Category Independent Object Proposals

By Ian Endres, Derek Hoiem. 2010

513 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation (2013, methodology): “We followed the same protocol of submitting test results to the ILSVRC2013 evaluation server only twice, once with and once without bounding-box regression.”
Scalable Object Detection Using Deep Neural Networks (2013, methodology): “In order to address this issue a variety of methods were proposed, varying from detector cascades, to using segmentation to suggest a small number of object hypotheses [14, 2, 4].”
Training Region-Based Object Detectors with Online Hard Example Mining (2016, methodology): “R-CNN, in contrast, uses region proposals [1, 2, 3, 4, 6, 10, 18, 32, 34], a method that was made popular by the selective search algorithm [32].”
What Makes for Effective Detection Proposals? (2015, background): “• In §3 we introduce the notion of proposal repeatability, discuss its relevance when considering proposals for detection, and measure the repeatability of existing methods.”
End-to-End Training of Deep Visuomotor Policies (2015, neutral): “ed by means of successive pooling layers to provide for invariance (Lee et al., 2009). Applications to localization typically either use a sliding window (Girshick et al., 2014a) or object proposals (Endres and Hoiem, 2010; Uijlings et al., 2013; Girshick et al., 2014b) to localize the object, reduc”
Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity (2022, background): “Objectness [13] measures grouping qualities; in our framework, it is critical to decide which pseudo-GT masks to select for training detectors.”
Recent advances in convolutional neural networks (2015, background): “Recently, object proposal based methods attract a lot of interests and are widely studied in the literature [107], [130– 133].”
On the Binding Problem in Artificial Neural Networks (2020, background): “…examples can be used to address this challenge in a multitude of ways, e.g. to learn a similarity function between segments (Ren and Malik, 2003; Endres and Hoiem, 2010; Kong and Fowlkes, 2018) or discrete graphical patterns (Lun et al., 2017), to learn boundary detection (Martin et al., 2004;…”
Category-specific object reconstruction from a single image (2014, background): “The realization that convolutional networks [31] trained on huge datasets worked [29], together with the development of methods for generating object segmentation proposals [12, 1, 15, 43, 3, 28] has resulted in much sudden progress in object detection and segmentation [20, 23, 11].”
DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection (2014, methodology): “arch Many approaches have been proposed to generate classindependent bounding box proposals. The recent approaches include objectness [1], selective search [48], category independent object proposals [16], constrained parametric min-cuts [7], combinatorial grouping [2], binarized normed gradients [8”
DeepBox: Learning Objectness with Convolutional Networks (2015, methodology): “[6] propose using bottom-up object proposals as a first step in recognition.”
How good are detection proposals, really? (2014, background): “We omit the slowest two methods, CPMC and Endres2010 , from this experiment because it involves running the candidate detector over the Pascal test set ~50 times (once for every perturbation).”
Deep learning for visual understanding (2017, unknown): “Currently, there are many object proposal algorithms, such as objectness [158], selective search [156], category-independent object proposals [159], BING [160], and edge boxes [161].”
Generating Object Segmentation Proposals Using Global and Local Search (2014, methodology): “Recently, a promising research direction for object detection has emerged with approaches that generate object segmentation proposals [16] [4] [5].”
Salient object detection by composition (2011, methodology): “A commonly adopted approach is to use different parameters to generate multiple segmentations and find promising candidate segments in between [5, 14].”
Learning to Navigate for Fine-grained Classification (2018, background): “Navigating to possible informative regions can be viewed as a region proposal problem, which has been widely studied in [41,11,1,7,20].”
Discovering important people and objects for egocentric video summarization (2012, methodology): “Important region prediction accuracy We first evaluate our method’s ability to predict important regions, compare d to three state-of-the-art high- and low-level saliency met hods: (1) the object-like score of [3], (2) the object-like sc ore of [6], and (3) the bottom-up saliency detector of [28].”
Action Localization with Tubelets from Motion (2014, background): “Rather than reducing the number of sliding windows, category-independent object proposals have been proposed to aid object localization [1, 7, 17, 20].”
Track and Segment: An Iterative Unsupervised Approach for Video Object Proposals (2016, background): “The state-of-the-art approaches of [33, 32] perform better with fewer proposals, by leveraging top-down cues from learned static object proposals [9, 14].”