Robust Loss Functions for Object Grasping under Limited Ground Truth
This work addresses accuracy issues in robot grasping under limited data conditions, but it is incremental as it builds on existing methods like pseudo-labeling.
The paper tackles the problem of missing or noisy ground truth in training convolutional neural networks for object grasping by proposing new loss functions, resulting in performance improvements of 2 to 13 percent.
Object grasping is a crucial technology enabling robots to perceive and interact with the environment sufficiently. However, in practical applications, researchers are faced with missing or noisy ground truth while training the convolutional neural network, which decreases the accuracy of the model. Therefore, different loss functions are proposed to deal with these problems to improve the accuracy of the neural network. For missing ground truth, a new predicted category probability method is defined for unlabeled samples, which works effectively in conjunction with the pseudo-labeling method. Furthermore, for noisy ground truth, a symmetric loss function is introduced to resist the corruption of label noises. The proposed loss functions are powerful, robust, and easy to use. Experimental results based on the typical grasping neural network show that our method can improve performance by 2 to 13 percent.