Regional Interactive Image Segmentation Networks

By J. Liew, Yunchao Wei, Wei Xiong, Sim Heng Ong, Jiashi Feng. 2017

158 citations recorded by the source corpus.

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, background): “Nevertheless, RIS-Net [23] crop multiple rois only based on click positions to make the refinement.”
Reviving Iterative Training with Mask Guidance for Interactive Segmentation (2021, methodology): “Later, [19, 20, 21, 22] propose various CNN-based methods for interactive segmentation that aimed at the refinement of predictions by increasing the diversity of predicted masks, and using the attention mechanism.”
Getting to 99% Accuracy in Interactive Segmentation (2020, methodology): “To integrate the click maps into the network, most papers (iFCN [6], RIS-Net [13], ITIS [7], DEXTR [8]) adopt an early fusion scheme by simply joining the click maps as extra channels to the input image tensor.”
Iteratively Trained Interactive Segmentation (2018, methodology): “The curve in Figure 3 b) shows however, that our method produces the best result for the initial few clicks and afterwards performs similar to RIS-Net [17].”
Deep Extreme Cut: From Extreme Points to Object Segmentation (2017, background): “Distance-map vs. ﬁxed points: Recent works [41, 40, 10] that focus on segmentation from (not-extreme) points use the distance transform of positive and negative annotations as an input to the network, in order to guide the segmentation.”
Fully Convolutional Networks for Panoptic Segmentation With Point-Based Supervision (2021, background): “In this way, users are required to give additional labels for guidance, like drawn box [69], clicked point [14], [70], and local context [71].”
Pointly-Supervised Instance Segmentation (2021, methodology): “For instance segmentation, point clicks are often used in interactive pipelines [5,29,30,35,59].”
Continuous Adaptation for Interactive Object Segmentation by Learning from Corrections (2019, methodology): “ssical methods are based on a weak appearance model which is specialized to one speciﬁc image. Recent methods rely on Convolutional Neural Networks (CNNs) to interactively produce a segmentation mask [52, 33,10,35,31,15,27,28,3]. These methods take the image and user corrections (transformed into a ”
Deep Interactive Thin Object Selection (2021, methodology): “On this task, deep learning based methods [51, 23, 50, 32, 21, 15, 31, 16, 27, 41] have been very successful.”
PhraseClick: Toward Achieving Flexible Interactive Segmentation by Phrase and Click (2020, background): “These inputs usually come in the form of user clicks/strokes [5,28,34,41,51,58] or bounding boxes [16, 29, 49, 57].”
MultiSeg: Semantically Meaningful, Scale-Diverse Segmentations From Minimal User Input (2019, methodology): “Following [23, 36], we apply graph cut [4] to the network prediction to obtain the final segmentation mask.”
A Fully Convolutional Two-Stream Fusion Network for Interactive Image Segmentation (2018, methodology): “However, the proposed network diﬀers from the network in [20] in three important aspects.”
Interactive Full Image Segmentation by Considering All Regions Jointly (2018, methodology): “Our approach of full image segmentation brings several advantages over modern interactive single object segmentation methods [24, 30, 31, 32, 36, 37, 60]: (I) It enables the annotator to focus on the largest errors in the whole image, rather than on the largest error of one given object.”
Interactive Image Segmentation via Backpropagating Refinement Scheme (2019, methodology): “Experimental results show that the proposed BRS algorithm outperforms the conventional algorithms [11, 10, 3, 52, 50, 2, 27, 26] on the GrabCut [42], Berkeley [34], DAVIS [37], and SBD [12] datasets.”
Interactive Object Segmentation With Inside-Outside Guidance (2020, methodology): “The success of CNN-based interactive segmentation has beneﬁted sig-niﬁcantly from the development of FCNs. Speciﬁcally, FCN [44], DeepLab series [10, 11, 12] and PSP [68] have been directly applied to tackle the interactive segmentation [67, 38, 45, 46].”
Interactive Video Object Segmentation in the Wild (2017, methodology): “On the Pascal dataset, our method is outperformed by [6, 12].”
FocusCut: Diving into a Focus View in Interactive Segmentation (2022, methodology): “In interactive segmentation, RIS-Net [28] has proved the significance of local refinement.”
Content-Aware Multi-Level Guidance for Interactive Instance Segmentation (2019, methodology): “For fair comparison with [53, 32], we randomly sample 10 images per category for evaluation and splitting the evaluation for the 20 Pascal categories versus the 60 additional categories.”
Large-Scale Interactive Object Segmentation With Human Annotators (2019, background): “When considering which corrective clicks should be done over a mask, the existing literature is split between clicks at the object border [26, 22, 15, 1] or clicks inside the error regions [36, 17, 16].”
Interactive Object Segmentation With Inside-Outside Guidance (2022, methodology): “According to the human inputs, the interactive segmentation approached can be roughly divided into click-based [1], [37], [38], [47], [48], [49], [50], [51] and polygon-based [52], [53], [54].”