# Hybrid CNN and Dictionary-Based Models for Scene Recognition and Domain Adaptation

arXiv: https://arxiv.org/abs/1601.07977 · HTML: https://mlsanity.com/paper/1601.07977/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jan 2016.

## Built on by (most cited first, 8 of 8)

- [Masked Contrastive Graph Representation Learning for Age Estimation](https://mlsanity.com/paper/2306.17798/) (2023)
- [CILF-CIAE: CLIP-driven Image-Language Fusion for Correcting Inverse Age Estimation](https://mlsanity.com/paper/2312.01758/) (2023)
- [Deep Learning for Scene Classification: A Survey](https://mlsanity.com/paper/2101.10531/) (2021)
- [Learning Muti-expert Distribution Calibration for Long-tailed Video Classification](https://mlsanity.com/paper/2205.10788/) (2022)
- [Multi-task Prompt Words Learning for Social Media Content Generation](https://mlsanity.com/paper/2407.07771/) (2024)
- [Scene Recognition with Objectness, Attribute and Category Learning](https://mlsanity.com/paper/2207.10174/) (2022)
- [Predicting Topological Maps for Visual Navigation in Unexplored Environments](https://mlsanity.com/paper/2211.12649/) (2022)
- [Semantic-embedded Similarity Prototype for Scene Recognition](https://mlsanity.com/paper/2308.05896/) (2023)

## Abstract (arXiv)

Convolutional neural network (CNN) has achieved state-of-the-art performance in many different visual tasks. Learned from a large-scale training dataset, CNN features are much more discriminative and accurate than the hand-crafted features. Moreover, CNN features are also transferable among different domains. On the other hand, traditional dictionarybased features (such as BoW and SPM) contain much more local discriminative and structural information, which is implicitly embedded in the images. To further improve the performance, in this paper, we propose to combine CNN with dictionarybased models for scene recognition and visual domain adaptation. Specifically, based on the well-tuned CNN models (e.g., AlexNet and VGG Net), two dictionary-based representations are further constructed, namely mid-level local representation (MLR) and convolutional Fisher vector representation (CFV). In MLR, an efficient two-stage clustering method, i.e., weighted spatial and feature space spectral clustering on the parts of a single image followed by clustering all representative parts of all images, is used to generate a class-mixture or a classspecific part dictionary. After that, the part dictionary is used to operate with the multi-scale image inputs for generating midlevel representation. In CFV, a multi-scale and scale-proportional GMM training strategy is utilized to generate Fisher vectors based on the last convolutional layer of CNN. By integrating the complementary information of MLR, CFV and the CNN features of the fully connected layer, the state-of-the-art performance can be achieved on scene recognition and domain adaptation problems. An interested finding is that our proposed hybrid representation (from VGG net trained on ImageNet) is also complementary with GoogLeNet and/or VGG-11 (trained on Place205) greatly.