Context-aware Padding for Semantic Segmentation

• URL: http://arxiv.org/abs/2109.07854v1
• Date: Thu, 16 Sep 2021 10:33:21 GMT
• Title: Context-aware Padding for Semantic Segmentation
• Authors: Yu-Hui Huang, Marc Proesmans, Luc Van Gool
• Abstract summary: We propose a context-aware (CA) padding approach to extend the image. Using context-aware padding, the ResNet-based segmentation model achieves higher mean Intersection-Over-Union than the traditional zero padding.
• Score: 82.37483350347559
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Zero padding is widely used in convolutional neural networks to prevent the size of feature maps diminishing too fast. However, it has been claimed to disturb the statistics at the border. As an alternative, we propose a context-aware (CA) padding approach to extend the image. We reformulate the padding problem as an image extrapolation problem and illustrate the effects on the semantic segmentation task. Using context-aware padding, the ResNet-based segmentation model achieves higher mean Intersection-Over-Union than the traditional zero padding on the Cityscapes and the dataset of DeepGlobe satellite imaging challenge. Furthermore, our padding does not bring noticeable overhead during training and testing.

Related papers

• Associative Memories in the Feature Space [68.1903319310263]
  We propose a class of memory models that only stores low-dimensional semantic embeddings, and uses them to retrieve similar, but not identical, memories. We demonstrate a proof of concept of this method on a simple task on the MNIST dataset.
  arXiv  Detail & Related papers  (2024-02-16T16:37:48Z)
• PadChannel: Improving CNN Performance through Explicit Padding Encoding [40.39759037668144]
  In convolutional neural networks (CNNs), padding plays a pivotal role in preserving spatial dimensions throughout the layers. Traditional padding techniques do not explicitly distinguish between the actual image content and the padded regions. We propose PadChannel, a novel padding method that encodes padding statuses as an additional input channel.
  arXiv  Detail & Related papers  (2023-11-13T07:44:56Z)
• Learning Semantic Segmentation with Query Points Supervision on Aerial Images [57.09251327650334]
  We present a weakly supervised learning algorithm to train semantic segmentation algorithms. Our proposed approach performs accurate semantic segmentation and improves efficiency by significantly reducing the cost and time required for manual annotation.
  arXiv  Detail & Related papers  (2023-09-11T14:32:04Z)
• On the Interplay of Convolutional Padding and Adversarial Robustness [16.306183236605364]
  We show that adversarial attacks often result in perturbation anomalies at the image boundaries, which are the areas where padding is used. We seek an answer to the question of how different padding modes (or their absence) affect adversarial robustness in various scenarios.
  arXiv  Detail & Related papers  (2023-08-12T17:06:48Z)
• Localizing Semantic Patches for Accelerating Image Classification [12.250230630124758]
  We first pinpoint task-aware regions over the input image by a lightweight patch proposal network called AnchorNet. We then feed these localized semantic patches with much smaller spatial redundancy into a general classification network. Our method outperforms SOTA dynamic inference methods with fewer inference costs.
  arXiv  Detail & Related papers  (2022-06-07T15:01:54Z)
• Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation [27.50216933606052]
  We address the problem of weakly-supervised semantic segmentation using bounding box annotations. Background regions are perceptually consistent in part within an image, and this can be leveraged to discriminate foreground and background regions inside object bounding boxes. We introduce a noise-aware loss (NAL) that makes the networks less susceptible to incorrect labels.
  arXiv  Detail & Related papers  (2021-04-02T06:38:41Z)
• Exploring Cross-Image Pixel Contrast for Semantic Segmentation [130.22216825377618]
  We propose a pixel-wise contrastive framework for semantic segmentation in the fully supervised setting. The core idea is to enforce pixel embeddings belonging to a same semantic class to be more similar than embeddings from different classes. Our method can be effortlessly incorporated into existing segmentation frameworks without extra overhead during testing.
  arXiv  Detail & Related papers  (2021-01-28T11:35:32Z)
• An Empirical Method to Quantify the Peripheral Performance Degradation in Deep Networks [18.808132632482103]
  convolutional neural network (CNN) kernels compound with each convolutional layer. Deeper and deeper networks combined with stride-based down-sampling means that the propagation of this region can end up covering a non-negligable portion of the image. Our dataset is constructed by inserting objects into high resolution backgrounds, thereby allowing us to crop sub-images which place target objects at specific locations relative to the image border. By probing the behaviour of Mask R-CNN across a selection of target locations, we see clear patterns of performance degredation near the image boundary, and in particular in the image corners.
  arXiv  Detail & Related papers  (2020-12-04T18:00:47Z)
• Learning Spatio-Appearance Memory Network for High-Performance Visual Tracking [79.80401607146987]
  Existing object tracking usually learns a bounding-box based template to match visual targets across frames, which cannot accurately learn a pixel-wise representation. This paper presents a novel segmentation-based tracking architecture, which is equipped with a local-temporal memory network to learn accurate-temporal correspondence.
  arXiv  Detail & Related papers  (2020-09-21T08:12:02Z)
• Real-Time High-Performance Semantic Image Segmentation of Urban Street Scenes [98.65457534223539]
  We propose a real-time high-performance DCNN-based method for robust semantic segmentation of urban street scenes. The proposed method achieves the accuracy of 73.6% and 68.0% mean Intersection over Union (mIoU) with the inference speed of 51.0 fps and 39.3 fps.
  arXiv  Detail & Related papers  (2020-03-11T08:45:53Z)

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.