Robust Object Co-Segmentation Using Background Prior

Abstract

Given a set of images that contain objects from a common category, object co-segmentation aims at automatically discovering and segmenting such common objects from each image. During the past few years, object co-segmentation has received great attention in the computer vision community. However, the existing approaches are usually designed with misleading assumptions, unscalable priors, or subjective computational models, which do not have sufficient robustness for dealing with complex and unconstrained real-world image contents. This paper proposes a novel two-stage co-segmentation framework, mainly for addressing the robustness issue. In the proposed framework, we first introduce the concept of union background and use it to improve the robustness for suppressing the image backgrounds contained by the given image groups. Then, we also weaken the requirement for the strong prior knowledge by using the background prior instead. This can improve the robustness when scaling up for the unconstrained image contents. Based on the weak background prior, we propose a novel MR-SGS model, i.e., manifold ranking with the self-learned graph structure, which can infer suitable graph structures in a data-driven manner rather than building the fixed graph structure relying on the subjective design. Such capacity is critical for further improving the robustness in inferring the foreground/background probability of each image pixel. Comprehensive experiments and comparisons with other state-of-the-art approaches can demonstrate the effectiveness of the proposed work.

Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks

“…Table 1 shows the detailed results. We can see that our AGNN outperforms the best reported results (i.e., AGS [69]) on DAVIS 16 benchmark by a significant margin in terms of mean J (80.7 vs 79.7) and F (79.1 vs 77.4). Compared to PDB [55], which uses the same training protocol and training datasets, our AGNN yields significant performance gains of 3.5% and 4.6% in terms of mean J and mean F, respectively.…”

“…Implementation Details: Following [44,55], both static data from image salient object segmentation datasets, MSRA10K [8], DUT [72], and video data from the training set of DAVIS 16 are iteratively used to train our model. In a 'static-image' iteration, we randomly sample 6 images from the static training data to train our backbone network (DeepLabV3) to extract more discriminative foreground features.…”

“…Val-set of DAVIS 16 . We compare the proposed AGNN with the top ZVOS methods from the DAVIS 16 benchmark 1 [45].…”

“…Fig. 4 depicts visual results for the proposed AGNN on two challenging video sequences soapbox and judo of DAVIS 16 and DAVIS 17 , respectively. For soapbox, the primary objects undergo huge scale variation, deformation and view changes, but our AGNN still generates accurate foreground segments.…”

“…We perform an ablation study on DAVIS 16 [45] to investigate the effect of each essential component of AGNN.…”