# Weakly Supervised PatchNets: Describing and Aggregating Local Patches for Scene Recognition

arXiv: https://arxiv.org/abs/1609.00153 · HTML: https://mlsanity.com/paper/1609.00153/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Sep 2016.

## Built on by (most cited first, 7 of 7)

- [Deep Learning for Scene Classification: A Survey](https://mlsanity.com/paper/2101.10531/) (2021)
- [Perception Framework through Real-Time Semantic Segmentation and Scene Recognition on a Wearable System for the Visually Impaired](https://mlsanity.com/paper/2103.04136/) (2021)
- [Attention-based Knowledge Distillation in Multi-attention Tasks: The Impact of a DCT-driven Loss](https://mlsanity.com/paper/2205.01997/) (2022)
- [Recent Advances in Scene Image Representation and Classification](https://mlsanity.com/paper/2206.07326/) (2022)
- [EnTri: Ensemble Learning with Tri-level Representations for Explainable Scene Recognition](https://mlsanity.com/paper/2307.12442/) (2023)
- [An embarrassingly simple comparison of machine learning algorithms for indoor scene classification](https://mlsanity.com/paper/2109.12261/) (2021)
- [Designing Deep Networks for Scene Recognition](https://mlsanity.com/paper/2303.07402/) (2023)

## Abstract (arXiv)

Traditional feature encoding scheme (e.g., Fisher vector) with local descriptors (e.g., SIFT) and recent convolutional neural networks (CNNs) are two classes of successful methods for image recognition. In this paper, we propose a hybrid representation, which leverages the discriminative capacity of CNNs and the simplicity of descriptor encoding schema for image recognition, with a focus on scene recognition. To this end, we make three main contributions from the following aspects. First, we propose a patch-level and end-to-end architecture to model the appearance of local patches, called em PatchNet. PatchNet is essentially a customized network trained in a weakly supervised manner, which uses the image-level supervision to guide the patch-level feature extraction. Second, we present a hybrid visual representation, called em VSAD, by utilizing the robust feature representations of PatchNet to describe local patches and exploiting the semantic probabilities of PatchNet to aggregate these local patches into a global representation. Third, based on the proposed VSAD representation, we propose a new state-of-the-art scene recognition approach, which achieves an excellent performance on two standard benchmarks: MIT Indoor67 (86.2%) and SUN397 (73.0%).