Learning ordered pooling weights in image classification
Spatial pooling is an important step in computer vision systems like Convolutional Neural Networks or the Bag-of-Words method. The spatial pooling purpose is to combine neighbouring descriptors to obtain a single descriptor for a given region (local or global). The resultant combined vector must be as discriminant as possible, in other words, must contain relevant information, while removing irrelevant and confusing details. Maximum and average are the most common aggregation functions used in the pooling step. To improve the aggregation of relevant information without degrading their discriminative power for image classification, we introduce a simple but effective scheme based on Ordered Weighted Average (OWA) aggregation operators. We present a method to learn the weights of the OWA aggregation operator in a Bag-of-Words framework and in Convolutional Neural Networks, and provide an extensive evaluation showing that OWA based pooling outperforms classical aggregation operators.
Code (1)
Tasks
ClassificationGeneral Classificationimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
Graph Pooling by Edge Cut
Graph neural networks (GNNs) are very efficient at solving several tasks in graphs such as node classification or graph classification. They come from an adaptation of convolutional neural networks on images to graph str…
General ClassificationGraph ClassificationNode Classification3DViewGraph: Learning Global Features for 3D Shapes from A Graph of Unordered Views with Attention
Learning global features by aggregating information over multiple views has been shown to be effective for 3D shape analysis. For view aggregation in deep learning models, pooling has been applied extensively. However, p…
Ordinal Pooling Networks: For Preserving Information over Shrinking Feature Maps
In the framework of convolutional neural networks that lie at the heart of deep learning, downsampling is often performed with a max-pooling operation that only retains the element with maximum activation, while complete…
image-classificationImage ClassificationA Closed-Form Learned Pooling for Deep Classification Networks
In modern computer vision tasks, convolutional neural networks (CNNs) are indispensable for image classification tasks due to their efficiency and effectiveness. Part of their superiority compared to other architectures,…
ClassificationFormFoveationGeneral Classification+2Node-Aligned Graph Convolutional Network for Whole-Slide Image Representation and Classification
The large-scale whole-slide images (WSIs) facilitate the learning-based computational pathology methods. However, the gigapixel size of WSIs makes it hard to train a conventional model directly. Current approaches ty…
Clusteringgraph constructionMultiple Instance Learningwhole slide images