paper-with-me

Papers

Native Segmentation Vision Transformers

2025-05-22 · Guillem Brasó, Aljoša Ošep, Laura Leal-Taixé

Uniform downsampling remains the de facto standard for reducing spatial resolution in vision backbones. In this work, we propose an alternative design built around a content-aware spatial grouping layer, that dynamically assigns tokens to a reduced set based on image boundaries and their semantic content. Stacking our grouping layer across consecutive backbone stages results in hierarchical segmentation that arises natively in the feature extraction process, resulting in our coined Native Segmentation Vision Transformer. We show that a careful design of our architecture enables the emergence of strong segmentation masks solely from grouping layers, that is, without additional segmentation-specific heads. This sets the foundation for a new paradigm of native, backbone-level segmentation, which enables strong zero-shot results without mask supervision, as well as a minimal and efficient standalone model design for downstream segmentation tasks. Our project page is https://research.nvidia.com/labs/dvl/projects/native-segmentation.

📄 PDF Abstract BibTeX arXiv:2505.16993

Code (0)

등록된 구현이 없습니다.

Tasks

Segmentation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Multi-Head Attention 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 $x$…
Position-Wise Feed-Forward Layer 설명 없음
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…

Similar Papers 제목 키워드 기반

Representation Separation for Semantic Segmentation with Vision Transformers

2022-12-28 · Yuanduo Hong, Huihui Pan, Weichao Sun, Xinghu Yu 외

Vision transformers (ViTs) encoding an image as a sequence of patches bring new paradigms for semantic segmentation.We present an efficient framework of representation separation in local-patch level and global-region le…

Semantic Segmentation

Dynamic Grained Encoder for Vision Transformers

2023-01-10 · NeurIPS 2021 12 · Lin Song, Songyang Zhang, Songtao Liu, Zeming Li 외

Transformers, the de-facto standard for language modeling, have been recently applied for vision tasks. This paper introduces sparse queries for vision transformers to exploit the intrinsic spatial redundancy of natural …

image-classificationImage ClassificationLanguage ModelingLanguage Modelling+2

Should we Replace CNNs with Transformers for Medical Images?

2021-09-29 · Christos Matsoukas, Johan Fredin Haslum, Moein Sorkhei, Magnus Soderberg 외

Convolutional Neural Networks (CNNs) have reigned for a decade as the de facto approach to automated medical image diagnosis, pushing the state-of-the-art in classification, detection and segmentation tasks. Recently, vi…

Segmentation

Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation

2022-10-31 · Simone Rossetti, Damiano Zappia, Marta Sanzari, Marco Schaerf 외

Weakly Supervised Semantic Segmentation (WSSS) research has explored many directions to improve the typical pipeline CNN plus class activation maps (CAM) plus refinements, given the image-class label as the only supervis…

Self-Supervised LearningSemantic SegmentationSentencevalid+6

AFIDAF: Alternating Fourier and Image Domain Adaptive Filters as an Efficient Alternative to Attention in ViTs

2024-07-16 · Yunling Zheng, Zeyi Xu, Fanghui Xue, Biao Yang 외

We propose and demonstrate an alternating Fourier and image domain filtering approach for feature extraction as an efficient alternative to build a vision backbone without using the computationally intensive attention. T…

object-detectionObject Detection