{
  "id": "2211.14126",
  "version": "v1",
  "published": "2022-11-25T14:09:02.000Z",
  "updated": "2022-11-25T14:09:02.000Z",
  "title": "A Strong Baseline for Generalized Few-Shot Semantic Segmentation",
  "authors": [
    "Sina Hajimiri",
    "Malik Boudiaf",
    "Ismail Ben Ayed",
    "Jose Dolz"
  ],
  "comment": "13 pages, 4 figures",
  "categories": [
    "cs.CV"
  ],
  "abstract": "This paper introduces a generalized few-shot segmentation framework with a straightforward training process and an easy-to-optimize inference phase. In particular, we propose a simple yet effective model based on the well-known InfoMax principle, where the Mutual Information (MI) between the learned feature representations and their corresponding predictions is maximized. In addition, the terms derived from our MI-based formulation are coupled with a knowledge distillation term to retain the knowledge on base classes. With a simple training process, our inference model can be applied on top of any segmentation network trained on base classes. The proposed inference yields substantial improvements on the popular few-shot segmentation benchmarks PASCAL-$5^i$ and COCO-$20^i$. Particularly, for novel classes, the improvement gains range from 5% to 20% (PASCAL-$5^i$) and from 2.5% to 10.5% (COCO-$20^i$) in the 1-shot and 5-shot scenarios, respectively. Furthermore, we propose a more challenging setting, where performance gaps are further exacerbated. Our code is publicly available at https://github.com/sinahmr/DIaM.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-11-25T14:09:02.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "generalized few-shot semantic segmentation",
      "strong baseline",
      "popular few-shot segmentation benchmarks",
      "inference yields substantial improvements",
      "base classes"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 13,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}