Object Recognition with and without Objects
This work addresses how visual cues are learned in object recognition, revealing differences between human and network mechanisms, but it is incremental as it builds on existing deep learning methods.
The paper investigates object recognition by training deep neural networks separately on foreground objects and background contexts, finding that networks outperform humans when given only context but humans excel with only objects, and combining networks improves performance.
While recent deep neural networks have achieved a promising performance on object recognition, they rely implicitly on the visual contents of the whole image. In this paper, we train deep neural net- works on the foreground (object) and background (context) regions of images respectively. Consider- ing human recognition in the same situations, net- works trained on the pure background without ob- jects achieves highly reasonable recognition performance that beats humans by a large margin if only given context. However, humans still outperform networks with pure object available, which indicates networks and human beings have different mechanisms in understanding an image. Furthermore, we straightforwardly combine multiple trained networks to explore different visual cues learned by different networks. Experiments show that useful visual hints can be explicitly learned separately and then combined to achieve higher performance, which verifies the advantages of the proposed framework.