Optimizing the decomposition for multiple foreground cosegmentation

Chang, Haw-Shiuan; Wang, Yu-Chiang Frank

doi:10.1016/j.cviu.2015.06.004

Cited by 22 publications

(12 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To further understand the image co-segmentation frameworks, we compared the co-segmentation performance of nine techniques: geometric mean saliency based cosegmentation (GMS) [121], group saliency propagation based co-segmentation (GSP) [122], saliency co-fusion based co-segmentation (SCF) [76], co-segmentation and cosketch (CSST) [89], co-segmentation and co-skeletonization (CSSL) [90], joint object discovery and segmentation (JODS) [21], decomposition multiple foreground co-segmentation (DMFC) [18], joint semantic matching and co-segmentation (JSMC) [100] and multiple random walkers based cosegmentation (MRW) [47] on iCoseg dataset, MSRC dataset, Internet dataset and Coseg-Rep dataset, respectively. The experimental results are produced by directly running the implementation codes from their websites.…”

Section: Resultsmentioning

confidence: 99%

“…Fig.7, Fig.8 and Fig.9 respectively show some visual cosegmentation results of GMS [121], GSP [122], SCF [76], CSST [89], CSSL [90] and MRW [47] on nine groups images, where Bear, Helicopter, Stongehenge from iCoseg dataset, Cat, Face, Plane from MSRC dataset, and Cranesbill, Fleabane, Seagull from Coseg-Rep dataset. Fig.10 shows some comparison co-segmentation results of JODS [21], DMFC [18], MRW [47], CSSL [90] and JSMC [100] on three groups images, where Airplane, Car, and Horse from Internet dataset. From Fig.7, Fig.8 and Fig.9, one can see that most of these techniques localize the foreground objects.…”

Section: Resultsmentioning

confidence: 99%

“…FIGURE 10. Some comparison co-segmentation results of JODS [21], DMFC [18], MRW [47], CSSL [90] and JSMC [100] on Airplane, Car, and Horse from Internet dataset. The first row shows the input images.…”

Section: Resultsmentioning

confidence: 99%

“…Images on the left are example images containing multiple objects from different semantic categories. Images on the right are co-segmentation results of [18].…”

Section: A a Brief Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Review of Recent Advances in Image Co-Segmentation Techniques

Lin

Wang

2019

IEEE Access

View full text Add to dashboard Cite

Recent advances in the corporate processing of images have exhibited its advantages over the individual processing. Image co-segmentation aims to segment shared objects from two or more relevant images, and is becoming more and more interesting for computer vision researchers. Many applications need accurate and efficient segmentation techniques: indoor navigation, autonomous driving, and virtual reality systems to name a few. Although numerous techniques have been proposed, it is still lacking a deep review of image co-segmentation techniques. In this paper, we provide a review on the fundamentals and challenges of image co-segmentation techniques. We organize the recent advances of image co-segmentation into seven major frameworks: graph based framework, clustering based framework, partial differential equation based framework, quadratic programming based framework, low rank matrix recovery based framework, joint optimization based framework, and machine learning based framework. We expect this review to be beneficial to both fresh and senior researchers in this field. INDEX TERMS Image co-segmentation, deep learning, multiple foreground, single foreground.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

“…Images on the left are example images containing multiple objects from different semantic categories. Images on the right are co-segmentation results of [18].…”

Section: A a Brief Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Review of Recent Advances in Image Co-Segmentation Techniques

Lin

Wang

2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Earlier approaches for semantic matching rely on hand-engineered features and a geometric alignment model in an energy minimization framework [1], [6], [7], [8]. Similarly, conventional object cosegmentation algorithms do not involve feature learning [9], [10], [11], [12]. The lack of end-to-end trainable features and inference pipelines often leads to limited performance.…”

Section: Introductionmentioning

confidence: 99%

Show, Match and Segment: Joint Weakly Supervised Learning of Semantic Matching and Object Co-Segmentation

Chen

Lin

Yang

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

We present an approach for jointly matching and segmenting object instances of the same category within a collection of images. In contrast to existing algorithms that tackle the tasks of semantic matching and object co-segmentation in isolation, our method exploits the complementary nature of the two tasks. The key insights of our method are two-fold. First, the estimated dense correspondence field from semantic matching provides supervision for object co-segmentation by enforcing consistency between the predicted masks from a pair of images. Second, the predicted object masks from object co-segmentation in turn allow us to reduce the adverse effects due to background clutters for improving semantic matching. Our model is end-to-end trainable and does not require supervision from manually annotated correspondences and object masks. We validate the efficacy of our approach on four benchmark datasets: TSS, Internet, PF-PASCAL, and PF-WILLOW, and show that our algorithm performs favorably against the state-of-the-art methods on both semantic matching and object co-segmentation tasks.Index Terms-Semantic matching, object co-segmentation, weakly-supervised learning. !Our work. In this paper, we propose to jointly tackle both semantic matching and object co-segmentation with a twostream network in an end-to-end trainable fashion. Our key insights are two-fold. First, to suppress the effect of background clutters, the predicted object masks by object co-segmentation allow the model to focus on matching the segmented foreground regions while excluding background matching. Second, the estimated dense correspondence fields by semantic matching provide supervision for enforcing the model to generate geometrically consistent object masks across images. Therefore, we exploit the interdependency between the two network outputs, i.e., the estimated dense correspondence fields and the predicted foreground object masks, by introducing the cross-network consistency loss. Incorporating this loss improves both tasks since it encourages arXiv:1906.05857v1 [cs.CV]

show abstract