Open-Vocabulary Image Segmentation

• URL: http://arxiv.org/abs/2112.12143v1
• Date: Wed, 22 Dec 2021 18:57:54 GMT
• Title: Open-Vocabulary Image Segmentation
• Authors: Golnaz Ghiasi, Xiuye Gu, Yin Cui, Tsung-Yi Lin
• Abstract summary: We design an open-vocabulary image segmentation model to organize an image into meaningful regions indicated by arbitrary texts. We argue that these models miss an important step of visual grouping, which organizes pixels into groups before learning visual-semantic alignments. Our work is the first to perform zero-shot transfer on holdout segmentation datasets.
• Score: 36.5086895686526
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We design an open-vocabulary image segmentation model to organize an image into meaningful regions indicated by arbitrary texts. We identify that recent open-vocabulary models can not localize visual concepts well despite recognizing what are in an image. We argue that these models miss an important step of visual grouping, which organizes pixels into groups before learning visual-semantic alignments. We propose OpenSeg to address the above issue. First, it learns to propose segmentation masks for possible organizations. Then it learns visual-semantic alignments by aligning each word in a caption to one or a few predicted masks. We find the mask representations are the key to support learning from captions, making it possible to scale up the dataset and vocabulary sizes. Our work is the first to perform zero-shot transfer on holdout segmentation datasets. We set up two strong baselines by applying class activation maps or fine-tuning with pixel-wise labels on a pre-trained ALIGN model. OpenSeg outperforms these baselines by 3.4 mIoU on PASCAL-Context (459 classes) and 2.7 mIoU on ADE-20k (847 classes).

Related papers

• Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels [53.8817160001038]
  We propose a novel method, PixelCLIP, to adapt the CLIP image encoder for pixel-level understanding. To address the challenges of leveraging masks without semantic labels, we devise an online clustering algorithm. PixelCLIP shows significant performance improvements over CLIP and competitive results compared to caption-supervised methods.
  arXiv  Detail & Related papers  (2024-09-30T01:13:03Z)
• Exploring Simple Open-Vocabulary Semantic Segmentation [7.245983878396646]
  Open-vocabulary semantic segmentation models aim to accurately assign a semantic label to each pixel in an image from a set of arbitrary open-vocabulary texts. In this paper, we introduce S-Seg, a novel model that can achieve surprisingly strong performance without depending on any of the above elements.
  arXiv  Detail & Related papers  (2024-01-22T18:59:29Z)
• Learning Open-vocabulary Semantic Segmentation Models From Natural Language Supervision [49.905448429974804]
  We consider the problem of open-vocabulary semantic segmentation (OVS), which aims to segment objects of arbitrary classes instead of pre-defined, closed-set categories. We propose a transformer-based model for OVS, termed as OVSegmentor, which exploits web-crawled image-text pairs for pre-training. Our model achieves superior segmentation results over the state-of-the-art method by using only 3% data (4M vs 134M) for pre-training.
  arXiv  Detail & Related papers  (2023-01-22T13:10:05Z)
• SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation [26.079055078561986]
  We propose a CLIP-based model named SegCLIP for the topic of open-vocabulary segmentation. The main idea is to gather patches with learnable centers to semantic regions through training on text-image pairs. Experimental results show that our model achieves comparable or superior segmentation accuracy.
  arXiv  Detail & Related papers  (2022-11-27T12:38:52Z)
• Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP [45.81698881151867]
  Open-vocabulary semantic segmentation aims to segment an image into semantic regions according to text descriptions, which may not have been seen during training. Recent two-stage methods first generate class-agnostic mask proposals and then leverage pre-trained vision-language models, e.g., CLIP, to classify masked regions. We propose to finetune CLIP on a collection of masked image regions and their corresponding text descriptions. In particular, when trained on COCO and evaluated on ADE20K-150, our best model achieves 29.6% mIoU, which is +8.5% higher than the previous state-
  arXiv  Detail & Related papers  (2022-10-09T02:57:32Z)
• Single-Stream Multi-Level Alignment for Vision-Language Pretraining [103.09776737512078]
  We propose a single stream model that aligns the modalities at multiple levels. We achieve this using two novel tasks: symmetric cross-modality reconstruction and a pseudo-labeled key word prediction. We demonstrate top performance on a set of Vision-Language downstream tasks such as zero-shot/fine-tuned image/text retrieval, referring expression, and VQA.
  arXiv  Detail & Related papers  (2022-03-27T21:16:10Z)
• GroupViT: Semantic Segmentation Emerges from Text Supervision [82.02467579704091]
  Grouping and recognition are important components of visual scene understanding. We propose a hierarchical Grouping Vision Transformer (GroupViT) GroupViT learns to group together semantic regions and successfully transfers to the task of semantic segmentation in a zero-shot manner.
  arXiv  Detail & Related papers  (2022-02-22T18:56:04Z)
• Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labeling [61.03262873980619]
  Open-vocabulary instance segmentation aims at segmenting novel classes without mask annotations. We propose a cross-modal pseudo-labeling framework, which generates training pseudo masks by aligning word semantics in captions with visual features of object masks in images. Our framework is capable of labeling novel classes in captions via their word semantics to self-train a student model.
  arXiv  Detail & Related papers  (2021-11-24T18:50:47Z)
• Learning to Generate Scene Graph from Natural Language Supervision [52.18175340725455]
  We propose one of the first methods that learn from image-sentence pairs to extract a graphical representation of localized objects and their relationships within an image, known as scene graph. We leverage an off-the-shelf object detector to identify and localize object instances, match labels of detected regions to concepts parsed from captions, and thus create "pseudo" labels for learning scene graph.
  arXiv  Detail & Related papers  (2021-09-06T03:38:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.