اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدRelaxed Earth Movers Distances for Chain- and Tree-connected Spaces and their use as a Loss Function in Deep Learning
47
0
0.0
(
0
)
نشر من قبل
Manuel Isaac Martinez Torres
تاريخ النشر
2016
مجال البحث
الهندسة المعلوماتية
والبحث باللغة
English
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
The Earth Movers Distance (EMD) computes the optimal cost of transforming one distribution into another, given a known transport metric between them. In deep learning, the EMD loss allows us to embed information during training about the output space structure like hierarchical or semantic relations. This helps in achieving better output smoothness and generalization. However EMD is computationally expensive.Moreover, solving EMD optimization problems usually require complex techniques like lasso. These properties limit the applicability of EMD-based approaches in large scale machine learning. We address in this work the difficulties facing incorporation of EMD-based loss in deep learning frameworks. Additionally, we provide insight and novel solutions on how to integrate such loss function in training deep neural networks. Specifically, we make three main contributions: (i) we provide an in-depth analysis of the fastest state-of-the-art EMD algorithm (Sinkhorn Distance) and discuss its limitations in deep learning scenarios. (ii) we derive fast and numerically stable closed-form solutions for the EMD gradient in output spaces with chain- and tree- connectivity; and (iii) we propose a relaxed form of the EMD gradient with equivalent computational complexity but faster convergence rate. We support our claims with experiments on real datasets. In a restricted data setting on the ImageNet dataset, we train a model to classify 1000 categories using 50K images, and demonstrate that our relaxed EMD loss achieves better Top-1 accuracy than the cross entropy loss. Overall, we show that our relaxed EMD loss criterion is a powerful asset for deep learning in the small data regime.
قيم البحث
اقرأ أيضاً
In the context of single-label classification, despite the huge success of deep learning, the commonly used cross-entropy loss function ignores the intricate inter-class relationships that often exist in real-life tasks such as age classification. In
this work, we propose to leverage these relationships between classes by training deep nets with the exact squared Earth Movers Distance (also known as Wasserstein distance) for single-label classification. The squared EMD loss uses the predicted probabilities of all classes and penalizes the miss-predictions according to a ground distance matrix that quantifies the dissimilarities between classes. We demonstrate that on datasets with strong inter-class relationships such as an ordering between classes, our exact squared EMD losses yield new state-of-the-art results. Furthermore, we propose a method to automatically learn this matrix using the CNNs own features during training. We show that our method can learn a ground distance matrix efficiently with no inter-class relationship priors and yield the same performance gain. Finally, we show that our method can be generalized to applications that lack strong inter-class relationships and still maintain state-of-the-art performance. Therefore, with limited computational overhead, one can always deploy the proposed loss function on any dataset over the conventional cross-entropy.
We introduce a method for training neural networks to perform image or volume segmentation in which prior knowledge about the topology of the segmented object can be explicitly provided and then incorporated into the training process. By using the di
fferentiable properties of persistent homology, a concept used in topological data analysis, we can specify the desired topology of segmented objects in terms of their Betti numbers and then drive the proposed segmentations to contain the specified topological features. Importantly this process does not require any ground-truth labels, just prior knowledge of the topology of the structure being segmented. We demonstrate our approach in three experiments. Firstly we create a synthetic task in which handwritten MNIST digits are de-noised, and show that using this kind of topological prior knowledge in the training of the network significantly improves the quality of the de-noised digits. Secondly we perform an experiment in which the task is segmenting the myocardium of the left ventricle from cardiac magnetic resonance images. We show that the incorporation of the prior knowledge of the topology of this anatomy improves the resulting segmentations in terms of both the topological accuracy and the Dice coefficient. Thirdly, we extend the method to 3D volumes and demonstrate its performance on the task of segmenting the placenta from ultrasound data, again showing that incorporating topological priors improves performance on this challenging task. We find that embedding explicit prior knowledge in neural network segmentation tasks is most beneficial when the segmentation task is especially challenging and that it can be used in either a semi-supervised or post-processing context to extract a useful training gradient from images without pixelwise labels.
Contour tracking in adverse environments is a challenging problem due to cluttered background, illumination variation, occlusion, and noise, among others. This paper presents a robust contour tracking method by contributing to some of the key issues
involved, including (a) a region functional formulation and its optimization; (b) design of a robust and effective feature; and (c) development of an integrated tracking algorithm. First, we formulate a region functional based on robust Earth Movers distance (EMD) with kernel density for distribution modeling, and propose a two-phase method for its optimization. In the first phase, letting the candidate contour be fixed, we express EMD as the transportation problem and solve it by the simplex algorithm. Next, using the theory of shape derivative, we make a perturbation analysis of the contour around the best solution to the transportation problem. This leads to a partial differential equation (PDE) that governs the contour evolution. Second, we design a novel and effective feature for tracking applications. We propose a dimensionality reduction method by tensor decomposition, achieving a low-dimensional description of SIFT features called Tensor-SIFT for characterizing local image region properties. Applicable to both color and gray-level images, Tensor-SIFT is very distinctive, insensitive to illumination changes, and noise. Finally, we develop an integrated algorithm that combines various techniques of the simplex algorithm, narrow-band level set and fast marching algorithms. Particularly, we introduce an inter-frame initialization method and a stopping criterion for the termination of PDE iteration. Experiments in challenging image sequences show that the proposed work has promising performance.
Nowadays, deep learning methods, especially the convolutional neural networks (CNNs), have shown impressive performance on extracting abstract and high-level features from the hyperspectral image. However, general training process of CNNs mainly cons
iders the pixel-wise information or the samples correlation to formulate the penalization while ignores the statistical properties especially the spectral variability of each class in the hyperspectral image. These samples-based penalizations would lead to the uncertainty of the training process due to the imbalanced and limited number of training samples. To overcome this problem, this work characterizes each class from the hyperspectral image as a statistical distribution and further develops a novel statistical loss with the distributions, not directly with samples for deep learning. Based on the Fisher discrimination criterion, the loss penalizes the sample variance of each class distribution to decrease the intra-class variance of the training samples. Moreover, an additional diversity-promoting condition is added to enlarge the inter-class variance between different class distributions and this could better discriminate samples from different classes in hyperspectral image. Finally, the statistical estimation form of the statistical loss is developed with the training samples through multi-variant statistical analysis. Experiments over the real-world hyperspectral images show the effectiveness of the developed statistical loss for deep learning.
The land-use map is an important data that can reflect the use and transformation of human land, and can provide valuable reference for land-use planning. For the traditional image classification method, producing a high spatial resolution (HSR), lan
d-use map in large-scale is a big project that requires a lot of human labor, time, and financial expenditure. The rise of the deep learning technique provides a new solution to the problems above. This paper proposes a fast and precise method that can achieve large-scale land-use classification based on deep convolutional neural network (DCNN). In this paper, we optimize the data tiling method and the structure of DCNN for the multi-channel data and the splicing edge effect, which are unique to remote sensing deep learning, and improve the accuracy of land-use classification. We apply our improved methods in the Guangdong Province of China using GF-1 images, and achieve the land-use classification accuracy of 81.52%. It takes only 13 hours to complete the work, which will take several months for human labor.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
