# Generalized orderless pooling performs implicit salient matching

arXiv: https://arxiv.org/abs/1705.00487 · HTML: https://mlsanity.com/paper/1705.00487/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 May 2017.

## Built on by (most cited first, 4 of 4)

- [SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization](https://mlsanity.com/paper/2209.02109/) (2022)
- [Re-rank Coarse Classification with Local Region Enhanced Features for Fine-Grained Image Recognition](https://mlsanity.com/paper/2102.09875/) (2021)
- [Fine-Grained Adversarial Semi-supervised Learning](https://mlsanity.com/paper/2110.05848/) (2021)
- [Enhancing Fine-Grained Classification for Low Resolution Images](https://mlsanity.com/paper/2105.00241/) (2021)

## Abstract (arXiv)

Most recent CNN architectures use average pooling as a final feature encoding step. In the field of fine-grained recognition, however, recent global representations like bilinear pooling offer improved performance. In this paper, we generalize average and bilinear pooling to "alpha-pooling", allowing for learning the pooling strategy during training. In addition, we present a novel way to visualize decisions made by these approaches. We identify parts of training images having the highest influence on the prediction of a given test image. It allows for justifying decisions to users and also for analyzing the influence of semantic parts. For example, we can show that the higher capacity VGG16 model focuses much more on the bird's head than, e.g., the lower-capacity VGG-M model when recognizing fine-grained bird categories. Both contributions allow us to analyze the difference when moving between average and bilinear pooling. In addition, experiments show that our generalized approach can outperform both across a variety of standard datasets.