Integrative Few-Shot Learning for Classification and Segmentation

2022-03-29 · CVPR 2022 1 · Dahyun Kang, Minsu Cho

We introduce the integrative task of few-shot classification and segmentation (FS-CS) that aims to both classify and segment target objects in a query image when the target classes are given with a few examples. This task combines two conventional few-shot learning problems, few-shot classification and segmentation. FS-CS generalizes them to more realistic episodes with arbitrary image pairs, where each target class may or may not be present in the query. To address the task, we propose the integrative few-shot learning (iFSL) framework for FS-CS, which trains a learner to construct class-wise foreground maps for multi-label classification and pixel-wise segmentation. We also develop an effective iFSL model, attentive squeeze network (ASNet), that leverages deep semantic correlation and global self-attention to produce reliable foreground maps. In experiments, the proposed method shows promising performance on the FS-CS task and also achieves the state of the art on standard few-shot segmentation benchmarks.

📄 PDF Abstract BibTeX arXiv:2203.15712

Code (1)

dahyun-kang/ifsl 공식 구현 pytorch

Tasks

ClassificationFew-Shot Classification and SegmentationFew-Shot Learning Few-Shot Semantic Segmentation Multi-Label Classification MUlTI-LABEL-ClASSIFICATION Segmentation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Position-Wise Feed-Forward Layer 설명 없음

Residual Connection 설명 없음

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Multi-Head Attention 설명 없음

Attention 설명 없음

Transformer A Transformer is a model architecture that eschews recurrence and instead relies entirely on an [attention…

Text Augmented Correlation Transformer For Few-shot Classification & Segmentation

2025-01-01 · CVPR 2025 1 · Srinivasa Rao Nandam, Sara Atito, ZhenHua Feng, Josef Kittler 외

Foundation models like CLIP and ALIGN have transformed few-shot and zero-shot vision applications by fusing visual and textual data, yet the integrative few-shot classification and segmentation (FS-CS) task primarily…

Few-Shot Classification and Segmentation Few-Shot Learning Segmentation

IGCN: Integrative Graph Convolution Networks for patient level insights and biomarker discovery in multi-omics integration

2024-01-31 · Cagri Ozdemir, Mohammad Al Olaimat, Yashu Vashishath, Serdar Bozdag 외

Developing computational tools for integrative analysis across multiple types of omics data has been of immense importance in cancer molecular biology and precision medicine research. While recent advancements have yield…

Node Classification

AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One

2023-12-10 · Mike Ranzinger, Greg Heinrich, Jan Kautz, Pavlo Molchanov

A handful of visual foundation models (VFMs) have recently emerged as the backbones for numerous downstream tasks. VFMs like CLIP, DINOv2, SAM are trained with distinct objectives, exhibiting unique characteristics for v…

All Benchmarking object-detection Object Detection+1

AM-RADIO: Agglomerative Vision Foundation Model Reduce All Domains Into One

2024-01-01 · CVPR 2024 1 · Mike Ranzinger, Greg Heinrich, Jan Kautz, Pavlo Molchanov

A handful of visual foundation models (VFMs) have recently emerged as the backbones for numerous downstream tasks. VFMs like CLIP DINOv2 SAM are trained with distinct objectives exhibiting unique characteristics for …