Looking Beyond the Image: Unsupervised Learning for Object Saliency and Detection

Siva, Parthipan; Russell, Chris; Xiang, Tao; Agapito, Lourdes

doi:10.1109/cvpr.2013.416

Cited by 149 publications

(102 citation statements)

References 33 publications

Supporting

Mentioning

102

Contrasting

Order By: Relevance

“…We also combine the two and present results for joint image-video co-localization. Following previous works in weakly supervised localization (WSL) [13,17,32,[43][44][45][46] and co-localization [47], we use the CorLoc evaluation metric, defined as the percentage of images correctly localized according to the PASCAL-criterion: area(Bp∩Bgt) area(Bp∪Bgt) > 0.5, where B p is the predicted box and B gt is the ground-truth box. All CorLoc results are given in percentages.…”

Section: Resultsmentioning

confidence: 99%

“…Our method (Co-localization) [44] (WSL) [46] (WSL) [45] (WSL) [43] (WSL) [17] Table 3. CorLoc results on PASCAL07 compared to previous methods for weakly supervised localization (WSL).…”

Section: Methodsmentioning

confidence: 99%

“…The co-localization problem is similar to co-segmentation [21-24, 38, 39, 50] and weakly supervised localization (WSL) [13,17,31,32,[43][44][45][46]49]. In contrast to co-segmentation, we seek to localize objects with bounding boxes rather than segmentations, which allows us to greatly decrease the number of variables in our problem.…”

Section: Related Workmentioning

confidence: 99%

“…In addition to pixels, these images and videos are often tagged with the visual concepts they contain, leading to a natural source of weakly labeled data. Recent research has studied ways of leveraging this data, such as weakly supervised localization [13,17,32,[43][44][45][46], co-segmentation [21,23,38], and co-localization [37,47].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Efficient Image and Video Co-localization with Frank-Wolfe Algorithm

Joulin

Tang

2014

Lecture Notes in Computer Science

154

205

View full text Add to dashboard Cite

Abstract. In this paper, we tackle the problem of performing efficient co-localization in images and videos. Co-localization is the problem of simultaneously localizing (with bounding boxes) objects of the same class across a set of distinct images or videos. Building upon recent stateof-the-art methods, we show how we are able to naturally incorporate temporal terms and constraints for video co-localization into a quadratic programming framework. Furthermore, by leveraging the Frank-Wolfe algorithm (or conditional gradient), we show how our optimization formulations for both images and videos can be reduced to solving a succession of simple integer programs, leading to increased efficiency in both memory and speed. To validate our method, we present experimental results on the PASCAL VOC 2007 dataset for images and the YouTube-Objects dataset for videos, as well as a joint combination of the two.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Our method (Co-localization) [44] (WSL) [46] (WSL) [45] (WSL) [43] (WSL) [17] Table 3. CorLoc results on PASCAL07 compared to previous methods for weakly supervised localization (WSL).…”

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Efficient Image and Video Co-localization with Frank-Wolfe Algorithm

Joulin

Tang

2014

Lecture Notes in Computer Science

154

205

View full text Add to dashboard Cite

show abstract

“…This new trend is driven by object based vision applications, such as object detection [6], contentaware image resizing [3], image segmentation [4], [40], and other applications [38], [39], [41], [43]. In this work, we focus on the salient object detection, and the algorithm outputs a gray saliency image, where a brighter pixel stands for a higher saliency value.…”

Section: Introductionmentioning

confidence: 99%

Correspondence Driven Saliency Transfer

Yang

Shen

Shao

et al. 2016

IEEE Trans. on Image Process.

138

View full text Add to dashboard Cite

Abstract-In this paper, we show that large annotated data sets have great potential to provide strong priors for saliency estimation rather than merely serving for benchmark evaluations. To this end, we present a novel image saliency detection method called saliency transfer. Given an input image, we first retrieve a support set of best matches from the large database of saliency annotated images. Then, we assign the transitional saliency scores by warping the support set annotations onto the input image according to computed dense correspondences. To incorporate context, we employ two complementary correspondence strategies: a global matching scheme based on scene-level analysis and a local matching scheme based on patch-level inference. We then introduce two refinement measures to further refine the saliency maps and apply the random-walk-with-restart by exploring the global saliency structure to estimate the affinity between foreground and background assignments. Extensive experimental results on four publicly available benchmark data sets demonstrate that the proposed saliency algorithm consistently outperforms the current state-of-the-art methods.

show abstract

Salient Object Subitizing

Zhang

Sameki

et al. 2019

Visual Saliency: From Pixel-Level to Object-Level Analysis

View full text Add to dashboard Cite

We study the problem of Salient Object Subitizing, i.e. predicting the existence and the number of salient objects in an image using holistic cues. This task is inspired by the ability of people to quickly and accurately identify the number of items within the subitizing range (1-4). To this end, we present a salient object subitizing image dataset of about 14K everyday images which are annotated using an online crowdsourcing marketplace. We show that using an end-to-end trained Convolutional Neural Network (CNN) model, we achieve prediction accuracy comparable to human performance in identifying images with zero or one salient object. For images with multiple salient objects, our model also provides significantly better than chance performance without requiring any localization process. Moreover, we propose a method to improve the training of the CNN subitizing model by leveraging synthetic images. In experiments, we demonstrate the accuracy and generalizability of our CNN subitizing model and its applications in salient object detection and image retrieval.

show abstract

Looking Beyond the Image: Unsupervised Learning for Object Saliency and Detection

Cited by 149 publications

References 33 publications

Efficient Image and Video Co-localization with Frank-Wolfe Algorithm

Efficient Image and Video Co-localization with Frank-Wolfe Algorithm

Correspondence Driven Saliency Transfer

Salient Object Subitizing

Contact Info

Product

Resources

About