# The Treasure beneath Convolutional Layers: Cross-convolutional-layer Pooling for Image Classification

arXiv: https://arxiv.org/abs/1411.7466 · HTML: https://mlsanity.com/paper/1411.7466/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2014.

## Built on by (most cited first, 9 of 9)

- [Fine-Grained Image Analysis with Deep Learning: A Survey](https://mlsanity.com/paper/2111.06119/) (2021)
- [SEMICON: A Learning-to-hash Solution for Large-scale Fine-grained Image Retrieval](https://mlsanity.com/paper/2209.13833/) (2022)
- [E-PixelHop: An Enhanced PixelHop Method for Object Classification](https://mlsanity.com/paper/2107.02966/) (2021)
- [A Survey on Image Aesthetic Assessment](https://mlsanity.com/paper/2103.11616/) (2021)
- [NOAH: Learning Pairwise Object Category Attentions for Image Classification](https://mlsanity.com/paper/2402.02377/) (2024)
- [Enhancing Fine-Grained Visual Recognition in the Low-Data Regime Through Feature Magnitude Regularization](https://mlsanity.com/paper/2409.01672/) (2024)
- [A Novel Feature Extraction Model for the Detection of Plant Disease from Leaf Images in Low Computational Devices](https://mlsanity.com/paper/2410.01854/) (2024)
- [AI-Powered Deepfake Detection Using CNN and Vision Transformer Architectures](https://mlsanity.com/paper/2601.01281/) (2026)
- [A Survey on Semantic Communication for Vision: Categories, Frameworks, Enabling Techniques, and Applications](https://mlsanity.com/paper/2601.22202/) (2026)

## Abstract (arXiv)

A number of recent studies have shown that a Deep Convolutional Neural Network (DCNN) pretrained on a large dataset can be adopted as a universal image description which leads to astounding performance in many visual classification tasks. Most of these studies, if not all, adopt activations of the fully-connected layer of a DCNN as the image or region representation and it is believed that convolutional layer activations are less discriminative. This paper, however, advocates that if used appropriately convolutional layer activations can be turned into a powerful image representation which enjoys many advantages over fully-connected layer activations. This is achieved by adopting a new technique proposed in this paper called cross-convolutional-layer pooling. More specifically, it extracts subarrays of feature maps of one convolutional layer as local features and pools the extracted features with the guidance of feature maps of the successive convolutional layer. Compared with exising methods that apply DCNNs in the local feature setting, the proposed method is significantly faster since it requires much fewer times of DCNN forward computation. Moreover, it avoids the domain mismatch issue which is usually encountered when applying fully connected layer activations to describe local regions. By applying our method to four popular visual classification tasks, it is demonstrated that the proposed method can achieve comparable or in some cases significantly better performance than existing fully-connected layer based image representations while incurring much lower computational cost.