# Scene recognition with CNNs: objects, scales and dataset bias

arXiv: https://arxiv.org/abs/1801.06867 · HTML: https://mlsanity.com/paper/1801.06867/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jan 2018.

## Built on by (most cited first, 18 of 18)

- [Object-to-Scene: Learning to Transfer Object Knowledge to Indoor Scene Recognition](https://mlsanity.com/paper/2108.00399/) (2021)
- [Deep Learning for Scene Classification: A Survey](https://mlsanity.com/paper/2101.10531/) (2021)
- [SRRM: Semantic Region Relation Model for Indoor Scene Recognition](https://mlsanity.com/paper/2305.08540/) (2023)
- [Unbiased Object Detection Beyond Frequency with Visually Prompted Image Synthesis](https://mlsanity.com/paper/2510.18229/) (2025)
- [Multi-resolution Outlier Pooling for Sorghum Classification](https://mlsanity.com/paper/2106.05748/) (2021)
- [Scene-centric vs. Object-centric Image-Text Cross-modal Retrieval: A Reproducibility Study](https://mlsanity.com/paper/2301.05174/) (2023)
- [Scale-Wise VAR is Secretly Discrete Diffusion](https://mlsanity.com/paper/2509.22636/) (2025)
- [Free Lunch for Co-Saliency Detection: Context Adjustment](https://mlsanity.com/paper/2108.02093/) (2021)
- [CYBORGS: Contrastively Bootstrapping Object Representations by Grounding in Segmentation](https://mlsanity.com/paper/2203.09343/) (2022)
- [EnTri: Ensemble Learning with Tri-level Representations for Explainable Scene Recognition](https://mlsanity.com/paper/2307.12442/) (2023)
- [Multi-task Prompt Words Learning for Social Media Content Generation](https://mlsanity.com/paper/2407.07771/) (2024)
- [Developing efficient transfer learning strategies for robust scene recognition in mobile robotics using pre-trained convolutional neural networks](https://mlsanity.com/paper/2107.11187/) (2021)
- [Scene Recognition with Objectness, Attribute and Category Learning](https://mlsanity.com/paper/2207.10174/) (2022)
- [Designing Deep Networks for Scene Recognition](https://mlsanity.com/paper/2303.07402/) (2023)
- [Semantic-embedded Similarity Prototype for Scene Recognition](https://mlsanity.com/paper/2308.05896/) (2023)
- [SNAP: A Benchmark for Testing the Effects of Capture Conditions on Fundamental Vision Tasks](https://mlsanity.com/paper/2505.15628/) (2025)
- [Improving Generative Adversarial Network Generalization for Facial Expression Synthesis](https://mlsanity.com/paper/2603.15648/) (2026)
- [ShieldCLIP: Selective Safety Alignment for Harmful Content Mitigation in Multimodal Foundation Models](https://mlsanity.com/paper/2609.39688/) (2026)

## Abstract (arXiv)

Since scenes are composed in part of objects, accurate recognition of scenes requires knowledge about both scenes and objects. In this paper we address two related problems: 1) scale induced dataset bias in multi-scale convolutional neural network (CNN) architectures, and 2) how to combine effectively scene-centric and object-centric knowledge (i.e. Places and ImageNet) in CNNs. An earlier attempt, Hybrid-CNN, showed that incorporating ImageNet did not help much. Here we propose an alternative method taking the scale into account, resulting in significant recognition gains. By analyzing the response of ImageNet-CNNs and Places-CNNs at different scales we find that both operate in different scale ranges, so using the same network for all the scales induces dataset bias resulting in limited performance. Thus, adapting the feature extractor to each particular scale (i.e. scale-specific CNNs) is crucial to improve recognition, since the objects in the scenes have their specific range of scales. Experimental results show that the recognition accuracy highly depends on the scale, and that simple yet carefully chosen multi-scale combinations of ImageNet-CNNs and Places-CNNs, can push the state-of-the-art recognition accuracy in SUN397 up to 66.26% (and even 70.17% with deeper architectures, comparable to human performance).