PanDA: Panoptic Data Augmentation

2019-11-27 · Yang Liu, Pietro Perona, Markus Meister

The recently proposed panoptic segmentation task presents a significant challenge of image understanding with computer vision by unifying semantic segmentation and instance segmentation tasks. In this paper we present an efficient and novel panoptic data augmentation (PanDA) method which operates exclusively in pixel space, requires no additional data or training, and is computationally cheap to implement. By retraining original state-of-the-art models on PanDA augmented datasets generated with a single frozen set of parameters, we show robust performance gains in panoptic segmentation, instance segmentation, as well as detection across models, backbones, dataset domains, and scales. Finally, the effectiveness of unrealistic-looking training images synthesized by PanDA suggest that one should rethink the need for image realism for efficient data augmentation.

📄 PDF Abstract BibTeX arXiv:1911.12317

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentation Instance Segmentation Panoptic Segmentation Segmentation Semantic Segmentation

PanDA: Unsupervised Domain Adaptation for Multimodal 3D Panoptic Segmentation in Autonomous Driving

2026-04-21 · Yining Pan, Shijie Li, Yuchen Wu, Xulei Yang 외 arxiv

This paper presents the first study on Unsupervised Domain Adaptation (UDA) for multimodal 3D panoptic segmentation (mm-3DPS), aiming to improve generalization under domain shifts commonly encountered in real-world auton…

Unsupervised Domain Adaptation 3D Semantic Segmentation Representation Learning Panoptic Segmentation

MC-PanDA: Mask Confidence for Panoptic Domain Adaptation

2024-07-19 · Ivan Martinović, Josip Šarić, Siniša Šegvić

Domain adaptive panoptic segmentation promises to resolve the long tail of corner cases in natural scene understanding. Previous state of the art addresses this problem with cross-task consistency, careful system-level o…

Domain Adaptation Panoptic Segmentation Scene Understanding Unsupervised Domain Adaptation

Panda: Test-Time Adaptation with Negative Data Augmentation

2025-11-13 · Ruxi Deng, Wenxuan Bao, Tianxin Wei, Jingrui He arxiv

Pretrained VLMs exhibit strong zero-shot classification capabilities, but their predictions degrade significantly under common image corruptions. To improve robustness, many test-time adaptation (TTA) methods adopt posit…

Test-time Adaptation Data Augmentation

Panoptic Pairwise Distortion Graph

2026-04-13 · Muhammad Kamran Janjua, Abdul Wahab, Bahador Rashidi arxiv

In this work, we introduce a new perspective on comparative image assessment by representing an image pair as a structured composition of its regions. In contrast, existing methods focus on whole image analysis, while im…

PANDA: AdaPtive Noisy Data Augmentation for Regularization of Undirected Graphical Models

2018-10-11 · Yi-Nan Li, Xiao Liu, Fang Liu

We propose an AdaPtive Noise Augmentation (PANDA) technique to regularize the estimation and construction of undirected graphical models. PANDA iteratively optimizes the objective function given the noise augmented data …

Data Augmentation Variable Selection