Focus-and-Expand: Training Guidance Through Gradual Manipulation of Input Features

• URL: http://arxiv.org/abs/2007.07723v1
• Date: Wed, 15 Jul 2020 14:49:56 GMT
• Title: Focus-and-Expand: Training Guidance Through Gradual Manipulation of Input Features
• Authors: Moab Arar, Noa Fish, Dani Daniel, Evgeny Tenetov, Ariel Shamir, Amit Bermano
• Abstract summary: We present a method to guide the training process of a neural-and-epand (fax) network. This process encourages the consideration of various input features. We achieve state-of-the- augmentation method on various Computer Vision tasks.
• Score: 11.200634125590069
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a simple and intuitive Focus-and-eXpand (\fax) method to guide the training process of a neural network towards a specific solution. Optimizing a neural network is a highly non-convex problem. Typically, the space of solutions is large, with numerous possible local minima, where reaching a specific minimum depends on many factors. In many cases, however, a solution which considers specific aspects, or features, of the input is desired. For example, in the presence of bias, a solution that disregards the biased feature is a more robust and accurate one. Drawing inspiration from Parameter Continuation methods, we propose steering the training process to consider specific features in the input more than others, through gradual shifts in the input domain. \fax extracts a subset of features from each input data-point, and exposes the learner to these features first, Focusing the solution on them. Then, by using a blending/mixing parameter $\alpha$ it gradually eXpands the learning process to include all features of the input. This process encourages the consideration of the desired features more than others. Though not restricted to this field, we quantitatively evaluate the effectiveness of our approach on various Computer Vision tasks, and achieve state-of-the-art bias removal, improvements to an established augmentation method, and two examples of improvements to image classification tasks. Through these few examples we demonstrate the impact this approach potentially carries for a wide variety of problems, which stand to gain from understanding the solution landscape.

Related papers

• Customize Your Own Paired Data via Few-shot Way [14.193031218059646]
  Some supervised methods require huge amounts of paired training data, which greatly limits their usages. The other unsupervised methods take full advantage of large-scale pre-trained priors, thus being strictly restricted to the domains where the priors are trained on and behaving badly in out-of-distribution cases. In our proposed framework, a novel few-shot learning mechanism based on the directional transformations among samples is introduced and expands the learnable space exponentially.
  arXiv  Detail & Related papers  (2024-05-21T04:21:35Z)
• Optimizing Solution-Samplers for Combinatorial Problems: The Landscape of Policy-Gradient Methods [52.0617030129699]
  We introduce a novel theoretical framework for analyzing the effectiveness of DeepMatching Networks and Reinforcement Learning methods. Our main contribution holds for a broad class of problems including Max-and Min-Cut, Max-$k$-Bipartite-Bi, Maximum-Weight-Bipartite-Bi, and Traveling Salesman Problem. As a byproduct of our analysis we introduce a novel regularization process over vanilla descent and provide theoretical and experimental evidence that it helps address vanishing-gradient issues and escape bad stationary points.
  arXiv  Detail & Related papers  (2023-10-08T23:39:38Z)
• Ideal Abstractions for Decision-Focused Learning [108.15241246054515]
  We propose a method that configures the output space automatically in order to minimize the loss of decision-relevant information. We demonstrate the method in two domains: data acquisition for deep neural network training and a closed-loop wildfire management task.
  arXiv  Detail & Related papers  (2023-03-29T23:31:32Z)
• Few-Shot Point Cloud Semantic Segmentation via Contrastive Self-Supervision and Multi-Resolution Attention [6.350163959194903]
  We propose a contrastive self-supervision framework for few-shot learning pretrain. Specifically, we implement a novel contrastive learning approach with a learnable augmentor for a 3D point cloud. We develop a multi-resolution attention module using both the nearest and farthest points to extract the local and global point information more effectively.
  arXiv  Detail & Related papers  (2023-02-21T07:59:31Z)
• Feature Selection with Distance Correlation [0.0]
  We develop a new feature selection method based on Distance Correlation (DisCo) Using our method to select features from a set of over 7,000 energy flows, we show that we can match the performance of much deeper architectures.
  arXiv  Detail & Related papers  (2022-11-30T19:00:04Z)
• OReX: Object Reconstruction from Planar Cross-sections Using Neural Fields [10.862993171454685]
  OReX is a method for 3D shape reconstruction from slices alone, featuring a Neural Field gradients as the prior. A modest neural network is trained on the input planes to return an inside/outside estimate for a given 3D coordinate, yielding a powerful prior that induces smoothness and self-similarities. We offer an iterative estimation architecture and a hierarchical input sampling scheme that encourage coarse-to-fine training, allowing the training process to focus on high frequencies at later stages.
  arXiv  Detail & Related papers  (2022-11-23T11:44:35Z)
• AMS-Net: Adaptive Multiscale Sparse Neural Network with Interpretable Basis Expansion for Multiphase Flow Problems [8.991619150027267]
  We propose an adaptive sparse learning algorithm that can be applied to learn the physical processes and obtain a sparse representation of the solution given a large snapshot space. The information of the basis functions are incorporated in the loss function, which minimizes the differences between the downscaled reduced order solutions and reference solutions at multiple time steps. More numerical tests are performed on two-phase multiscale flow problems to show the capability and interpretability of the proposed method on complicated applications.
  arXiv  Detail & Related papers  (2022-07-24T13:12:43Z)
• Revisiting Point Cloud Simplification: A Learnable Feature Preserving Approach [57.67932970472768]
  Mesh and Point Cloud simplification methods aim to reduce the complexity of 3D models while retaining visual quality and relevant salient features. We propose a fast point cloud simplification method by learning to sample salient points. The proposed method relies on a graph neural network architecture trained to select an arbitrary, user-defined, number of points from the input space and to re-arrange their positions so as to minimize the visual perception error.
  arXiv  Detail & Related papers  (2021-09-30T10:23:55Z)
• Learning Neural Network Subspaces [74.44457651546728]
  Recent observations have advanced our understanding of the neural network optimization landscape. With a similar computational cost as training one model, we learn lines, curves, and simplexes of high-accuracy neural networks. With a similar computational cost as training one model, we learn lines, curves, and simplexes of high-accuracy neural networks.
  arXiv  Detail & Related papers  (2021-02-20T23:26:58Z)
• Multi-task Supervised Learning via Cross-learning [102.64082402388192]
  We consider a problem known as multi-task learning, consisting of fitting a set of regression functions intended for solving different tasks. In our novel formulation, we couple the parameters of these functions, so that they learn in their task specific domains while staying close to each other. This facilitates cross-fertilization in which data collected across different domains help improving the learning performance at each other task.
  arXiv  Detail & Related papers  (2020-10-24T21:35:57Z)
• Saliency-driven Class Impressions for Feature Visualization of Deep Neural Networks [55.11806035788036]
  It is advantageous to visualize the features considered to be essential for classification. Existing visualization methods develop high confidence images consisting of both background and foreground features. In this work, we propose a saliency-driven approach to visualize discriminative features that are considered most important for a given task.
  arXiv  Detail & Related papers  (2020-07-31T06:11:06Z)
• Exchangeable Input Representations for Reinforcement Learning [48.696389129611056]
  This work presents an attention-based method to project neural network inputs into an efficient representation space. We show that our proposed representation results in an input space that is a factor of $m!$ smaller for inputs of $m$ objects.
  arXiv  Detail & Related papers  (2020-03-19T21:18:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.