paper-with-me

Papers

PatternNet: Visual Pattern Mining with Deep Neural Network

2017-03-18 · Hongzhi Li, Joseph G. Ellis, Lei Zhang, Shih-Fu Chang

Visual patterns represent the discernible regularity in the visual world. They capture the essential nature of visual objects or scenes. Understanding and modeling visual patterns is a fundamental problem in visual recognition that has wide ranging applications. In this paper, we study the problem of visual pattern mining and propose a novel deep neural network architecture called PatternNet for discovering these patterns that are both discriminative and representative. The proposed PatternNet leverages the filters in the last convolution layer of a convolutional neural network to find locally consistent visual patches, and by combining these filters we can effectively discover unique visual patterns. In addition, PatternNet can discover visual patterns efficiently without performing expensive image patch sampling, and this advantage provides an order of magnitude speedup compared to most other approaches. We evaluate the proposed PatternNet subjectively by showing randomly selected visual patterns which are discovered by our method and quantitatively by performing image classification with the identified visual patterns and comparing our performance with the current state-of-the-art. We also directly evaluate the quality of the discovered visual patterns by leveraging the identified patterns as proposed objects in an image and compare with other relevant methods. Our proposed network and procedure, PatterNet, is able to outperform competing methods for the tasks described.

📄 PDF Abstract BibTeX arXiv:1703.06339

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classification

Similar Papers 제목 키워드 기반

PatternNet: A Benchmark Dataset for Performance Evaluation of Remote Sensing Image Retrieval

2017-06-11 · Weixun Zhou, Shawn Newsam, Congmin Li, Zhenfeng Shao

Remote sensing image retrieval(RSIR), which aims to efficiently retrieve data of interest from large collections of remote sensing data, is a fundamental task in remote sensing. Over the past several decades, there has b…

Image RetrievalLand Cover ClassificationRetrieval

Learning how to explain neural networks: PatternNet and PatternAttribution

2017-05-16 · ICLR 2018 1 · Pieter-Jan Kindermans, Kristof T. Schütt, Maximilian Alber, Klaus-Robert Müller 외

DeConvNet, Guided BackProp, LRP, were invented to better understand deep neural networks. We show that these methods do not produce the theoretically correct explanation for a linear model. Yet they are used on multi-lay…

ArcGate: Adaptive Arctangent Gated Activation

2026-05-14 · Avik Bhattacharya, Siddhant Dnyanesh Gole, Subhasis Chaudhuri, Alejandro C. Frery 외 arxiv

Activation functions are central to deep networks, influencing non-linearity, feature learning, convergence, and robustness. This paper proposes the Adaptive Arctangent Gated Activation (ArcGate) function, a flexible for…

iNNvestigate neural networks!

2018-08-13 · Maximilian Alber, Sebastian Lapuschkin, Philipp Seegerer, Miriam Hägele 외

In recent years, deep neural networks have revolutionized many application domains of machine learning and are key components of many critical decision or predictive processes. Therefore, it is crucial that domain specia…

Interpretable Machine Learning

Mining Mid-level Visual Patterns with Deep CNN Activations

2015-06-21 · Yao Li, Lingqiao Liu, Chunhua Shen, Anton Van Den Hengel

The purpose of mid-level visual element discovery is to find clusters of image patches that are both representative and discriminative. Here we study this problem from the prospective of pattern mining while relying on t…