# Scene Recognition with Objectness, Attribute and Category Learning

arXiv: https://arxiv.org/abs/2207.10174 · HTML: https://mlsanity.com/paper/2207.10174/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 59 references that are in the map.
- First posted on arXiv 20 Jul 2022.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Taskonomy: Disentangling Task Transfer Learning](https://mlsanity.com/paper/1804.08328/) (2018)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition](https://mlsanity.com/paper/1310.1531/) (2013)
- [Improving Person Re-identification by Attribute and Identity Learning](https://mlsanity.com/paper/1703.07220/) (2017)
- [AANet: Attribute Attention Network for Person Re-Identifications](https://mlsanity.com/paper/1912.09021/) (2019)
- [Semantic-Aware Scene Recognition](https://mlsanity.com/paper/1909.02410/) (2019)
- [Multi-scale Orderless Pooling of Deep Convolutional Activation Features](https://mlsanity.com/paper/1403.1840/) (2014)
- [Multi-scale recognition with DAG-CNNs](https://mlsanity.com/paper/1505.05232/) (2015)
- [Scene recognition with CNNs: objects, scales and dataset bias](https://mlsanity.com/paper/1801.06867/) (2018)
- [Scene Recognition with Prototype-agnostic Scene Layout](https://mlsanity.com/paper/1909.03234/) (2019)
- [Knowledge Guided Disambiguation for Large-Scale Scene Classification with Multi-Resolution CNNs](https://mlsanity.com/paper/1610.01119/) (2016)
- [Hybrid CNN and Dictionary-Based Models for Scene Recognition and Domain Adaptation](https://mlsanity.com/paper/1601.07977/) (2016)
- [Learning Attribute Representation for Human Activity Recognition](https://mlsanity.com/paper/1802.00761/) (2018)

## Abstract (arXiv)

Scene classification has established itself as a challenging research problem. Compared to images of individual objects, scene images could be much more semantically complex and abstract. Their difference mainly lies in the level of granularity of recognition. Yet, image recognition serves as a key pillar for the good performance of scene recognition as the knowledge attained from object images can be used for accurate recognition of scenes. The existing scene recognition methods only take the category label of the scene into consideration. However, we find that the contextual information that contains detailed local descriptions are also beneficial in allowing the scene recognition model to be more discriminative. In this paper, we aim to improve scene recognition using attribute and category label information encoded in objects. Based on the complementarity of attribute and category labels, we propose a Multi-task Attribute-Scene Recognition (MASR) network which learns a category embedding and at the same time predicts scene attributes. Attribute acquisition and object annotation are tedious and time consuming tasks. We tackle the problem by proposing a partially supervised annotation strategy in which human intervention is significantly reduced. The strategy provides a much more cost-effective solution to real world scenarios, and requires considerably less annotation efforts. Moreover, we re-weight the attribute predictions considering the level of importance indicated by the object detected scores. Using the proposed method, we efficiently annotate attribute labels for four large-scale datasets, and systematically investigate how scene and attribute recognition benefit from each other. The experimental results demonstrate that MASR learns a more discriminative representation and achieves competitive recognition performance compared to the state-of-the-art methods