Total Variation Optimization Layers for Computer Vision
Optimization within a layer of a deep-net has emerged as a new direction for deep-net layer design. However, there are two main challenges when applying these layers to computer vision tasks: (a) which optimization problem within a layer is useful?; (b) how to ensure that computation within a layer remains efficient? To study question (a), in this work, we propose total variation (TV) minimization as a layer for computer vision. Motivated by the success of total variation in image processing, we hypothesize that TV as a layer provides useful inductive bias for deep-nets too. We study this hypothesis on five computer vision tasks: image classification, weakly supervised object localization, edge-preserving smoothing, edge detection, and image denoising, improving over existing baselines. To achieve these results we had to address question (b): we developed a GPU-based projected-Newton method which is $37\times$ faster than existing solutions.
Code (1)
Tasks
DenoisingEdge DetectionGPUimage-classificationImage ClassificationImage DenoisingInductive BiasObject LocalizationWeakly-Supervised Object LocalizationSimilar Papers 제목 키워드 기반
An Iterated L1 Algorithm for Non-smooth Non-convex Optimization in Computer Vision
Natural image statistics indicate that we should use nonconvex norms for most regularization tasks in image processing and computer vision. Still, they are rarely used in practice due to the challenge to optimize them. R…
DenoisingImage DenoisingOptical Flow EstimationTotal variation on a tree
We consider the problem of minimizing the continuous valued total variation subject to different unary terms on trees and propose fast direct algorithms based on dynamic programming to solve these problems. We treat both…
Total Variation Applications in Computer Vision
The objectives of this chapter are: (i) to introduce a concise overview of regularization; (ii) to define and to explain the role of a particular type of regularization called total variation norm (TV-norm) in computer v…
WeLa-VAE: Learning Alternative Disentangled Representations Using Weak Labels
Learning disentangled representations without supervision or inductive biases, often leads to non-interpretable or undesirable representations. On the other hand, strict supervision requires detailed knowledge of the tru…
Variational InferenceConcurrent validity of computer-vision artificial intelligence player tracking software using broadcast footage
This study aimed to: (1) understand whether commercially available computer-vision and artificial intelligence (AI) player tracking software can accurately measure player position, speed and distance using broadcast foot…