Compact Bilinear Pooling
Bilinear models has been shown to achieve impressive performance on a wide range of visual tasks, such as semantic segmentation, fine grained recognition and face recognition. However, bilinear features are high dimensional, typically on the order of hundreds of thousands to a few million, which makes them impractical for subsequent analysis. We propose two compact bilinear representations with the same discriminative power as the full bilinear representation but with only a few thousand dimensions. Our compact representations allow back-propagation of classification errors enabling an end-to-end optimization of the visual recognition system. The compact bilinear representations are derived through a novel kernelized analysis of bilinear pooling which provide insights into the discriminative power of bilinear pooling, and a platform for further research in compact pooling methods. Experimentation illustrate the utility of the proposed representations for image classification and few-shot learning across several datasets.
Code (7)
Tasks
Face RecognitionFew-Shot LearningGeneral Classificationimage-classificationImage ClassificationSemantic SegmentationSimilar Papers 제목 키워드 기반
Hadamard Product for Low-rank Bilinear Pooling
Bilinear models provide rich representations compared with linear models. They have been applied in various visual tasks, such as object recognition, segmentation, and visual question-answering, to get state-of-the-art p…
Visual Question AnsweringVisual Question Answering (VQA)MoNet: Moments Embedding Network
Bilinear pooling has been recently proposed as a feature encoding layer, which can be used after the convolutional layers of a deep network, to improve performance in multiple vision tasks. Different from conventional gl…
Toward Faster and Simpler Matrix Normalization via Rank-1 Update
Bilinear pooling has achieved an impressive improvement in many computer vision tasks. Recent studies discover that matrix normalization is vital for improving the performance of bilinear pooling. Nevertheless, tradition…
GPUDo ReLU Networks Have An Edge When Approximating Compactly-Supported Functions?
We study the problem of approximating compactly-supported integrable functions while implementing their support set using feedforward neural networks. Our first main result transcribes this "structured" approximation pro…
Low-rank Bilinear Pooling for Fine-Grained Classification
Pooling second-order local feature statistics to form a high-dimensional bilinear feature has been shown to achieve state-of-the-art performance on a variety of fine-grained classification tasks. To address the computati…
ClassificationGeneral Classification