Log In Sign Up

Weakly Supervised Multi-Object Tracking and Segmentation

by   Idoia Ruiz, et al.

We introduce the problem of weakly supervised Multi-Object Tracking and Segmentation, i.e. joint weakly supervised instance segmentation and multi-object tracking, in which we do not provide any kind of mask annotation. To address it, we design a novel synergistic training strategy by taking advantage of multi-task learning, i.e. classification and tracking tasks guide the training of the unsupervised instance segmentation. For that purpose, we extract weak foreground localization information, provided by Grad-CAM heatmaps, to generate a partial ground truth to learn from. Additionally, RGB image level information is employed to refine the mask prediction at the edges of the objects. We evaluate our method on KITTI MOTS, the most representative benchmark for this task, reducing the performance gap on the MOTSP metric between the fully supervised and weakly supervised approach to just 12 12.7


page 1

page 3

page 5

page 6

page 7


Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images

Humans have a strong class-agnostic object segmentation ability and can ...

Weakly Supervised Instance Segmentation for Videos with Temporal Mask Consistency

Weakly supervised instance segmentation reduces the cost of annotations ...

Image Co-skeletonization via Co-segmentation

Recent advances in the joint processing of images have certainly shown i...

Weakly Supervised Instance Segmentation using Motion Information via Optical Flow

Weakly supervised instance segmentation has gained popularity because it...

Learning Multi-Object Tracking and Segmentation from Automatic Annotations

In this work we contribute a novel pipeline to automatically generate tr...

Acquire, Augment, Segment & Enjoy: Weakly Supervised Instance Segmentation of Supermarket Products

Grocery stores have thousands of products that are usually identified us...

Bootstrapping Labelled Dataset Construction for Cow Tracking and Behavior Analysis

This paper introduces a new approach to the long-term tracking of an obj...