See More for Scene: Pairwise Consistency Learning for Scene Classification

Gongwei Chen, Xinhang Song, Bohan Wang, Shuqiang Jiang

Keywords: pairwise learning, scene classification, convolution neural networks

TL;DR: From the perspective of the focus area, we explore a new way to understand scene classification and propose a new learning scheme with a tailored loss in accordance with the empirical knowledge about scenes.

Abstract: Scene classification is a valuable classification subtask and has its own characteristics which still needs more in-depth studies. Basically, scene characteristics are distributed over the whole image, which cause the need of “seeing” comprehensive and informative regions. Previous works mainly focus on region discovery and aggregation, while rarely involves the inherent properties of CNN along with its potential ability to satisfy the requirements of scene classification. In this paper, we propose to understand scene images and the scene classification CNN models in terms of the focus area. From this new perspective, we find that large focus area is preferred in scene classification CNN models as a consequence of learning scene characteristics. Meanwhile, the analysis about existing training schemes helps us to understand the effects of focus area, and also raises the question about optimal training method for scene classification. Pursuing the better usage of scene characteristics, we propose a new learning scheme with a tailored loss in the goal of activating larger focus area on scene images. Since the supervision of the target regions to be enlarged is usually lacked, our alternative learning scheme is to erase already activated area, and allow the CNN models to activate more area during training. The proposed scheme is implemented by keeping the pairwise consistency between the output of the erased image and its original one. In particular, a tailored loss is proposed to keep such pairwise consistency by leveraging category-relevance information. Experiments on Places365 show the significant improvements of our method with various CNNs. Our method shows an inferior result on the object-centric dataset, ImageNet, which experimentally indicates that it captures the unique characteristics of scenes.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.