Related papers: Strip Pooling: Rethinking Spatial Pooling for Scen…
In this work, we evaluate the use of superpixel pooling layers in deep network architectures for semantic segmentation. Superpixel pooling is a flexible and efficient replacement for other pooling strategies that incorporates spatial prior…
There are a variety of approaches to obtain a vast receptive field with convolutional neural networks (CNNs), such as pooling or striding convolutions. Most of these approaches were initially designed for image classification and later…
We propose a novel superpixel-based multi-view convolutional neural network for semantic image segmentation. The proposed network produces a high quality segmentation of a single image by leveraging information from additional views of the…
Feature pooling layers (e.g., max pooling) in convolutional neural networks (CNNs) serve the dual purpose of providing increasingly abstract representations as well as yielding computational savings in subsequent convolutional layers. We…
This paper introduces SpaPool, a novel pooling method that combines the strengths of both dense and sparse techniques for a graph neural network. SpaPool groups vertices into an adaptive number of clusters, leveraging the benefits of both…
Scene parsing is challenging for unrestricted open vocabulary and diverse scenes. In this paper, we exploit the capability of global context information by different-region-based context aggregation through our pyramid pooling module…
Over the last two decades we have witnessed strong progress on modeling visual object classes, scenes and attributes that have significantly contributed to automated image understanding. On the other hand, surprisingly little progress has…
Existing deep convolutional neural networks (CNNs) require a fixed-size (e.g., 224x224) input image. This requirement is "artificial" and may reduce the recognition accuracy for the images or sub-images of an arbitrary size/scale. In this…
Most deep learning backbones are evaluated on ImageNet. Using scenery images as an example, we conducted extensive experiments to demonstrate the widely accepted principles in network design may result in dramatic performance differences…
Semantic segmentation is a fundamental task in computer vision, which can be considered as a per-pixel classification problem. Recently, although fully convolutional neural network (FCN) based approaches have made remarkable progress in…
We propose a network architecture to perform efficient scene understanding. This work presents three main novelties: the first is an Improved Guided Upsampling Module that can replace in toto the decoder part in common semantic segmentation…
In this work, we explore the cross-scale similarity in crowd counting scenario, in which the regions of different scales often exhibit high visual similarity. This feature is universal both within an image and across different images,…
Existing studies tend tofocus onmodel modifications and integration with higher accuracy, which improve performance but also carry huge computational costs, resulting in longer detection times. Inmedical imaging, the use of time is…
Inspired by the success of recent vision transformers and large kernel design in convolutional neural networks (CNNs), in this paper, we analyze and explore essential reasons for their success. We claim two factors that are critical for 3D…
Biologically inspired, from the early HMAX model to Spatial Pyramid Matching, pooling has played an important role in visual recognition pipelines. Spatial pooling, by grouping of local codes, equips these methods with a certain degree of…
Graph Neural Networks (GNN) have been shown to work effectively for modeling graph structured data to solve tasks such as node classification, link prediction and graph classification. There has been some recent progress in defining the…
The goal of this paper is to introduce pooling strategies for simplicial convolutional neural networks. Inspired by graph pooling methods, we introduce a general formulation for a simplicial pooling layer that performs: i) local aggregation…
Pooling is a crucial operation in computer vision, yet the unique structure of skeletons hinders the application of existing pooling strategies to skeleton graph modelling. In this paper, we propose an Improved Graph Pooling Network,…
Scene parsing from images is a fundamental yet challenging problem in visual content understanding. In this dense prediction task, the parsing model assigns every pixel to a categorical label, which requires the contextual information of…
Learning invariant representations from images is one of the hardest challenges facing computer vision. Spatial pooling is widely used to create invariance to spatial shifting, but it is restricted to convolutional models. In this paper, we…