# Learning to Segment Object Candidates

arXiv: https://arxiv.org/abs/1506.06204 · HTML: https://mlsanity.com/paper/1506.06204/

## Key facts

- Cited by 79 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jun 2015.

## Built on by (most cited first, 30 of 79)

- [Fast Segment Anything](https://mlsanity.com/paper/2306.12156/) (2023)
- [Decoupling Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/2112.07910/) (2021)
- [RTMDet: An Empirical Study of Designing Real-Time Object Detectors](https://mlsanity.com/paper/2212.07784/) (2022)
- [Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals](https://mlsanity.com/paper/2102.06191/) (2021)
- [Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation](https://mlsanity.com/paper/2104.04691/) (2021)
- [Learning Open-World Object Proposals without Learning to Classify](https://mlsanity.com/paper/2108.06753/) (2021)
- [Class-agnostic Object Detection with Multi-modal Transformer](https://mlsanity.com/paper/2111.11430/) (2021)
- [Open-World Entity Segmentation](https://mlsanity.com/paper/2107.14228/) (2021)
- [Opening up Open-World Tracking](https://mlsanity.com/paper/2104.11221/) (2021)
- [Incremental Few-Shot Instance Segmentation](https://mlsanity.com/paper/2105.05312/) (2021)
- [Amodal Ground Truth and Completion in the Wild](https://mlsanity.com/paper/2312.17247/) (2023)
- [Local contrastive loss with pseudo-label based self-training for semi-supervised medical image segmentation](https://mlsanity.com/paper/2112.09645/) (2021)
- [Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity](https://mlsanity.com/paper/2204.06107/) (2022)
- [Learning to Detect Every Thing in an Open World](https://mlsanity.com/paper/2112.01698/) (2021)
- [EDTER: Edge Detection with Transformer](https://mlsanity.com/paper/2203.08566/) (2022)
- [SOLO: A Simple Framework for Instance Segmentation](https://mlsanity.com/paper/2106.15947/) (2021)
- [Instance-wise Occlusion and Depth Orders in Natural Scenes](https://mlsanity.com/paper/2111.14562/) (2021)
- [CAT: LoCalization and IdentificAtion Cascade Detection Transformer for Open-World Object Detection](https://mlsanity.com/paper/2301.01970/) (2023)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [Visiting the Invisible: Layer-by-Layer Completed Scene Decomposition](https://mlsanity.com/paper/2104.05367/) (2021)
- [Instance Shadow Detection with A Single-Stage Detector](https://mlsanity.com/paper/2207.04614/) (2022)
- [Active Fire Detection in Landsat-8 Imagery: a Large-Scale Dataset and a Deep-Learning Study](https://mlsanity.com/paper/2101.03409/) (2021)
- [Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation](https://mlsanity.com/paper/2104.04782/) (2021)
- [Capturing the objects of vision with neural networks](https://mlsanity.com/paper/2109.03351/) (2021)
- [Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images](https://mlsanity.com/paper/2104.01526/) (2021)
- [ContrastMask: Contrastive Learning to Segment Every Thing](https://mlsanity.com/paper/2203.09775/) (2022)
- [Learning Equivariant Segmentation with Instance-Unique Querying](https://mlsanity.com/paper/2210.00911/) (2022)
- [Unknown Object Segmentation from Stereo Images](https://mlsanity.com/paper/2103.06796/) (2021)
- [A^2-FPN: Attention Aggregation based Feature Pyramid Network for Instance Segmentation](https://mlsanity.com/paper/2105.03186/) (2021)
- [RICE: Refining Instance Masks in Cluttered Environments with Graph Neural Networks](https://mlsanity.com/paper/2106.15711/) (2021)

## Abstract (arXiv)

Recent object detection systems rely on two critical steps: (1) a set of object proposals is predicted as efficiently as possible, and (2) this set of candidate proposals is then passed to an object classifier. Such approaches have been shown they can be fast, while achieving the state of the art in detection performance. In this paper, we propose a new way to generate object proposals, introducing an approach based on a discriminative convolutional network. Our model is trained jointly with two objectives: given an image patch, the first part of the system outputs a class-agnostic segmentation mask, while the second part of the system outputs the likelihood of the patch being centered on a full object. At test time, the model is efficiently applied on the whole test image and generates a set of segmentation masks, each of them being assigned with a corresponding object likelihood score. We show that our model yields significant improvements over state-of-the-art object proposal algorithms. In particular, compared to previous approaches, our model obtains substantially higher object recall using fewer proposals. We also show that our model is able to generalize to unseen categories it has not seen during training. Unlike all previous approaches for generating object masks, we do not rely on edges, superpixels, or any other form of low-level segmentation.