# Pixel Objectness

arXiv: https://arxiv.org/abs/1701.05349 · HTML: https://mlsanity.com/paper/1701.05349/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jan 2017.

## Built on by (most cited first, 2 of 2)

- [On Moving Object Segmentation from Monocular Video with Transformers](https://mlsanity.com/paper/2411.19141/) (2024)
- [DeePaste -- Inpainting for Pasting](https://mlsanity.com/paper/2112.10600/) (2021)

## Abstract (arXiv)

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 on foreground segmentation for ImageNet and MIT Object Discovery datasets. Furthermore, on over 1 million images, we show that it generalizes well to segment 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.