Visualizing Object Detection Features
This work provides insights for researchers and practitioners in computer vision by highlighting inherent feature space limitations in object detectors, though it is incremental as it focuses on visualization rather than solving the problem.
The paper tackled the problem of understanding object detection systems by introducing algorithms to visualize feature spaces, revealing that high-scoring false alarms appear similar to true positives in feature space, suggesting feature space limitations rather than dataset or algorithm issues.
We introduce algorithms to visualize feature spaces used by object detectors. Our method works by inverting a visual feature back to multiple natural images. We found that these visualizations allow us to analyze object detection systems in new ways and gain new insight into the detector's failures. For example, when we visualize the features for high scoring false alarms, we discovered that, although they are clearly wrong in image space, they do look deceptively similar to true positives in feature space. This result suggests that many of these false alarms are caused by our choice of feature space, and supports that creating a better learning algorithm or building bigger datasets is unlikely to correct these errors. By visualizing feature spaces, we can gain a more intuitive understanding of recognition systems.