Related papers: Hierarchical Dense Correlation Distillation for Few-Shot Segmentation

Hierarchical Dense Correlation Distillation for Few-Shot Segmentation

URL: http://arxiv.org/abs/2303.14652v1
Date: Sun, 26 Mar 2023 08:13:12 GMT
Title: Hierarchical Dense Correlation Distillation for Few-Shot Segmentation
Authors: Bohao Peng, Zhuotao Tian, Xiaoyang Wu, Chenyao Wang, Shu Liu, Jingyong Su, Jiaya Jia
Abstract summary: Few-shot semantic segmentation (FSS) aims to form class-agnostic models segmenting unseen classes with only a handful of annotations. We design Hierarchically Decoupled Matching Network (HDMNet) mining pixel-level support correlation based on the transformer architecture. We propose a matching module to reduce train-set overfitting and introduce correlation distillation leveraging semantic correspondence from coarse resolution to boost fine-grained segmentation.
Score: 46.696051965252934
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Few-shot semantic segmentation (FSS) aims to form class-agnostic models segmenting unseen classes with only a handful of annotations. Previous methods limited to the semantic feature and prototype representation suffer from coarse segmentation granularity and train-set overfitting. In this work, we design Hierarchically Decoupled Matching Network (HDMNet) mining pixel-level support correlation based on the transformer architecture. The self-attention modules are used to assist in establishing hierarchical dense features, as a means to accomplish the cascade matching between query and support features. Moreover, we propose a matching module to reduce train-set overfitting and introduce correlation distillation leveraging semantic correspondence from coarse resolution to boost fine-grained segmentation. Our method performs decently in experiments. We achieve $50.0\%$ mIoU on \coco~dataset one-shot setting and $56.0\%$ on five-shot segmentation, respectively.

Related papers

Hierarchical Dense Correlation Distillation for Few-Shot Segmentation-Extended Abstract [47.85056124410376]
Few-shot semantic segmentation (FSS) aims to form class-agnostic models segmenting unseen classes with only a handful of annotations. We design Hierarchically Decoupled Matching Network (HDMNet) mining pixel-level support correlation based on the transformer architecture. We propose a matching module to reduce train-set overfitting and introduce correlation distillation leveraging semantic correspondence from coarse resolution to boost fine-grained segmentation.
arXiv Detail & Related papers (2023-06-27T08:10:20Z)
Cost Aggregation Is All You Need for Few-Shot Segmentation [28.23753949369226]
We introduce Volumetric Aggregation with Transformers (VAT) to tackle the few-shot segmentation task. VAT uses both convolutions and transformers to efficiently handle high dimensional correlation maps between query and support. We find that the proposed method attains state-of-the-art performance even for the standard benchmarks in semantic correspondence task.
arXiv Detail & Related papers (2021-12-22T06:18:51Z)
APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation [56.387647750094466]
Few-shot semantic segmentation aims to segment novel-class objects in a given query image with only a few labeled support images. Most advanced solutions exploit a metric learning framework that performs segmentation through matching each query feature to a learned class-specific prototype. We present an adaptive prototype representation by introducing class-specific and class-agnostic prototypes.
arXiv Detail & Related papers (2021-11-24T04:38:37Z)
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)
Hypercorrelation Squeeze for Few-Shot Segmentation [33.45698767126036]
Few-shot semantic segmentation aims at learning to segment a target object from a query image using only a few annotated support images of the target class. This challenge requires to understand diverse levels of visual cues and analyze fine-grained correspondence relations between the query and the support images. We propose Hypercorrelation Squeeze Networks (HSNet) that leverages multi-level feature correlation and efficient 4D convolutions.
arXiv Detail & Related papers (2021-04-04T05:27:13Z)
Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation [49.90178055521207]
This work addresses weakly supervised semantic segmentation (WSSS), with the goal of bridging the gap between image-level annotations and pixel-level segmentation. We formulate WSSS as a novel group-wise learning task that explicitly models semantic dependencies in a group of images to estimate more reliable pseudo ground-truths. In particular, we devise a graph neural network (GNN) for group-wise semantic mining, wherein input images are represented as graph nodes.
arXiv Detail & Related papers (2020-12-09T12:40:13Z)
Self-Supervised Tuning for Few-Shot Segmentation [82.32143982269892]
Few-shot segmentation aims at assigning a category label to each image pixel with few annotated samples. Existing meta-learning method tends to fail in generating category-specifically discriminative descriptor when the visual features extracted from support images are marginalized in embedding space. This paper presents an adaptive framework tuning, in which the distribution of latent features across different episodes is dynamically adjusted based on a self-segmentation scheme.
arXiv Detail & Related papers (2020-04-12T03:53:53Z)

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