# Cross-convolutional-layer Pooling for Image Recognition

arXiv: https://arxiv.org/abs/1510.00921 · HTML: https://mlsanity.com/paper/1510.00921/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Oct 2015.

## Built on by (most cited first, 2 of 2)

- [Regularized Optimal Transport Layers for Generalized Global Pooling Operations](https://mlsanity.com/paper/2212.06339/) (2022)
- [A Benchmark Comparison of Visual Place Recognition Techniques for Resource-Constrained Embedded Platforms](https://mlsanity.com/paper/2109.11002/) (2021)

## Abstract (arXiv)

Recent studies have shown that a Deep Convolutional Neural Network (DCNN) pretrained on a large image dataset can be used as a universal image descriptor, and that doing so leads to impressive performance for a variety of image classification tasks. Most of these studies adopt activations from a single DCNN layer, usually the fully-connected layer, as the image representation. In this paper, we proposed a novel way to extract image representations from two consecutive convolutional layers: one layer is utilized for local feature extraction and the other serves as guidance to pool the extracted features. By taking different viewpoints of convolutional layers, we further develop two schemes to realize this idea. The first one directly uses convolutional layers from a DCNN. The second one applies the pretrained CNN on densely sampled image regions and treats the fully-connected activations of each image region as convolutional feature activations. We then train another convolutional layer on top of that as the pooling-guidance convolutional layer. By applying our method to three popular visual classification tasks, we find our first scheme tends to perform better on the applications which need strong discrimination on subtle object patterns within small regions while the latter excels in the cases that require discrimination on category-level patterns. Overall, the proposed method achieves superior performance over existing ways of extracting image representations from a DCNN.