LSM: Learning Subspace Minimization for Low-level Vision

04/20/2020
by   Chengzhou Tang, et al.
0

We study the energy minimization problem in low-level vision tasks from a novel perspective. We replace the heuristic regularization term with a learnable subspace constraint, and preserve the data term to exploit domain knowledge derived from the first principle of a task. This learning subspace minimization (LSM) framework unifies the network structures and the parameters for many low-level vision tasks, which allows us to train a single network for multiple tasks simultaneously with completely shared parameters, and even generalizes the trained network to an unseen task as long as its data term can be formulated. We demonstrate our LSM framework on four low-level tasks including interactive image segmentation, video segmentation, stereo matching, and optical flow, and validate the network on various datasets. The experiments show that the proposed LSM generates state-of-the-art results with smaller model size, faster training convergence, and real-time inference.

READ FULL TEXT

page 1

page 3

page 4

page 6

page 7

page 8

page 13

research
06/28/2023

Let Segment Anything Help Image Dehaze

The large language model and high-level vision model have achieved impre...
research
05/14/2018

Learning Dual Convolutional Neural Networks for Low-Level Vision

In this paper, we propose a general dual convolutional neural network (D...
research
03/30/2023

Masked Autoencoders as Image Processors

Transformers have shown significant effectiveness for various vision tas...
research
01/02/2023

Task-specific Scene Structure Representations

Understanding the informative structures of scenes is essential for low-...
research
12/02/2021

Event Neural Networks

Video data is often repetitive; for example, the content of adjacent fra...
research
08/16/2023

SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-time Performance on Mobile Device

With the rapid development of AI hardware accelerators, applying deep le...
research
03/06/2013

On Considering Uncertainty and Alternatives in Low-Level Vision

In this paper we address the uncertainty issues involved in the low-leve...

Please sign up or login with your details

Forgot password? Click here to reset