# Interactive Object Segmentation with Dynamic Click Transform

arXiv: https://arxiv.org/abs/2106.10465 · HTML: https://mlsanity.com/paper/2106.10465/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 21 references that are in the map.
- First posted on arXiv 19 Jun 2021.

## Builds on (most cited first, 6 of 6)

- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Deep Interactive Object Selection](https://mlsanity.com/paper/1603.04042/) (2016)
- [f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation](https://mlsanity.com/paper/2001.10331/) (2020)
- [Iteratively Trained Interactive Segmentation](https://mlsanity.com/paper/1805.04398/) (2018)
- [Getting to 99% Accuracy in Interactive Segmentation](https://mlsanity.com/paper/2003.07932/) (2020)

## Built on by (most cited first, 3 of 3)

- [Guiding the Guidance: A Comparative Analysis of User Guidance Signals for Interactive Segmentation of Volumetric Images](https://mlsanity.com/paper/2303.06942/) (2023)
- [Structured Click Control in Transformer-based Interactive Segmentation](https://mlsanity.com/paper/2405.04009/) (2024)
- [Panoptic One-Click Segmentation: Applied to Agricultural Data](https://mlsanity.com/paper/2303.08689/) (2023)

## Abstract (arXiv)

In the interactive segmentation, users initially click on the target object to segment the main body and then provide corrections on mislabeled regions to iteratively refine the segmentation masks. Most existing methods transform these user-provided clicks into interaction maps and concatenate them with image as the input tensor. Typically, the interaction maps are determined by measuring the distance of each pixel to the clicked points, ignoring the relation between clicks and mislabeled regions. We propose a Dynamic Click Transform Network~(DCT-Net), consisting of Spatial-DCT and Feature-DCT, to better represent user interactions. Spatial-DCT transforms each user-provided click with individual diffusion distance according to the target scale, and Feature-DCT normalizes the extracted feature map to a specific distribution predicted from the clicked points. We demonstrate the effectiveness of our proposed method and achieve favorable performance compared to the state-of-the-art on three standard benchmark datasets.