computer-vision-4

Weakly-supervised instance segmentation

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in weakly-supervised-instance-segmentation-4

Trend

Dataset

Best Model

Actions

COCO test-dev

PASCAL VOC 2012 val

COCO 2017 val

Libraries

i

Use these libraries to find weakly-supervised-instance-segmentation-4 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision

Anima Anandkumar, Yuke Zhu, Zhiding Yu, Guilin Liu, Larry S. Davis, C. Choy, Shiyi Lan, Subhashree Radhakrishnan•Wed May 12 2021

A self-ensembling framework where instance segmentation and semantic correspondence are jointly guided by a structured teacher in addition to the bounding box supervision, which shows a symbiotic relationship where the two tasks mutually benefit from each other.

91

Content

COCO 2017 val

0

Paper Graph

BoxInst: High-Performance Instance Segmentation with Box Annotations

Chunhua Shen, Hao Chen, Xinlong Wang, Zhi Tian•Wed Dec 02 2020

The core idea is to redesign the loss of learning masks in instance segmentation, with no modification to the segmentation network itself, and demonstrates that the redesigned mask loss can yield surprisingly high-quality instance masks with only box annotations.

300 0

Paper Graph

Pointly-Supervised Instance Segmentation

A. Kirillov, Omkar M. Parkhi, Bowen Cheng•Mon Apr 12 2021

The existing instance segmentation models developed for full mask supervision can be seamlessly trained with point-based supervision collected via the proposed point annotation scheme, which is approximately 5 times faster than annotating full object masks, making high-quality instance segmentations more accessible in practice.

136 0

Paper Graph

Weakly Supervised Instance Segmentation Using Class Peak Response

Qiang Qiu, Jianbin Jiao, Qixiang Ye, Yanzhao Zhou, Yi Zhu•Mon Apr 02 2018

This paper addresses the challenging image-level supervised instance segmentation task by exploiting class peak responses to enable a classification network for instance mask extraction, and reports state-of-the-art results on popular benchmarks, including PASCAL VOC 2012 and MS COCO.

291 0

Paper Graph

Weakly- and Semi-Supervised Panoptic Segmentation

Philip H. S. Torr, Anurag Arnab, Qizhu Li•Thu Aug 09 2018

A weakly supervised model that jointly performs both semantic- and instance-segmentation and is able to segment both “thing” and “stuff” classes, and thus explain all the pixels in the image.

169 0

Paper Graph

Weakly Supervised Instance Segmentation using the Bounding Box Tightness Prior

Kuang-Jui Hsu, Yen-Yu Lin, Yung-Yu Chuang, Cheng-Chun Hsu, Chung-Chi Tsai•Mon Dec 31 2018

The proposed deep model integrates MIL into a fully supervised instance segmentation network, and can be derived by the objective consisting of two terms, i.e., the unary term and the pairwise term.

204 0

Paper Graph

Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation

Ming-Ming Cheng, Yun Liu, Yu-Huan Wu, Peisong Wen, Yujun Shi, Yu Qiu•Wed Sep 09 2020

Weakly supervised semantic instance segmentation with only image-level supervision, instead of relying on expensive pixel-wise masks or bounding box annotations, is an important problem to alleviate the data-hungry nature of deep learning. In this article, we tackle this challenging problem by aggregating the image-level information of all training images into a large knowledge graph and exploiting semantic relationships from this graph. Specifically, our effort starts with some generic segment-based object proposals (SOP) without category priors. We propose a multiple instance learning (MIL) framework, which can be trained in an end-to-end manner using training images with image-level labels. For each proposal, this MIL framework can simultaneously compute probability distributions and category-aware semantic features, with which we can formulate a large undirected graph. The category of background is also included in this graph to remove the massive noisy object proposals. An optimal multi-way cut of this graph can thus assign a reliable category label to each proposal. The denoised SOP with assigned category labels can be viewed as pseudo instance segmentation of training images, which are used to train fully supervised models. The proposed approach achieves state-of-the-art performance for both weakly supervised instance segmentation and semantic segmentation. The code is available at https://github.com/yun-liu/LIID.

151 0

Paper Graph

BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation

Sungroh Yoon, Jungbeom Lee, Jihun Yi, Chaehun Shin•Mon Mar 15 2021

This work utilizes higher-level information from the behavior of a trained object detector, by seeking the smallest areas of the image from which the object detector produces almost the same result as it does from the whole image.

218 0

Paper Graph

Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement

Y. Yoo, Junmo Kim, Beomyoung Kim, Chae-Eun Rhee•Sun Sep 19 2021

A semantic knowledge transfer to obtain pseudo instance labels by transferring the knowledge of WSSS to WSIS while eliminating the need for the off-the-shelf proposals is proposed and a self-refinement method is proposed to eliminate the semantic drift problem.

41 0

Paper Graph

Bounding Box Tightness Prior for Weakly Supervised Image Segmentation

Juan Wang, Bin Xia•Sat Oct 02 2021

This paper proposes generalized multiple instance learning (MIL) and smooth maximum approximation to integrate the bounding box tightness prior into the deep neural network in an end-to-end manner.

45 0

Paper Graph

Adding a benchmark result helps the community track progress.