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-11

Unsupervised Saliency Detection

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 unsupervised-saliency-detection-11

Trend

Dataset

Best Model

Actions

ECSSD

DUTS

DUT-OMRON

Libraries

Use these libraries to find unsupervised-saliency-detection-11 models and implementations

Datasets

DUTS

DUT-OMRON

ECSSD

Subtasks

No subtasks available.

Most implemented papers

Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut

Yangtao Wang, XI Shen, S. Hu, Yuan Yuan, James L. Crowley, Dominique Vaufreydaz•Tue Feb 22 2022

A graph-based method that uses the selfsupervised transformer features to discover an object from an image using spectral clustering with generalized eigen-decomposition and showing that the second smallest eigenvector provides a cutting solution since its absolute value indicates the likelihood that a token belongs to a foreground object.

213

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

Unsupervised Salient Object Detection with Spectral Cluster Voting

Weidi Xie, Samuel Albanie, Gyungin Shin•Tue Mar 22 2022

This paper proposes a simple but effective winner-takes-all voting mechanism for selecting the salient masks, leveraging object priors based on framing and distinctiveness and trains a salient object detector, termed SELF-MASK, which outperforms prior approaches on three unsupervised SOD benchmarks.

83 0

Paper Graph

MOVE: Unsupervised Movable Object Segmentation and Detection

P. Favaro, Adam Bielski•Thu Oct 13 2022

We introduce MOVE, a novel method to segment objects without any form of supervision. MOVE exploits the fact that foreground objects can be shifted locally relative to their initial position and result in realistic (undistorted) new images. This property allows us to train a segmentation model on a dataset of images without annotation and to achieve state of the art (SotA) performance on several evaluation datasets for unsupervised salient object detection and segmentation. In unsupervised single object discovery, MOVE gives an average CorLoc improvement of 7.2% over the SotA, and in unsupervised class-agnostic object detection it gives a relative AP improvement of 53% on average. Our approach is built on top of self-supervised features (e.g. from DINO or MAE), an inpainting network (based on the Masked AutoEncoder) and adversarial training.

27 0

Paper Graph

Unsupervised Object Localization: Observing the Background to Discover Objects

Éloi Zablocki, Oriane Siméoni, Chlo'e Sekkat, Gilles Puy, Antonín Vobecký, Patrick P'erez•Wed Dec 14 2022

This work proposes FOUND, a simple model made of a single conv1 x 1 initialized with coarse background masks extracted from self-supervised patch-based representations, which reaches state-of-the-art results on unsupervised saliency detection and object discovery benchmarks.

83 0

Paper Graph

Adding a benchmark result helps the community track progress.

Unsupervised Saliency Detection | State-of-the-Art