MeNToS: Tracklets Association with a Space-Time Memory Network

TL;DR

MeNToS introduces a novel space-time memory network approach for multi-object tracking and segmentation that improves data association without requiring fine-tuning, achieving competitive results in challenging benchmarks.

Contribution

First application of space-time memory networks to multi-object tracking and segmentation, enhancing data association without fine-tuning or hyperparameter tuning.

Findings

Achieved 4th place in RobMOTS challenge.

Effective tracklet association with space-time memory network.

No need for per benchmark hyperparameter tuning.

Abstract

We propose a method for multi-object tracking and segmentation (MOTS) that does not require fine-tuning or per benchmark hyperparameter selection. The proposed method addresses particularly the data association problem. Indeed, the recently introduced HOTA metric, that has a better alignment with the human visual assessment by evenly balancing detections and associations quality, has shown that improvements are still needed for data association. After creating tracklets using instance segmentation and optical flow, the proposed method relies on a space-time memory network (STM) developed for one-shot video object segmentation to improve the association of tracklets with temporal gaps. To the best of our knowledge, our method, named MeNToS, is the first to use the STM network to track object masks for MOTS. We took the 4th place in the RobMOTS challenge. The project page is https://mehdimiah.com/mentos.html.