paper-with-me

홈 › Papers

Beyond Gradient Descent for Regularized Segmentation Losses

2018-09-07 · CVPR 2019 6 · Dmitrii Marin, Meng Tang, Ismail Ben Ayed, Yuri Boykov

The simplicity of gradient descent (GD) made it the default method for training ever-deeper and complex neural networks. Both loss functions and architectures are often explicitly tuned to be amenable to this basic local optimization. In the context of weakly-supervised CNN segmentation, we demonstrate a well-motivated loss function where an alternative optimizer (ADM) achieves the state-of-the-art while GD performs poorly. Interestingly, GD obtains its best result for a "smoother" tuning of the loss function. The results are consistent across different network architectures. Our loss is motivated by well-understood MRF/CRF regularization models in "shallow" segmentation and their known global solvers. Our work suggests that network design/training should pay more attention to optimization methods.

📄 PDF Abstract BibTeX arXiv:1809.02322

Code (1)

dmitrii-marin/adm-seg 공식 구현

Tasks

Segmentation

Similar Papers 제목 키워드 기반

Robust Trust Region for Weakly Supervised Segmentation

2021-04-05 · ICCV 2021 10 · Dmitrii Marin, Yuri Boykov

Acquisition of training data for the standard semantic segmentation is expensive if requiring that each pixel is labeled. Yet, current methods significantly deteriorate in weakly supervised settings, e.g. where a fractio…

SegmentationSemantic SegmentationWeakly supervised segmentation

Gradient descent follows the regularization path for general losses

2020-06-19 · Ziwei Ji, Miroslav Dudík, Robert E. Schapire, Matus Telgarsky

Recent work across many machine learning disciplines has highlighted that standard descent methods, even without explicit regularization, do not merely minimize the training error, but also exhibit an implicit bias. This…

Duality between subgradient and conditional gradient methods

2012-11-27 · Francis Bach

Given a convex optimization problem and its dual, there are many possible first-order algorithms. In this paper, we show the equivalence between mirror descent algorithms and algorithms generalizing the conditional gradi…

BIG-bench Machine Learning

SOFIM: Stochastic Optimization Using Regularized Fisher Information Matrix

2024-03-05 · Mrinmay Sen, A. K. Qin, Gayathri C, Raghu Kishore N 외

This paper introduces a new stochastic optimization method based on the regularized Fisher information matrix (FIM), named SOFIM, which can efficiently utilize the FIM to approximate the Hessian matrix for finding Newton…

image-classificationImage ClassificationStochastic Optimization

On the Convergence of Gradient Descent in GANs: MMD GAN As a Gradient Flow

2020-11-04 · Youssef Mroueh, Truyen Nguyen

We consider the maximum mean discrepancy ($\mathrm{MMD}$) GAN problem and propose a parametric kernelized gradient flow that mimics the min-max game in gradient regularized $\mathrm{MMD}$ GAN. We show that this flow prov…