paper-with-me

홈 › Papers

Towards Agnostic and Holistic Universal Image Segmentation with Bit Diffusion

2026-01-06 · Jakob Lønborg Christensen, Morten Rieger Hannemose, Anders Bjorholm Dahl, Vedrana Andersen Dahl arxiv

This paper introduces a diffusion-based framework for universal image segmentation, making agnostic segmentation possible without depending on mask-based frameworks and instead predicting the full segmentation in a holistic manner. We present several key adaptations to diffusion models, which are important in this discrete setting. Notably, we show that a location-aware palette with our 2D gray code ordering improves performance. Adding a final tanh activation function is crucial for discrete data. On optimizing diffusion parameters, the sigmoid loss weighting consistently outperforms alternatives, regardless of the prediction type used, and we settle on x-prediction. While our current model does not yet surpass leading mask-based architectures, it narrows the performance gap and introduces unique capabilities, such as principled ambiguity modeling, that these models lack. All models were trained from scratch, and we believe that combining our proposed improvements with large-scale pretraining or promptable conditioning could lead to competitive models.

📄 PDF Abstract BibTeX arXiv:2601.02881

Code (0)

등록된 구현이 없습니다.

Tasks

Image Segmentation

Similar Papers 제목 키워드 기반

Uni-3D: A Universal Model for Panoptic 3D Scene Reconstruction

2023-01-01 · ICCV 2023 1 · Xiang Zhang, Zeyuan Chen, Fangyin Wei, Zhuowen Tu

Performing holistic 3D scene understanding from a single-view observation, involving generating instance shapes and 3D scene segmentation, is a long-standing challenge. Prevailing works either focus only on geometry …

3D Scene ReconstructionImage SegmentationPanoptic SegmentationScene Parsing+4

DFormer: Diffusion-guided Transformer for Universal Image Segmentation

2023-06-06 · Hefeng Wang, Jiale Cao, Rao Muhammad Anwer, Jin Xie 외

This paper introduces an approach, named DFormer, for universal image segmentation. The proposed DFormer views universal image segmentation task as a denoising process using a diffusion model. DFormer first adds various …

DecoderDenoisingImage SegmentationInstance Segmentation+3

HoliSDiP: Image Super-Resolution via Holistic Semantics and Diffusion Prior

2024-11-27 · Li-Yuan Tsao, Hao-Wei Chen, Hao-Wei Chung, Deqing Sun 외

Text-to-image diffusion models have emerged as powerful priors for real-world image super-resolution (Real-ISR). However, existing methods may produce unintended results due to noisy text prompts and their lack of spatia…

Image Super-ResolutionSegmentationSemantic SegmentationSuper-Resolution

Universal Adversarial Perturbations Against Semantic Image Segmentation

2017-04-19 · ICCV 2017 10 · Jan Hendrik Metzen, Mummadi Chaithanya Kumar, Thomas Brox, Volker Fischer

While deep learning is remarkably successful on perceptual tasks, it was also shown to be vulnerable to adversarial perturbations of the input. These perturbations denote noise added to the input that was generated speci…

image-classificationImage ClassificationImage SegmentationSegmentation+1

Towards Universal Dataset Distillation via Task-Driven Diffusion

2025-01-01 · CVPR 2025 1 · Ding Qi, Jian Li, Junyao Gao, Shuguang Dou 외

Dataset distillation (DD) condenses key information from large-scale datasets into smaller synthetic datasets, reducing storage and computational costs for training networks. However, recent research has primarily fo…

Dataset Distillationimage-classificationImage ClassificationImage Generation