Progressive Recurrent Learning for Visual Recognition

11/29/2018
by   Xutong Ren, et al.
0

Computer vision is difficult, partly because the mathematical function connecting input and output data is often complex, fuzzy and thus hard to learn. A currently popular solution is to design a deep neural network and optimize it on a large-scale dataset. However, as the number of parameters increases, the generalization ability is often not guaranteed, e.g., the model can over-fit due to the limited amount of training data, or fail to converge because the desired function is too difficult to learn. This paper presents an effective framework named progressive recurrent learning (PRL). The core idea is similar to curriculum learning which gradually increases the difficulty of training data. We generalize it to a wide range of vision problems that were previously considered less proper to apply curriculum learning. PRL starts with inserting a recurrent prediction scheme, based on the motivation of feeding the prediction of a vision model to the same model iteratively, so that the auxiliary cues contained in it can be exploited to improve the quality of itself. In order to better optimize this framework, we start with providing perfect prediction, i.e., ground-truth, to the second stage, but gradually replace it with the prediction of the first stage. In the final status, the ground-truth information is not needed any more, so that the entire model works on the real data distribution as in the testing process. We apply PRL to two challenging visual recognition tasks, namely, object localization and semantic segmentation, and demonstrate consistent accuracy gain compared to the baseline training strategy, especially in the scenarios of more difficult vision tasks.

READ FULL TEXT

page 3

page 6

research
03/19/2020

Curriculum DeepSDF

When learning to sketch, beginners start with simple and flexible shapes...
research
11/22/2019

BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks

While deep learning has recently achieved great success on multi-view st...
research
09/22/2020

Curriculum Learning with Diversity for Supervised Computer Vision Tasks

Curriculum learning techniques are a viable solution for improving the a...
research
09/15/2014

Transfer Learning for Video Recognition with Scarce Training Data for Deep Convolutional Neural Network

Unconstrained video recognition and Deep Convolution Network (DCN) are t...
research
09/01/2022

Video-Guided Curriculum Learning for Spoken Video Grounding

In this paper, we introduce a new task, spoken video grounding (SVG), wh...
research
08/15/2020

Curriculum Learning for Recurrent Video Object Segmentation

Video object segmentation can be understood as a sequence-to-sequence ta...
research
06/22/2023

Curriculum Knowledge Switching for Pancreas Segmentation

Pancreas segmentation is challenging due to the small proportion and hig...

Please sign up or login with your details

Forgot password? Click here to reset