ProMi: An Efficient Prototype-Mixture Baseline for Few-Shot Segmentation with Bounding-Box Annotations

• URL: http://arxiv.org/abs/2505.12547v1
• Date: Sun, 18 May 2025 21:08:05 GMT
• Title: ProMi: An Efficient Prototype-Mixture Baseline for Few-Shot Segmentation with Bounding-Box Annotations
• Authors: Florent Chiaroni, Ali Ayub, Ola Ahmad,
• Abstract summary: We present a novel few-shot binary segmentation method based on bounding-box annotations instead of pixel-level labels.<n>We introduce ProMi, an efficient prototype-mixture-based method that treats the background class as a mixture of distributions.<n>Our approach is simple, training-free, and effective, accommodating coarse annotations with ease.
• Score: 10.544272345573718
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In robotics applications, few-shot segmentation is crucial because it allows robots to perform complex tasks with minimal training data, facilitating their adaptation to diverse, real-world environments. However, pixel-level annotations of even small amount of images is highly time-consuming and costly. In this paper, we present a novel few-shot binary segmentation method based on bounding-box annotations instead of pixel-level labels. We introduce, ProMi, an efficient prototype-mixture-based method that treats the background class as a mixture of distributions. Our approach is simple, training-free, and effective, accommodating coarse annotations with ease. Compared to existing baselines, ProMi achieves the best results across different datasets with significant gains, demonstrating its effectiveness. Furthermore, we present qualitative experiments tailored to real-world mobile robot tasks, demonstrating the applicability of our approach in such scenarios. Our code: https://github.com/ThalesGroup/promi.

Related papers

• Integrated Image-Text Based on Semi-supervised Learning for Small Sample Instance Segmentation [1.3157419797035321]
  The article proposes a novel small sample instance segmentation solution from the perspective of maximizing the utilization of existing information. First, it helps the model fully utilize unlabeled data by learning to generate pseudo labels, increasing the number of available samples. Second, by integrating the features of text and image, more accurate classification results can be obtained.
  arXiv  Detail & Related papers  (2024-10-21T14:44:08Z)
• A Good Foundation is Worth Many Labels: Label-Efficient Panoptic Segmentation [22.440065488051047]
  Key challenge for the widespread application of learning-based models for robotic perception is to significantly reduce the required amount of annotated training data.<n>We exploit the groundwork paved by visual foundation models to train two lightweight network heads for semantic segmentation and object boundary detection.<n>We demonstrate that PASTEL significantly outperforms previous methods for label-efficient segmentation even when using fewer annotations.
  arXiv  Detail & Related papers  (2024-05-29T12:23:29Z)
• MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments [72.6405488990753]
  Self-supervised learning can be used for mitigating the greedy needs of Vision Transformer networks. We propose a single-stage and standalone method, MOCA, which unifies both desired properties. We achieve new state-of-the-art results on low-shot settings and strong experimental results in various evaluation protocols.
  arXiv  Detail & Related papers  (2023-07-18T15:46:20Z)
• CropMix: Sampling a Rich Input Distribution via Multi-Scale Cropping [97.05377757299672]
  We present a simple method, CropMix, for producing a rich input distribution from the original dataset distribution. CropMix can be seamlessly applied to virtually any training recipe and neural network architecture performing classification tasks. We show that CropMix is of benefit to both contrastive learning and masked image modeling towards more powerful representations.
  arXiv  Detail & Related papers  (2022-05-31T16:57:28Z)
• Semantic Segmentation with Active Semi-Supervised Learning [23.79742108127707]
  We propose a novel algorithm that combines active learning and semi-supervised learning. Our method obtains over 95% of the network's performance on the full-training set.
  arXiv  Detail & Related papers  (2022-03-21T04:16:25Z)
• EdgeFlow: Achieving Practical Interactive Segmentation with Edge-Guided Flow [5.696221390328458]
  We propose EdgeFlow, a novel architecture that fully utilizes interactive information of user clicks with edge-guided flow. Our method achieves state-of-the-art performance without any post-processing or iterative optimization scheme. With the proposed method, we develop an efficient interactive segmentation tool for practical data annotation tasks.
  arXiv  Detail & Related papers  (2021-09-20T10:07:07Z)
• Multi-dataset Pretraining: A Unified Model for Semantic Segmentation [97.61605021985062]
  We propose a unified framework, termed as Multi-Dataset Pretraining, to take full advantage of the fragmented annotations of different datasets. This is achieved by first pretraining the network via the proposed pixel-to-prototype contrastive loss over multiple datasets. In order to better model the relationship among images and classes from different datasets, we extend the pixel level embeddings via cross dataset mixing.
  arXiv  Detail & Related papers  (2021-06-08T06:13:11Z)
• Towards Good Practices for Efficiently Annotating Large-Scale Image Classification Datasets [90.61266099147053]
  We investigate efficient annotation strategies for collecting multi-class classification labels for a large collection of images. We propose modifications and best practices aimed at minimizing human labeling effort. Simulated experiments on a 125k image subset of the ImageNet100 show that it can be annotated to 80% top-1 accuracy with 0.35 annotations per image on average.
  arXiv  Detail & Related papers  (2021-04-26T16:29:32Z)
• SCNet: Enhancing Few-Shot Semantic Segmentation by Self-Contrastive Background Prototypes [56.387647750094466]
  Few-shot semantic segmentation aims to segment novel-class objects in a query image with only a few annotated examples. Most of advanced solutions exploit a metric learning framework that performs segmentation through matching each pixel to a learned foreground prototype. This framework suffers from biased classification due to incomplete construction of sample pairs with the foreground prototype only.
  arXiv  Detail & Related papers  (2021-04-19T11:21:47Z)
• Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization [112.68171734288237]
  We propose a novel framework for discriminative pixel-level tasks using a generative model of both images and labels. We learn a generative adversarial network that captures the joint image-label distribution and is trained efficiently using a large set of unlabeled images. We demonstrate strong in-domain performance compared to several baselines, and are the first to showcase extreme out-of-domain generalization.
  arXiv  Detail & Related papers  (2021-04-12T21:41:25Z)

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.