Learning Image Relations with Contrast Association Networks
This addresses a key challenge in computer vision for tasks like optical flow and stereo disparity, but it appears incremental as it builds on existing neural network approaches with a new module.
The paper tackled the problem of inferring relations between images, such as optical flow and stereo disparity, by proposing a new neural network module called contrast association unit (CAU) that explicitly models these relations. Experiments demonstrated that networks with CAUs were more effective in learning five fundamental image transformations compared to conventional neural networks.
Inferring the relations between two images is an important class of tasks in computer vision. Examples of such tasks include computing optical flow and stereo disparity. We treat the relation inference tasks as a machine learning problem and tackle it with neural networks. A key to the problem is learning a representation of relations. We propose a new neural network module, contrast association unit (CAU), which explicitly models the relations between two sets of input variables. Due to the non-negativity of the weights in CAU, we adopt a multiplicative update algorithm for learning these weights. Experiments show that neural networks with CAUs are more effective in learning five fundamental image transformations than conventional neural networks.