CORA: Consistency-Guided Semi-Supervised Framework for Reasoning Segmentation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Howlader, Prantik, Nguyen-Canh, Hoang, Das, Srijan, Xu, Jingyi, Le, Hieu, Samaras, Dimitris
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909917070229504
author Howlader, Prantik
Nguyen-Canh, Hoang
Das, Srijan
Xu, Jingyi
Le, Hieu
Samaras, Dimitris
author_facet Howlader, Prantik
Nguyen-Canh, Hoang
Das, Srijan
Xu, Jingyi
Le, Hieu
Samaras, Dimitris
contents Reasoning segmentation seeks pixel-accurate masks for targets referenced by complex, often implicit instructions, requiring context-dependent reasoning over the scene. Recent multimodal language models have advanced instruction following segmentation, yet generalization remains limited. The key bottleneck is the high cost of curating diverse, high-quality pixel annotations paired with rich linguistic supervision leading to brittle performance under distribution shift. Therefore, we present CORA, a semi-supervised reasoning segmentation framework that jointly learns from limited labeled data and a large corpus of unlabeled images. CORA introduces three main components: 1) conditional visual instructions that encode spatial and contextual relationships between objects; 2) a noisy pseudo-label filter based on the consistency of Multimodal LLM's outputs across semantically equivalent queries; and 3) a token-level contrastive alignment between labeled and pseudo-labeled samples to enhance feature consistency. These components enable CORA to perform robust reasoning segmentation with minimal supervision, outperforming existing baselines under constrained annotation settings. CORA achieves state-of-the-art results, requiring as few as 100 labeled images on Cityscapes, a benchmark dataset for urban scene understanding, surpassing the baseline by $+2.3\%$. Similarly, CORA improves performance by $+2.4\%$ with only 180 labeled images on PanNuke, a histopathology dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2511_17755
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CORA: Consistency-Guided Semi-Supervised Framework for Reasoning Segmentation
Howlader, Prantik
Nguyen-Canh, Hoang
Das, Srijan
Xu, Jingyi
Le, Hieu
Samaras, Dimitris
Computer Vision and Pattern Recognition
Reasoning segmentation seeks pixel-accurate masks for targets referenced by complex, often implicit instructions, requiring context-dependent reasoning over the scene. Recent multimodal language models have advanced instruction following segmentation, yet generalization remains limited. The key bottleneck is the high cost of curating diverse, high-quality pixel annotations paired with rich linguistic supervision leading to brittle performance under distribution shift. Therefore, we present CORA, a semi-supervised reasoning segmentation framework that jointly learns from limited labeled data and a large corpus of unlabeled images. CORA introduces three main components: 1) conditional visual instructions that encode spatial and contextual relationships between objects; 2) a noisy pseudo-label filter based on the consistency of Multimodal LLM's outputs across semantically equivalent queries; and 3) a token-level contrastive alignment between labeled and pseudo-labeled samples to enhance feature consistency. These components enable CORA to perform robust reasoning segmentation with minimal supervision, outperforming existing baselines under constrained annotation settings. CORA achieves state-of-the-art results, requiring as few as 100 labeled images on Cityscapes, a benchmark dataset for urban scene understanding, surpassing the baseline by $+2.3\%$. Similarly, CORA improves performance by $+2.4\%$ with only 180 labeled images on PanNuke, a histopathology dataset.
title CORA: Consistency-Guided Semi-Supervised Framework for Reasoning Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.17755