Cracking BING and Beyond
The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Abstract
The problem, generic objectness proposal, aims to reduce the candidate windows for object detection tasks. The popular evaluation criterion for related methods is detection-rate/windows-amount(DR-#WIN), where DR is the percentage of groundtruth objects covered by proposal windows. An object is considered “covered” by a window only if the strict PASCAL-overall criterion [3] is satisfied (the intersection of a proposal window and the object rectangle is not smaller than half of their union, so we call it “0.5-criterion” for short). Under the DR-#WIN evaluation framework, BING [2] in CVPR2014, obtains the best performance on the VOC2007 test set. It recalls 96.2% objects with only 1,000 proposal windows. The more surprising is the method is totally a realtime one. The authors of BING suggest that, after being resized to a fixed size (8× 8), almost all annotated rectangle regions share a common characteristics in gradients [2]. This commonness is captured by a template W learned from training images with a linear SVM. Besides this, the subtle differences between diverse width/height configurations are captured in a re-weighting model. Therefore BING consists of two stages: calculating W in stage I, and learning the re-weighting model in stage II. Furthermore, BING uses smart bitwise operations to calculate the inner product of W and candidate windows, so to improve the efficiency. We designed several templates by hands to substitute W , to verify whether templates play a key role in BING. These templates become less correlated to W in turn, but their performances on VOC 2007 test set are very close, see Fig.1.a. Next we discarded any templates and directly assigned the scores of stage I with uniformly random values (we call this method RAND-SCORE). Surprisingly, the performance of RANDSCORE is even very close to BING, as shown in Fig.1.b. It is clear that these templates do not have as strong significance as suggested in [2]. Then what on earth makes BING performing so well? To get the deep insight, we finished a theoretical analysis from the view of combinatorial geometry. We try to construct a small set of windows to “cover” all legal rectangles (we call it a full cover set). This is an atypical covering problem in combinatorial geometry [1]. We proposed four lemmas to solve it in the full paper. In conclusion, for an image of the width M and height N, we can use s(i, j)windows of the width 2i · √ 2 and height 2 j · √ 2 to cover all 2i ≤ w ≤ 2i+1,2 j ≤ h ≤ 2 j+1 rectangle regions, where s(i, j) = ⌈ M−2i ( 1− √ 2 2 ) ·2i· √ 2 ⌉ · ⌈ N−2 j ( 1− √ 2 2 ) ·2 j · √ 2 ⌉. Suppose the image size
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Histograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584
Segmentation as selective search for object recognition
van de Sande, K. E. A., Uijlings, J. R. R., Gevers, T., & Smeulders, A. W. M. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126456 · Cited by 739 · cited 1×
“In recent years, generic objectness proposal which aims to reduce the candidate windows in the preprocessing stage [1][2], has gained wide attention [7][8][10][16][17][12].”
Background
Cited by
What Makes for Effective Detection Proposals?
Hosang, J., Benenson, R., Dollar, P., & Schiele, B. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2465908 · Cited by 727
LocNet: Improving Localization Accuracy for Object Detection
Gidaris, S., & Komodakis, N. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.92 · Cited by 154
Towards Real-Time Object Detection on Embedded Systems
Mao, H., Yao, S., Tang, T., Li, B., Yao, J., & Wang, Y. (2018) · IEEE Transactions on Emerging Topics in Computing · doi:10.1109/tetc.2016.2593643 · Cited by 94
Attend Refine Repeat: Active Box Proposal Generation via In-Out Localization
Gidaris, S., & Komodakis, N. (2016) · Procedings of the British Machine Vision Conference 2016 · doi:10.5244/c.30.90 · Cited by 23
(2015) · arXiv (Cornell University) · Cited by 14
Metadata
- Authors
- Zhao, Q., & Liu, Z.
- Venue
- Proceedings of the British Machine Vision Conference 2014
- Publisher
- British Machine Vision Association
- Published
- 2014
- Pages
- 23.1-23.10
- OpenAlex
- W2064977923
- Cited by
- 34
- References
- 2
- FWCI
- 4.87
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.