NeurIPS 2019 Disentanglement Challenge: Improved Disentanglement through Aggregated Convolutional Feature Maps

• URL: http://arxiv.org/abs/2002.10003v1
• Date: Sun, 23 Feb 2020 22:35:59 GMT
• Title: NeurIPS 2019 Disentanglement Challenge: Improved Disentanglement through Aggregated Convolutional Feature Maps
• Authors: Maximilian Seitzer
• Abstract summary: This report presents a simple image preprocessing method for training VAEs. In particular, we propose to use regionally aggregated feature maps extracted from CNNs pretrained on ImageNet. Our method achieved the 2nd place in stage 1 of the NeurIPS 2019 disentanglement challenge.
• Score: 2.538209532048867
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This report to our stage 1 submission to the NeurIPS 2019 disentanglement challenge presents a simple image preprocessing method for training VAEs leading to improved disentanglement compared to directly using the images. In particular, we propose to use regionally aggregated feature maps extracted from CNNs pretrained on ImageNet. Our method achieved the 2nd place in stage 1 of the challenge. Code is available at https://github.com/mseitzer/neurips2019-disentanglement-challenge.

Related papers

• Enhanced Semantic Segmentation Pipeline for WeatherProof Dataset Challenge [2.722639169181398]
  This report describes the winning solution to the WeatherProof dataset challenge. We propose an enhanced semantic segmentation pipeline for this challenge. We introduce a new dataset WeatherProofExtra with wider viewing angle and employ data augmentation methods. Our solution is ranked 1st on the final leaderboard.
  arXiv  Detail & Related papers  (2024-06-06T07:12:50Z)
• Deblurring Photographs of Characters Using Deep Neural Networks [0.5156484100374059]
  We present our approach for the Helsinki Deblur Challenge (HDC 2021) The challenge is to deblur images of characters without knowing the point spread function (PSF) Our method consists of three steps: first, we estimate a warping transformation of the images to align the sharp images with the blurred ones; second, we estimate the PSF using a quasi-Newton method; third, we train a deep convolutional neural network to reconstruct the sharp images from the blurred images.
  arXiv  Detail & Related papers  (2022-05-30T12:32:26Z)
• 1st Place Solutions for UG2+ Challenge 2021 -- (Semi-)supervised Face detection in the low light condition [13.241328369629453]
  "TAL-ai" for (Semi-) supervised Face detection in the low light condition in UG2+ Challenge in CVPR 2021. By conducting several experiments with popular image enhancement methods and image transfer methods, we pulled the low light image and the normal image to a more closer domain. We ensemble several models which achieved mAP 74.89 on the testing set, ranking 1st on the final leaderboard.
  arXiv  Detail & Related papers  (2021-07-02T04:12:23Z)
• Learning Semantic Person Image Generation by Region-Adaptive Normalization [81.52223606284443]
  We propose a new two-stage framework to handle the pose and appearance translation. In the first stage, we predict the target semantic parsing maps to eliminate the difficulties of pose transfer. In the second stage, we suggest a new person image generation method by incorporating the region-adaptive normalization.
  arXiv  Detail & Related papers  (2021-04-14T06:51:37Z)
• Ultra-Data-Efficient GAN Training: Drawing A Lottery Ticket First, Then Training It Toughly [114.81028176850404]
  Training generative adversarial networks (GANs) with limited data generally results in deteriorated performance and collapsed models. We decompose the data-hungry GAN training into two sequential sub-problems. Such a coordinated framework enables us to focus on lower-complexity and more data-efficient sub-problems.
  arXiv  Detail & Related papers  (2021-02-28T05:20:29Z)
• Image Restoration by Deep Projected GSURE [115.57142046076164]
  Ill-posed inverse problems appear in many image processing applications, such as deblurring and super-resolution. We propose a new image restoration framework that is based on minimizing a loss function that includes a "projected-version" of the Generalized SteinUnbiased Risk Estimator (GSURE) and parameterization of the latent image by a CNN.
  arXiv  Detail & Related papers  (2021-02-04T08:52:46Z)
• 1st Place Solutions for OpenImage2019 -- Object Detection and Instance Segmentation [116.25081559037872]
  This article introduces the solutions of the two champion teams, MMfruit' for the detection track and MMfruitSeg' for the segmentation track, in OpenImage Challenge 2019. It is commonly known that for an object detector, the shared feature at the end of the backbone is not appropriate for both classification and regression. We propose the Decoupling Head (DH) to disentangle the object classification and regression via the self-learned optimal feature extraction.
  arXiv  Detail & Related papers  (2020-03-17T06:45:07Z)
• Top-1 Solution of Multi-Moments in Time Challenge 2019 [56.15819266653481]
  We conduct several experiments with popular Image-Based action recognition methods TRN, TSN, and TSM. A novel temporal interlacing network is proposed towards fast and accurate recognition. We ensemble all the above models and achieve 67.22% on the validation set and 60.77% on the test set, which ranks 1st on the final leaderboard.
  arXiv  Detail & Related papers  (2020-03-12T15:11:38Z)
• NeurIPS 2019 Disentanglement Challenge: Improved Disentanglement through Learned Aggregation of Convolutional Feature Maps [2.8360662552057323]
  We propose to train a variational autoencoder on regionally aggregated feature maps obtained from networks pretrained on the ImageNet database. Our approach achieved the 2nd place in stage 2 of the NeurIPS 2019 disentanglement challenge.
  arXiv  Detail & Related papers  (2020-02-27T08:46:17Z)
• Lipreading using Temporal Convolutional Networks [57.41253104365274]
  Current model for recognition of isolated words in-the-wild consists of a residual network and Bi-directional Gated Recurrent Unit layers. We address the limitations of this model and we propose changes which further improve its performance. Our proposed model results in an absolute improvement of 1.2% and 3.2%, respectively, in these datasets.
  arXiv  Detail & Related papers  (2020-01-23T17:49:35Z)

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.