FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1595095002> ?p ?o ?g. }

• W1595095002 abstract "Many classes of objects can now be successfully detected with statistical machine learning techniques. Faces, cars and pedestrians, have all been detected with low error rates by learning their appearance in a highly generic manner from extensive training sets. These recent advances have enabled the use of reliable object detection components in real systems, such as automatic face focusing functions on digital cameras. One key drawback of these methods, and the issue addressed here, is the prohibitive requirement that training sets contain thousands of manually annotated examples. We present three methods which make headway toward reducing labeling requirements and in turn, toward a tractable solution to the general detection problem. First, we propose a new learning strategy for object detection. The proposed scheme forgoes the need to train a collection of detectors dedicated to homogeneous families of poses, and instead learns a single classifier that has the inherent ability to deform based on the signal of interest. We train a detector with a standard AdaBoost procedure by using combinations of pose-indexed features and pose estimators. This allows the learning process to select and combine various estimates of the pose with features able to compensate for variations in pose without the need to label data for training or explore the pose space in testing. We validate our framework on three types of data: hand video sequences, aerial images of cars, as well as face images. We compare our method to a standard Boosting framework, with access to the same ground truth, and show a reduction in the false alarm rate of up to an order of magnitude. Where possible, we compare our method to the state-of-the art, which requires pose annotations of the training data, and demonstrate comparable performance. Second, we propose a new learning method which exploits temporal consistency to successfully learn a complex appearance model from a sparsely labeled training video. Our approach consists in iteratively improving an appearance-based model built with a Boosting procedure, and the reconstruction of trajectories corresponding to the motion of multiple targets. We demonstrate the efficiency of our procedure by learning a pedestrian detector from videos and a cell detector from microscopy image sequences. In both cases, our method is demonstrated to reduce the labeling requirement by one to two orders of magnitude. We show that in some instances, our method trained with sparse labels on a video sequence is able to outperform a standard learning procedure trained with the fully labeled sequence. Third, we propose a new active learning procedure which exploits the spatial structure of image data and queries entire scenes or frames of a video rather than individual examples. We extend the Query by Committee approach allowing it to characterize the most informative scenes that are to be selected for labeling. We show that an aggressive procedure which exhibits zero tolerance to target localization error performs as well as more sophisticated strategies taking into account the trade-off between missed detections and localization error. Finally, we combine this method with our two proposed approaches above and demonstrate that the resulting algorithm can properly perform car detection from a small set of annotated image as well as pedestrian detection from a handful of labeled video frames." @default.
• W1595095002 created "2016-06-24" @default.
• W1595095002 creator A5084446948 @default.
• W1595095002 date "2012-01-01" @default.
• W1595095002 modified "2023-09-23" @default.
• W1595095002 title "Learning to Detect Objects with Minimal Supervision" @default.
• W1595095002 cites W1485283426 @default.
• W1595095002 cites W1496659369 @default.
• W1595095002 cites W1555563476 @default.
• W1595095002 cites W1573508639 @default.
• W1595095002 cites W1576445103 @default.
• W1595095002 cites W1582044912 @default.
• W1595095002 cites W1585385982 @default.
• W1595095002 cites W1608462934 @default.
• W1595095002 cites W1630959083 @default.
• W1595095002 cites W1638573433 @default.
• W1595095002 cites W1759219755 @default.
• W1595095002 cites W1970255615 @default.
• W1595095002 cites W1971293974 @default.
• W1595095002 cites W1973058695 @default.
• W1595095002 cites W1981176352 @default.
• W1595095002 cites W1984525543 @default.
• W1595095002 cites W1988790447 @default.
• W1595095002 cites W1992825118 @default.
• W1595095002 cites W1994030361 @default.
• W1595095002 cites W2024046085 @default.
• W1595095002 cites W2032194607 @default.
• W1595095002 cites W2042932437 @default.
• W1595095002 cites W2045798786 @default.
• W1595095002 cites W2048679005 @default.
• W1595095002 cites W2054373439 @default.
• W1595095002 cites W2080021732 @default.
• W1595095002 cites W2082125094 @default.
• W1595095002 cites W2084844503 @default.
• W1595095002 cites W2085989833 @default.
• W1595095002 cites W2098663280 @default.
• W1595095002 cites W2104156750 @default.
• W1595095002 cites W2104671481 @default.
• W1595095002 cites W2105488551 @default.
• W1595095002 cites W2110122948 @default.
• W1595095002 cites W2110135697 @default.
• W1595095002 cites W2111316763 @default.
• W1595095002 cites W2111557120 @default.
• W1595095002 cites W2112076978 @default.
• W1595095002 cites W2115578160 @default.
• W1595095002 cites W2116871363 @default.
• W1595095002 cites W2120369594 @default.
• W1595095002 cites W2120419212 @default.
• W1595095002 cites W2121601095 @default.
• W1595095002 cites W2123456673 @default.
• W1595095002 cites W2124386111 @default.
• W1595095002 cites W2124722975 @default.
• W1595095002 cites W2125489247 @default.
• W1595095002 cites W2125799637 @default.
• W1595095002 cites W2126666380 @default.
• W1595095002 cites W2131225894 @default.
• W1595095002 cites W2133366724 @default.
• W1595095002 cites W2140274257 @default.
• W1595095002 cites W2143343451 @default.
• W1595095002 cites W2148603752 @default.
• W1595095002 cites W2148999380 @default.
• W1595095002 cites W2151023586 @default.
• W1595095002 cites W2151103935 @default.
• W1595095002 cites W2151259137 @default.
• W1595095002 cites W2152473410 @default.
• W1595095002 cites W2154376992 @default.
• W1595095002 cites W2154422044 @default.
• W1595095002 cites W2155511848 @default.
• W1595095002 cites W2155904486 @default.
• W1595095002 cites W2156406284 @default.
• W1595095002 cites W2156539399 @default.
• W1595095002 cites W2157958821 @default.
• W1595095002 cites W2160225842 @default.
• W1595095002 cites W2161969291 @default.
• W1595095002 cites W2162915993 @default.
• W1595095002 cites W2164598857 @default.
• W1595095002 cites W2166770390 @default.
• W1595095002 cites W2170717121 @default.
• W1595095002 cites W2171243491 @default.
• W1595095002 cites W2172704881 @default.
• W1595095002 cites W2217896605 @default.
• W1595095002 cites W2534262995 @default.
• W1595095002 cites W2739698496 @default.
• W1595095002 cites W3097096317 @default.
• W1595095002 cites W3104873989 @default.
• W1595095002 doi "https://doi.org/10.5075/epfl-thesis-5310" @default.
• W1595095002 hasPublicationYear "2012" @default.
• W1595095002 type Work @default.
• W1595095002 sameAs 1595095002 @default.
• W1595095002 citedByCount "0" @default.
• W1595095002 crossrefType "journal-article" @default.
• W1595095002 hasAuthorship W1595095002A5084446948 @default.
• W1595095002 hasConcept C119857082 @default.
• W1595095002 hasConcept C141404830 @default.
• W1595095002 hasConcept C153180895 @default.
• W1595095002 hasConcept C154945302 @default.
• W1595095002 hasConcept C2776151529 @default.
• W1595095002 hasConcept C31510193 @default.
• W1595095002 hasConcept C31972630 @default.
• W1595095002 hasConcept C41008148 @default.

• next