Co-Saliency Detection via a Self-Paced Multiple-Instance Learning Framework

TLDR

Co‑saliency detection seeks to simultaneously extract common salient objects from a group of images, yet existing hand‑crafted metric approaches and unsupervised methods suffer from poor generalization and weak performance in complex scenarios. This work introduces a self‑paced multiple‑instance learning (SP‑MIL) framework that jointly leverages MIL and SPL to overcome these limitations. By formulating co‑saliency as an MIL problem, the framework learns discriminative instance‑level classifiers that automatically generate metrics for intra‑image contrast and inter‑image consistency, while the embedded SPL component mitigates data ambiguity under weak supervision and guides robust learning in challenging settings. Experiments on benchmark datasets and extended computer‑vision applications demonstrate that the proposed SP‑MIL framework surpasses state‑of‑the‑art methods.

Abstract

As an interesting and emerging topic, co-saliency detection aims at simultaneously extracting common salient objects from a group of images. On one hand, traditional co-saliency detection approaches rely heavily on human knowledge for designing hand-crafted metrics to possibly reflect the faithful properties of the co-salient regions. Such strategies, however, always suffer from poor generalization capability to flexibly adapt various scenarios in real applications. On the other hand, most current methods pursue co-saliency detection in unsupervised fashions. This, however, tends to weaken their performance in real complex scenarios because they are lack of robust learning mechanism to make full use of the weak labels of each image. To alleviate these two problems, this paper proposes a new SP-MIL framework for co-saliency detection, which integrates both multiple instance learning (MIL) and self-paced learning (SPL) into a unified learning framework. Specifically, for the first problem, we formulate the co-saliency detection problem as a MIL paradigm to learn the discriminative classifiers to detect the co-saliency object in the "instance-level". The formulated MIL component facilitates our method capable of automatically producing the proper metrics to measure the intra-image contrast and the inter-image consistency for detecting co-saliency in a purely self-learning way. For the second problem, the embedded SPL paradigm is able to alleviate the data ambiguity under the weak supervision of co-saliency detection and guide a robust learning manner in complex scenarios. Experiments on benchmark datasets together with multiple extended computer vision applications demonstrate the superiority of the proposed framework beyond the state-of-the-arts.