# Knowledge Guided Disambiguation for Large-Scale Scene Classification with Multi-Resolution CNNs

arXiv: https://arxiv.org/abs/1610.01119 · HTML: https://mlsanity.com/paper/1610.01119/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Oct 2016.

## Built on by (most cited first, 16 of 16)

- [Semantic Image Inversion and Editing using Rectified Stochastic Differential Equations](https://mlsanity.com/paper/2410.10792/) (2024)
- [Isometric Representation Learning for Disentangled Latent Space of Diffusion Models](https://mlsanity.com/paper/2407.11451/) (2024)
- [Deep Learning for Scene Classification: A Survey](https://mlsanity.com/paper/2101.10531/) (2021)
- [CoMAE: Single Model Hybrid Pre-training on Small-Scale RGB-D Datasets](https://mlsanity.com/paper/2302.06148/) (2023)
- [Tackling Distribution Shifts in Task-Oriented Communication with Information Bottleneck](https://mlsanity.com/paper/2405.09514/) (2024)
- [SRRM: Semantic Region Relation Model for Indoor Scene Recognition](https://mlsanity.com/paper/2305.08540/) (2023)
- [FINE: Factorizing Knowledge for Initialization of Variable-sized Diffusion Models](https://mlsanity.com/paper/2409.19289/) (2024)
- [Optimal Transport for Rectified Flow Image Editing: Unifying Inversion-Based and Direct Methods](https://mlsanity.com/paper/2508.02363/) (2025)
- [A Unified Hierarchical Framework for Fine-grained Cross-view Geo-localization over Large-scale Scenarios](https://mlsanity.com/paper/2505.07622/) (2025)
- [DCAC: Dynamic Class-Aware Cache Creates Stronger Out-of-Distribution Detectors](https://mlsanity.com/paper/2601.12468/) (2026)
- [Scene Recognition with Objectness, Attribute and Category Learning](https://mlsanity.com/paper/2207.10174/) (2022)
- [Semantic-guided modeling of spatial relation and object co-occurrence for indoor scene recognition](https://mlsanity.com/paper/2305.12661/) (2023)
- [Semantic-embedded Similarity Prototype for Scene Recognition](https://mlsanity.com/paper/2308.05896/) (2023)
- [The Role of Active Learning in Modern Machine Learning](https://mlsanity.com/paper/2508.00586/) (2025)
- [Constraint-based Pre-training: From Structured Constraints to Scalable Model Initialization](https://mlsanity.com/paper/2604.14769/) (2026)
- [DynProto: Dynamic Prototype Evolution for Out-of-Distribution Detection](https://mlsanity.com/paper/2604.23729/) (2026)

## Abstract (arXiv)

Convolutional Neural Networks (CNNs) have made remarkable progress on scene recognition, partially due to these recent large-scale scene datasets, such as the Places and Places2. Scene categories are often defined by multi-level information, including local objects, global layout, and background environment, thus leading to large intra-class variations. In addition, with the increasing number of scene categories, label ambiguity has become another crucial issue in large-scale classification. This paper focuses on large-scale scene recognition and makes two major contributions to tackle these issues. First, we propose a multi-resolution CNN architecture that captures visual content and structure at multiple levels. The multi-resolution CNNs are composed of coarse resolution CNNs and fine resolution CNNs, which are complementary to each other. Second, we design two knowledge guided disambiguation techniques to deal with the problem of label ambiguity. (i) We exploit the knowledge from the confusion matrix computed on validation data to merge ambiguous classes into a super category. (ii) We utilize the knowledge of extra networks to produce a soft label for each image. Then the super categories or soft labels are employed to guide CNN training on the Places2. We conduct extensive experiments on three large-scale image datasets (ImageNet, Places, and Places2), demonstrating the effectiveness of our approach. Furthermore, our method takes part in two major scene recognition challenges, and achieves the second place at the Places2 challenge in ILSVRC 2015, and the first place at the LSUN challenge in CVPR 2016. Finally, we directly test the learned representations on other scene benchmarks, and obtain the new state-of-the-art results on the MIT Indoor67 (86.7%) and SUN397 (72.0%). We release the code and models at~urlhttps://github.com/wanglimin/MRCNN-Scene-Recognition.