A Self-Paced Multiple-Instance Learning Framework for Co-Saliency Detection

By Dingwen Zhang, Deyu Meng, Chao Li, Lu Jiang, Qian Zhao, Junwei Han. 2015

136 citations recorded by the source corpus.

As an interesting and emerging topic, co-saliency detection aims at simultaneously extracting common salient objects in a group of images. Traditional co-saliency detection approaches rely heavily on human knowledge for designing hand-crafted metrics to explore the intrinsic patterns underlying co-salient objects. Such strategies, however, always suffer from poor generalization capability to flexibly adapt various scenarios in real applications, especially due to their lack of insightful understanding of the biological mechanisms of human visual co-attention. To alleviate this problem, we propose a novel framework for this task, by naturally reformulating it as a multiple-instance learning (MIL) problem and further integrating it into a self-paced learning (SPL) regime. The proposed framework on one hand is capable of fitting insightful metric measurements and discovering common patterns under co-salient regions in a self-learning way by MIL, and on the other hand tends to promise the learning reliability and stability by simulating the human learning process through SPL. Experiments on benchmark datasets have demonstrated the effectiveness of the proposed framework as compared with the state-of-the-arts.

Subfields: Computer Vision and Pattern Recognition, Sensory Systems

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

In Sensory Systems

Citations in the corpus

Video Representation Learning Using Discriminative Pooling (2018, methodology): “An important component of our scheme is the MIL scheme, which is a popular data selection technique [7, 26, 57, 58, 62].”
Review of Visual Saliency Detection With Comprehensive Information (2018, background): “SPMI [74] 2015 learning self-paced multi-instance learning”
Self-Paced Boost Learning for Classification (2016, methodology): “SPL is applied in different applications, such as image segmentation [Kumar et al., 2011], multimedia reranking [Jiang et al., 2014a], matrix factorization [Zhao et al., 2015], and multiple instance learning [Zhang et al., 2015].”
Toward unsupervised, multi-object discovery in large-scale image collections (2020, background): “it is implicit in several successful approaches to image retrieval [18,37] or cosaliency detection [2,3,35].”
Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models (2024, background): “Initial studies in curriculum learning introduced efficient algorithms that adhere to an ‘easy-to-hard’ progression (Spitkovsky et al., 2009; Kumar et al., 2010; Lee & Grauman, 2011; Zhang et al., 2015).”
Co-Saliency Detection via a Self-Paced Multiple-Instance Learning Framework (2017, methodology): “Compared with the conference version of the work [19], this paper makes the following extensions: 1) We introduce an additional term in the self-paced regularizer to explore the spatial smoothness of the superpixel instances during the learning process.”
What Objective Does Self-paced Learning Indeed Optimize? (2015, background): “…considerably necessary for future developments of CL, SPL and their re- lated realizations, and will illuminate whether the SPL methodology would be just an idealistic method occasionally perform on several datasets, or a rigorous and solid scientific research field worthy to be further explored.”
A Survey on Curriculum Learning (2021, background): “(iii) For inex-act supervision, i.e., only coarse-grained labels are given, CL helps to gradually integrate conﬁdent ﬁne-grained pseudo labels into training while denoising the noisy ones, usually under a multi-instance learning framework [34], [111], [134], [135].”
Easy Questions First? A Case Study on Curriculum Learning for Question Answering (2016, background): “Since its inception, variations of SPL such as self-paced re-ranking (Jiang et al., 2014a), self-paced learning with diversity (Jiang et al., 2014b), self-paced multiple-instance learning (Zhang et al., 2015) and self-paced curriculum learning (Jiang et al., 2015) have been proposed.”