improves on the simple FL in two ways. Firstly, it takes the idea of FL to focus more on difficult examples than the easy ones, but evaluates loss on both true and negative classes with equal importance. Secondly, the scaling parameter of DFL has been made learnable so that it can tune itself by backpropagation rather than being dependent on manual tuning. In this way, our proposed DFL method offers an auto-tunable loss function that can reduce the class imbalance effect as well as put more focus on both true difficult examples and negative easy examples. Experimental results show that our proposed method provides better accuracy in every test run conducted over a variety of different network models and datasets.


page 1

page 7


Striking the Right Balance: Recall Loss for Semantic Segmentation

Class imbalance is a fundamental problem in computer vision applications...

Gradient Harmonized Single-stage Detector

Despite the great success of two-stage detectors, single-stage detector ...

The Tree Loss: Improving Generalization with Many Classes

Multi-class classification problems often have many semantically similar...

Federated Learning with Label Distribution Skew via Logits Calibration

Traditional federated optimization methods perform poorly with heterogen...

CAMRI Loss: Improving Recall of a Specific Class without Sacrificing Accuracy

In real-world applications of multi-class classification models, misclas...

ImageTBAD: A 3D Computed Tomography Angiography Image Dataset for Automatic Segmentation of Type-B Aortic Dissection

Type-B Aortic Dissection (TBAD) is one of the most serious cardiovascula...

Yes, IoU loss is submodular - as a function of the mispredictions

This note is a response to [7] in which it is claimed that [13, Proposit...