Deep Interactive Thin Object Selection

By J. Liew, Scott D. Cohen, Brian L. Price, Long Mai, Jiashi Feng. 2021

65 citations recorded by the source corpus.

Existing deep learning based interactive segmentation methods have achieved remarkable performance with only a few user clicks, e.g. DEXTR [32] attaining 91.5% IoU on PASCAL VOC with only four extreme clicks. However, we observe even the state-of-the-art methods would often struggle in cases of objects to be segmented with elongated thin structures (e.g. bug legs and bicycle spokes). We investigate such failures, and find the critical reasons behind are two-fold: 1) lack of appropriate training dataset; and 2) extremely imbalanced distribution w.r.t. number of pixels belonging to thin and non-thin regions. Targeted at these challenges, we collect a large-scale dataset specifically for segmentation of thin elongated objects, named ThinObject-5K. Also, we present a novel integrative thin object segmentation network consisting of three streams. Among them, the high-resolution edge stream aims at preserving fine-grained details including elongated thin parts; the fixed-resolution context stream focuses on capturing semantic contexts. The two streams’ outputs are then amalgamated in the fusion stream to complement each other for help producing a refined segmentation output with sharper predictions around thin parts. Extensive experimental results well demonstrate the effectiveness of our proposed solution on segmenting thin objects, surpassing the baseline by ~ 30% IoUthin despite using only four clicks. Codes and dataset are available at https://github.com/liewjunhao/thin-object-selection.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

FocalClick: Towards Practical Interactive Image Segmentation (2022, methodology): “We also report the performance of our model trained on SBD [15], and a large combined dataset [2, 7, 13, 24, 26, 39, 45, 48].”
FocusCut: Diving into a Focus View in Interactive Segmentation (2022, methodology): “For example, the extreme points have been used in the segmentation for common objects [36], thin objecst [29], and the full image [2].”
Segment Anything in High Quality (2023, methodology): “HQSeg-44K is constructed by merging six existing image datasets [34, 29, 26, 37, 8, 45] with highly accurate mask annotations, covering over 1,000 diverse semantic classes.”