Pixel Objectness

We propose an end-to-end learning framework for generating foreground object segmentations. Given a single novel image, our approach produces pixel-level masks for all "object-like" regions---even for object categories never seen during training. We formulate the task as a structured prediction problem of assigning foreground/background labels to all pixels, implemented using a deep fully convolutional network. Key to our idea is training with a mix of image-level object category examples together with relatively few images with boundary-level annotations. Our method substantially improves the state-of-the-art for foreground segmentation accuracy on the ImageNet and MIT Object Discovery datasets---with 19% improvements in some cases. Furthermore, with extensive evaluation on over 1 million images, we show it generalizes well to segment even object categories unseen in the foreground maps used for training. Finally, we demonstrate how our approach benefits image retrieval and image retargeting, both of which flourish when given our high-quality foreground maps.