Weakly-supervised instance segmentation

19 papers with code • 3 benchmarks • 1 datasets

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


Most implemented papers

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

NVlabs/DiscoBox ICCV 2021

We introduce DiscoBox, a novel framework that jointly learns instance segmentation and semantic correspondence using bounding box supervision.

BoxInst: High-Performance Instance Segmentation with Box Annotations

aim-uofa/adet CVPR 2021

We present a high-performance method that can achieve mask-level instance segmentation with only bounding-box annotations for training.

Pointly-Supervised Instance Segmentation

facebookresearch/detectron2 CVPR 2022

Our experiments show that the new module is more suitable for the point-based supervision.

Weakly Supervised Instance Segmentation using Class Peak Response

ZhouYanzhao/PRM CVPR 2018

Motivated by this, we first design a process to stimulate peaks to emerge from a class response map.

Weakly- and Semi-Supervised Panoptic Segmentation

qizhuli/Weakly-Supervised-Panoptic-Segmentation ECCV 2018

We present a weakly supervised model that jointly performs both semantic- and instance-segmentation -- a particularly relevant problem given the substantial cost of obtaining pixel-perfect annotation for these tasks.

Weakly Supervised Instance Segmentation using the Bounding Box Tightness Prior

chengchunhsu/WSIS_BBTP NeurIPS 2019

This paper presents a weakly supervised instance segmentation method that consumes training data with tight bounding box annotations.

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

yun-liu/LIID 10 Sep 2020

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.

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

jbeomlee93/BBAM CVPR 2021

Weakly supervised segmentation methods using bounding box annotations focus on obtaining a pixel-level mask from each box containing an object.

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

clovaai/BESTIE CVPR 2022

This semantic drift occurs confusion between background and instance in training and consequently degrades the segmentation performance.

Bounding Box Tightness Prior for Weakly Supervised Image Segmentation

wangjuan313/wsis-boundingbox 3 Oct 2021

Two variants of smooth maximum approximation, i. e., $\alpha$-softmax function and $\alpha$-quasimax function, are exploited to conquer the numeral instability introduced by maximum function of bag prediction.