clm_66dedeafIn this paper, we show that an algorithmic change— computing proposals with a deep convolutional neural network—leads to an elegant and effective solution where proposal computation is nearly cost-free given … (excerpt)
arXiv 1506.01497 · cs.CV
Read on arXiv · arXiv non-exclusive license
Claims were extracted automatically by reducer-1 on 2026-11-12. The paper's license does not allow republishing it, so long claims are shortened to a quotation. Read the full text on arXiv.
clm_66dedeafIn this paper, we show that an algorithmic change— computing proposals with a deep convolutional neural network—leads to an elegant and effective solution where proposal computation is nearly cost-free given … (excerpt)
clm_79948a25To unify RPNs with Fast R-CNN [2] object detection networks, we propose a training scheme that alternates between fine-tuning for the region proposal task and then fine-tuning for object detection, … (excerpt)
res_bee3bb8d1 We comprehensively evaluate our method on the PASCAL VOC detection benchmarks [11] where RPNs with Fast R-CNNs produce detection accuracy better than the strong baseline of Selective Search with … (excerpt)
res_699c2515We also report results on the MS COCO dataset [12] and investigate the improvements on PASCAL VOC using the COCO data.
res_c0b9acfa[10], we have also found that RPNs can be trained jointly with Fast R-CNN networks leading to less training time. mercial systems such as at Pinterests [17], with user engagement … (excerpt)
clm_8c21be53Multi-Scale Anchors as Regression References Our design of anchors presents a novel scheme for addressing multiple scales (and aspect ratios).
res_1a6e12caNevertheless, our method achieves bounding-box regression by a different manner from previous RoIbased (Region of Interest) methods [1], [2].
res_d268742cRPN with Fast R-CNN achieves competitive results, with an mAP of 59.9% while using up to 300 proposals 8.
res_f43bf9a7Using RPN yields a much faster detection system than using either SS or EB because of shared convolutional computations; the fewer proposals also reduce the region-wise fully-connected layers’ cost (Table … (excerpt)
res_656ce84bSomewhat surprisingly, the RPN still leads to a competitive result (55.1%) when using the top-ranked 8.
res_3cf155e3The mAP is nearly unchanged with N = 1000 (55.8%), but degrades considerably to 44.6% when N = 100 .
res_15c91bbfThe mAP improves from 56.8% (using RPN+ZF) to 59.2% (using RPN+VGG).
res_9c649732Because proposals of RPN+ZF are competitive with SS (both are 58.7% when consistently used for training and testing), we may expect RPN+VGG to be better than SS.
res_f1effb25Using RPN+VGG, the result is 68.5% for unshared features, slightly higher than the SS baseline.
res_e89c7ddcFor the feature- shared variant, the result is 69.9%—better than the strong SS baseline, yet with nearly cost-free proposals.
res_55ed0facThe mAP is higher if using 3 scales (with 1 aspect ratio) or 3 aspect ratios (with 1 scale), demonstrating that using anchors of multiple sizes as the regression references … (excerpt)
res_0dbcacf7Using just 3 scales with 1 aspect ratio (69.8%) is as good as using 3 scales with 3 aspect ratios on this dataset, suggesting that scales and aspect ratios are … (excerpt)
res_b210397dThis explains why the RPN has a good ultimate detection mAP when using as few as 300 proposals.
res_0d331a32This is lower than the two-stage system (58.7%) by 4.8%.
res_ea4f8aebIncluding these [0, 0.1) samples improves mAP@0.5 on the COCO dataset for both Fast R-CNN and Faster R-CNN systems (but the impact is negligible on PASCAL VOC).
res_230de1a2Our Fast R-CNN baseline has 39.3% mAP@0.5 on the test-dev set, higher than that reported in [2].
res_c99e7743Using the COCO training set to train, Faster R-CNN has 42.1% mAP@0.5 and 21.5% mAP@[.5, .95] on the COCO test-dev set.
res_9d802d51This is 2.8% higher for mAP@0.5 and 2.2% higher for mAP@[.5, .95] than the Fast R- CNN counterpart under the same protocol (Table 11).
res_05ec7ceaUsing the COCO trainval set to train, Faster R- CNN has 42.7% mAP@0.5 and 21.9% mAP@[.5, .95] on the COCO test-dev set.
res_6665ddffThis result is better than that trained on VOC07+12 (73.2%) by a good margin, even though the PASCAL VOC data are not exploited.
res_f3f2ecbcSimilar improvements are observed on the PASCAL VOC 2012 test set (Table 12 and Table 7).
Record your result in the Mearc app on your own machine, then use Publish this result with this paper's id (1506.01497) and the claim id shown next to the claim. Mearc creates a file that holds only what you choose to publish. Add it to the public claim data by pull request; a maintainer other than you reviews it before it counts.