Deep Spatial Pyramid: The Devil is Once Again in the Details
In this paper we show that by carefully making good choices for various detailed but important factors in a visual recognition framework using deep learning features, one can achieve a simple, efficient, yet highly accurate image classification system. We first list 5 important factors, based on both existing researches and ideas proposed in this paper. These important detailed factors include: 1) $\ell_2$ matrix normalization is more effective than unnormalized or $\ell_2$ vector normalization, 2) the proposed natural deep spatial pyramid is very effective, and 3) a very small $K$ in Fisher Vectors surprisingly achieves higher accuracy than normally used large $K$ values. Along with other choices (convolutional activations and multiple scales), the proposed DSP framework is not only intuitive and efficient, but also achieves excellent classification accuracy on many benchmark datasets. For example, DSP's accuracy on SUN397 is 59.78%, significantly higher than previous state-of-the-art (53.86%).
Code (0)
등록된 구현이 없습니다.
Tasks
General Classificationimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
Suppress and Balance: A Simple Gated Network for Salient Object Detection
Most salient object detection approaches use U-Net or feature pyramid networks (FPN) as their basic structures. These methods ignore two key problems when the encoder exchanges information with the decoder: one is the la…
DecoderDichotomous Image Segmentationobject-detectionObject Detection+2DeViL: Decoding Vision features into Language
Post-hoc explanation methods have often been criticised for abstracting away the decision-making process of deep neural networks. In this work, we would like to provide natural language descriptions for what different la…
Decision MakingLanguage ModelingLanguage Modelling“Devils Are in the Details”: Annotating Specificity of Clinical Advice from Medical Literature
Prior studies have raised concerns over specificity issues in clinical advice. Lacking specificity — explicitly discussed detailed information — may affect the quality and implementation of clinical advice in medical pra…
SpecificityImproving Optical Flow on a Pyramid Level
In this work we review the coarse-to-fine spatial feature pyramid concept, which is used in state-of-the-art optical flow estimation networks to make exploration of the pixel flow search space computationally tractable a…
BlockingOptical Flow EstimationPyramid Attention Network for Semantic Segmentation
A Pyramid Attention Network(PAN) is proposed to exploit the impact of global contextual information in semantic segmentation. Different from most existing works, we combine attention mechanism and spatial pyramid to extr…
DecoderSegmentationSemantic SegmentationThermal Image Segmentation