Weakly-supervised instance segmentation

11 papers with code • 3 benchmarks • 2 datasets

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

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

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

3

BoxInst: High-Performance Instance Segmentation with Box Annotations

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

2

Weakly Supervised Instance Segmentation using Class Peak Response

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

1

Weakly- and Semi-Supervised Panoptic Segmentation

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.

1

Weakly Supervised Instance Segmentation using the Bounding Box Tightness Prior

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

1

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

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.

1

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

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

1

Pointly-Supervised Instance Segmentation

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

1

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

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

1

Bounding Box Tightness Prior for Weakly Supervised Image Segmentation

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.

1