# Semantic-Aware Scene Recognition

arXiv: https://arxiv.org/abs/1909.02410 · HTML: https://mlsanity.com/paper/1909.02410/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Sep 2019.

## Built on by (most cited first, 30 of 43)

- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [The Platonic Representation Hypothesis](https://mlsanity.com/paper/2405.07987/) (2024)
- [Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey](https://mlsanity.com/paper/2308.09388/) (2023)
- [UniBind: LLM-Augmented Unified and Balanced Representation Space to Bind Them All](https://mlsanity.com/paper/2403.12532/) (2024)
- [PixMIM: Rethinking Pixel Reconstruction in Masked Image Modeling](https://mlsanity.com/paper/2303.02416/) (2023)
- [ChatGPT-Powered Hierarchical Comparisons for Image Classification](https://mlsanity.com/paper/2311.00206/) (2023)
- [FF-NSL: Feed-Forward Neural-Symbolic Learner](https://mlsanity.com/paper/2106.13103/) (2021)
- [Object-to-Scene: Learning to Transfer Object Knowledge to Indoor Scene Recognition](https://mlsanity.com/paper/2108.00399/) (2021)
- [BORM: Bayesian Object Relation Model for Indoor Scene Recognition](https://mlsanity.com/paper/2108.00397/) (2021)
- [Deep Learning for Scene Classification: A Survey](https://mlsanity.com/paper/2101.10531/) (2021)
- [Energy-based Hopfield Boosting for Out-of-Distribution Detection](https://mlsanity.com/paper/2405.08766/) (2024)
- [Graph Concept Bottleneck Models](https://mlsanity.com/paper/2508.14255/) (2025)
- [Navigating the Latent Space Dynamics of Neural Models](https://mlsanity.com/paper/2505.22785/) (2025)
- [A Unified Approach Towards Active Learning and Out-of-Distribution Detection](https://mlsanity.com/paper/2405.11337/) (2024)
- [ATLAS: Adapter-Based Multi-Modal Continual Learning with a Two-Stage Learning Strategy](https://mlsanity.com/paper/2410.10923/) (2024)
- [Rethinking Person Re-Identification via Semantic-Based Pretraining](https://mlsanity.com/paper/2110.05074/) (2021)
- [SRRM: Semantic Region Relation Model for Indoor Scene Recognition](https://mlsanity.com/paper/2305.08540/) (2023)
- [Reassessing the Validity of Spurious Correlations Benchmarks](https://mlsanity.com/paper/2409.04188/) (2024)
- [Outlier Synthesis via Hamiltonian Monte Carlo for Out-of-Distribution Detection](https://mlsanity.com/paper/2501.16718/) (2025)
- [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)
- [Explainable fetal ultrasound quality assessment with progressive concept bottleneck models](https://mlsanity.com/paper/2211.10630/) (2022)
- [Narrowing the Focus: Learned Optimizers for Pretrained Models](https://mlsanity.com/paper/2408.09310/) (2024)
- [Generate Any Scene: Scene Graph Driven Data Synthesis for Visual Generation Training](https://mlsanity.com/paper/2412.08221/) (2024)
- [Uncertainty-based Visual Question Answering: Estimating Semantic Inconsistency between Image and Knowledge Base](https://mlsanity.com/paper/2207.13242/) (2022)
- [On the challenges to learn from Natural Data Streams](https://mlsanity.com/paper/2301.03495/) (2023)
- [Inter-object Discriminative Graph Modeling for Indoor Scene Recognition](https://mlsanity.com/paper/2311.05919/) (2023)
- [Towards Reliable AI Model Deployments: Multiple Input Mixup for Out-of-Distribution Detection](https://mlsanity.com/paper/2312.15514/) (2023)
- [Split Adaptation for Pre-trained Vision Transformers](https://mlsanity.com/paper/2503.00441/) (2025)
- [Attention-based Knowledge Distillation in Multi-attention Tasks: The Impact of a DCT-driven Loss](https://mlsanity.com/paper/2205.01997/) (2022)

## Abstract (arXiv)

Scene recognition is currently one of the top-challenging research fields in computer vision. This may be due to the ambiguity between classes: images of several scene classes may share similar objects, which causes confusion among them. The problem is aggravated when images of a particular scene class are notably different. Convolutional Neural Networks (CNNs) have significantly boosted performance in scene recognition, albeit it is still far below from other recognition tasks (e.g., object or image recognition). In this paper, we describe a novel approach for scene recognition based on an end-to-end multi-modal CNN that combines image and context information by means of an attention module. Context information, in the shape of semantic segmentation, is used to gate features extracted from the RGB image by leveraging on information encoded in the semantic representation: the set of scene objects and stuff, and their relative locations. This gating process reinforces the learning of indicative scene content and enhances scene disambiguation by refocusing the receptive fields of the CNN towards them. Experimental results on four publicly available datasets show that the proposed approach outperforms every other state-of-the-art method while significantly reducing the number of network parameters. All the code and data used along this paper is available at https://github.com/vpulab/Semantic-Aware-Scene-Recognition