Training for Task Specific Keypoint Detection

Strecha, Christoph; Lindner, Albrecht; Ali, Karim; Fua, Pascal

doi:10.1007/978-3-642-03798-6_16

Cited by 28 publications

(16 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Repeatability is also considered in the extended version FAST-ER [31], but it did not play a significant role. [38] trained the Wald-Boost classifier [36] to learn keypoints with high repeatability on a pre-aligned training set, and then filter out an initial set of keypoints according to the score of the classifier. Their method, called TaSK, is probably the most related to our method in the sense that they use pre-aligned images to build the training set.…”

Section: Related Workmentioning

confidence: 99%

TILDE: A Temporally Invariant Learned DEtector

Verdie

Fua

et al. 2015

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

299

261

View full text Add to dashboard Cite

We introduce a learning-based approach to detect repeatable keypoints under drastic imaging changes of weather and lighting conditions to which state-of-the-art keypoint detectors are surprisingly sensitive. We first identify good keypoint candidates in multiple training images taken from the same viewpoint. We then train a regressor to predict a score map whose maxima are those points so that they can be found by simple non-maximum suppression. As there are no standard datasets to test the influence of these kinds of changes, we created our own, which we will make publicly available. We will show that our method significantly outperforms the state-of-the-art methods in such challenging conditions, while still achieving state-of-the-art performance on the untrained standard Oxford dataset

show abstract

Section: Related Workmentioning

confidence: 99%

TILDE: A Temporally Invariant Learned DEtector

Verdie

Fua

et al. 2015

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

299

261

View full text Add to dashboard Cite

show abstract

“…By additionally introducing locations from those images where these stable points were not originally detected into the training set, TILDE outperforms DoG in terms of repeatability. TaSK [16] and LIFT [19] also detects anchor points based on similar strategies. The downside of such approaches is that the performance of the learned detector is dependent on the anchor detector used, i.e for certain transformations the learned detector can also reflect the poor performance of the anchor detector.…”

Section: Related Workmentioning

confidence: 99%

An Improved Learning Framework for Covariant Local Feature Detection

Doiphode¹,

Mitra²,

Ahmed³

et al. 2019

Computer Vision – ACCV 2018

View full text Add to dashboard Cite

Learning feature detection has been largely an unexplored area when compared to handcrafted feature detection. Recent learning formulations use the covariant constraint in their loss function to learn covariant detectors. However, just learning from covariant constraint can lead to detection of unstable features. To impart further, stability detectors are trained to extract pre-determined features obtained by handcrafted detectors. However, in the process they lose the ability to detect novel features. In an attempt to overcome the above limitations, we propose an improved scheme by incorporating covariant constraints in form of triplets with addition to an affine covariant constraint. We show that using these additional constraints one can learn to detect novel and stable features without using pre-determined features for training. Extensive experiments show our model achieves state-of-the-art performance in repeatability score on the well known datasets such as Vgg-Affine, EF, and Webcam.

show abstract

“…This approach leads to interesting results, although it uses a WaldBoost classifier instead of CNNs. Another approach tunes for specific tasks such as detecting keypoints from man-made structures [24]. Other machine learning approaches include using Genetic Programming [25], and learning linear filters [19] where the lack of non-linearity makes it more suited for very specific tasks.…”

Section: Related Workmentioning

confidence: 99%

KCNN: Extremely-Efficient Hardware Keypoint Detection with a Compact Convolutional Neural Network

Febbo¹,

Mutto²,

Tieu³

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

Keypoint detection algorithms are typically based on handcrafted combinations of derivative operations implemented with standard image filtering approaches. The early layers of Convolutional Neural Networks (CNNs) for image classification, whose implementation is nowadays often available within optimized hardware units, are characterized by a similar architecture. Therefore, the exploration of CNNs for keypoint detection is a promising avenue to obtain a low-latency implementation, also enabling to effectively move the computational cost of the detection to dedicated Neural Network processing units. This paper proposes a methodology for effective keypoint detection by means of an efficient CNN characterized by a compact three-layer architecture. A novel training procedure is proposed for learning values of the network parameters which allow for an approximation of the response of handcrafted detectors, showing that the proposed architecture is able to obtain results comparable with the state of the art. The capability of emulating different detectors allows to deploy a variety of algorithms to dedicated hardware by simply retraining the network. A sensor-based FPGA implementation of the introduced CNN architecture is presented, allowing latency smaller than 1[ms].

show abstract

Training for Task Specific Keypoint Detection

Cited by 28 publications

References 17 publications

TILDE: A Temporally Invariant Learned DEtector

TILDE: A Temporally Invariant Learned DEtector

An Improved Learning Framework for Covariant Local Feature Detection

KCNN: Extremely-Efficient Hardware Keypoint Detection with a Compact Convolutional Neural Network

Contact Info

Product

Resources

About