CVJan 12, 2023

Open-vocabulary Object Segmentation with Diffusion Models

arXiv:2301.05221v299 citationsh-index: 50
Originality Incremental advance
AI Analysis

This work addresses open-vocabulary object segmentation for computer vision applications, offering an incremental improvement by adapting diffusion models for discriminative tasks.

The paper tackles the problem of extracting visual-language correspondences from a pre-trained text-to-image diffusion model to generate segmentation maps, achieving competitive performance on zero-shot segmentation benchmarks.

The goal of this paper is to extract the visual-language correspondence from a pre-trained text-to-image diffusion model, in the form of segmentation map, i.e., simultaneously generating images and segmentation masks for the corresponding visual entities described in the text prompt. We make the following contributions: (i) we pair the existing Stable Diffusion model with a novel grounding module, that can be trained to align the visual and textual embedding space of the diffusion model with only a small number of object categories; (ii) we establish an automatic pipeline for constructing a dataset, that consists of {image, segmentation mask, text prompt} triplets, to train the proposed grounding module; (iii) we evaluate the performance of open-vocabulary grounding on images generated from the text-to-image diffusion model and show that the module can well segment the objects of categories beyond seen ones at training time; (iv) we adopt the augmented diffusion model to build a synthetic semantic segmentation dataset, and show that, training a standard segmentation model on such dataset demonstrates competitive performance on the zero-shot segmentation(ZS3) benchmark, which opens up new opportunities for adopting the powerful diffusion model for discriminative tasks.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes