# Ada-Segment: Automated Multi-loss Adaptation for Panoptic Segmentation

Source: [Ada-Segment: Automated Multi-loss Adaptation for Panoptic Segmentation](<https://www.sota2.com/research/paper/68fa68e11e209131cea1eeb8>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:23:03.491Z

Authors: Gengwei Zhang, Yiming Gao, Hang Xu, Hao Zhang, Zhenguo Li, Xiaodan Liang

Published: 2020-12-07T11:43:10.000Z

## Abstract

Panoptic segmentation that unifies instance segmentation and semantic segmentation has recently attracted increasing attention. While most existing methods focus on designing novel architectures, we steer toward a different perspective: performing automated multi-loss adaptation (named Ada-Segment) on the fly to flexibly adjust multiple training losses over the course of training using a controller trained to capture the learning dynamics. This offers a few advantages: it bypasses manual tuning of the sensitive loss combination, a decisive factor for panoptic segmentation; it allows to explicitly model the learning dynamics, and reconcile the learning of multiple objectives (up to ten in our experiments); with an end-to-end architecture, it generalizes to different datasets without the need of re-tuning hyperparameters or re-adjusting the training process laboriously. Our Ada-Segment brings 2.7% panoptic quality (PQ) improvement on COCO val split from the vanilla baseline, achieving the state-of-the-art 48.5% PQ on COCO test-dev split and 32.9% PQ on ADE20K dataset. The extensive ablation studies reveal the ever-changing dynamics throughout the training process, necessitating the incorporation of an automated and adaptive learning strategy as presented in this paper.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Panoptic Segmentation on COCO (test-dev)](<https://www.sota2.com/research/sota/panoptic-segmentation-on-coco-test-dev.md>): Panoptic Segmentation; COCO (test-dev); PQ: 48.5.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2012.03603>)

[PDF](<https://arxiv.org/pdf/2012.03603.pdf>)