Learning Good Representation via Continuous Attention
This work addresses representation learning for object recognition in AI, but appears incremental as it combines existing UL and RL techniques.
The paper tackles learning good object representations by using continuous attention driven by intrinsic motivation from unsupervised learning to guide reinforcement learning, and demonstrates effectiveness in simulated environments for few-shot object recognition.
In this paper we present our scientific discovery that good representation can be learned via continuous attention during the interaction between Unsupervised Learning(UL) and Reinforcement Learning(RL) modules driven by intrinsic motivation. Specifically, we designed intrinsic rewards generated from UL modules for driving the RL agent to focus on objects for a period of time and to learn good representations of objects for later object recognition task. We evaluate our proposed algorithm in both with and without extrinsic reward settings. Experiments with end-to-end training in simulated environments with applications to few-shot object recognition demonstrated the effectiveness of the proposed algorithm.