Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

computer-vision-1

Weakly supervised segmentation

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in weakly-supervised-segmentation-1

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

Use these libraries to find weakly-supervised-segmentation-1 models and implementations

Datasets

ACDC Scribbles

MARIDA

CheXlocalize

Subtasks

No subtasks available.

Most implemented papers

OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold

Mohamed Yousef, Tom E. Bishop•Sun May 31 2020

A novel and simple neural network module is proposed, termed OrigamiNet, that can augment any CTC-trained, fully convolutional single line text recognizer, to convert it into a multi-line version by providing the model with enough spatial capacity to be able to properly collapse a 2D input signal into 1D without losing information.

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

Learn To Pay Attention

Philip H. S. Torr, Namhoon Lee, Nicholas A. Lord, Saumya Jetley•Wed Feb 14 2018

An end-to-end-trainable attention module for convolutional neural network (CNN) architectures built for image classification that is able to bootstrap standard CNN architectures for the task of image classification, demonstrating superior generalisation over 6 unseen benchmark datasets.

463 0

Paper Graph

Integral Object Mining via Online Attention Accumulation

Peng-Tao Jiang, Ming-Ming Cheng, Yunchao Wei, Qibin Hou, H. Xiong, Yang Cao•Mon Sep 30 2019

Object attention maps generated by image classifiers are usually used as priors for weakly-supervised segmentation approaches. However, normal image classifiers produce attention only at the most discriminative object parts, which limits the performance of weakly-supervised segmentation task. Therefore, how to effectively identify entire object regions in a weakly-supervised manner has always been a challenging and meaningful problem. We observe that the attention maps produced by a classification network continuously focus on different object parts during training. In order to accumulate the discovered different object parts, we propose an online attention accumulation (OAA) strategy which maintains a cumulative attention map for each target category in each training image so that the integral object regions can be gradually promoted as the training goes. These cumulative attention maps, in turn, serve as the pixel-level supervision, which can further assist the network in discovering more integral object regions. Our method (OAA) can be plugged into any classification network and progressively accumulate the discriminative regions into integral objects as the training process goes. Despite its simplicity, when applying the resulting attention maps to the weakly-supervised semantic segmentation task, our approach improves the existing state-of-the-art methods on the PASCAL VOC 2012 segmentation benchmark, achieving a mIoU score of 66.4% on the test set. Code is available at https://mmcheng.net/oaa/.

244 0

Paper Graph

Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images via Max-Min Uncertainty

Eric Granger, Luke McCaffrey, Ismail Ben Ayed, J. Dolz, Soufiane Belharbi, Jérôme Rony•Fri Nov 13 2020

High uncertainty is introduced as a criterion to localize non-discriminative regions that do not affect classifier decision, and is described with original Kullback-Leibler (KL) divergence losses evaluating the deviation of posterior predictions from the uniform distribution.

59 0

Paper Graph

Learning Whole-Slide Segmentation from Inexact and Incomplete Labels using Tissue Graphs

Guillaume Jaume, J. Thiran, Pushpak Pati, M. Gabrani, Behzad Bozorgtabar, Valentin Anklin, Antonio Foncubierta-Rodríguez, M. Sibony, O. Goksel•Wed Mar 03 2021

This paper proposes SegGini, a weakly supervised segmentation method using graphs that can utilize weak multiplex annotations, i.e. inexact and incomplete annotations, to segment arbitrary and large images, scaling from tissue microarray to whole slide image (WSI).

44 0

Paper Graph

Adaptive Early-Learning Correction for Segmentation from Noisy Annotations

Yiqiu Shen, Sheng Liu, Kangning Liu, Weicheng Zhu, C. Fernandez‐Granda•Wed Oct 06 2021

This work study the learning dynamics of deep segmentation networks trained on inaccurately annotated data and proposes a new method for segmentation from noisy annotations with two key elements, which outperforms standard approaches on a medical-imaging segmentation task where noises are synthesized to mimic human annotation errors.

121 0

Paper Graph

Land Cover Segmentation with Sparse Annotations from Sentinel-2 Imagery

Edoardo Arnaudo, Luca Barco, Marco Galatola, C. Rossi, F. Dominici•Tue Jun 27 2023

SPADA is introduced, a framework for fuel map delineation that addresses the challenges associated with LC segmentation using sparse annotations and domain adaptation techniques for semantic segmentation, and outperforms state-of-the-art semantic segmentations approaches as well as third-party products.

2 0

Paper Graph

Constrained Convolutional Neural Networks for Weakly Supervised Segmentation

Philipp Krähenbühl, Trevor Darrell, Deepak Pathak•Wed Jun 10 2015

This work proposes Constrained CNN (CCNN), a method which uses a novel loss function to optimize for any set of linear constraints on the output space of a CNN, and demonstrates the generality of this new learning framework.

638 0

Paper Graph

Adding a benchmark result helps the community track progress.

Weakly supervised segmentation | State-of-the-Art