Localizing objects in cluttered backgrounds is a challenging task in weakly supervised localization. Due to large object variations in cluttered images, objects have large ambiguity with backgrounds. However, backgrounds contain useful latent information, e.g., the sky for aeroplanes. If we can learn this latent information, object-background ambiguity can be reduced to suppress the background. In this paper, we propose the latent category learning (LCL), which is an unsupervised learning problem given only image-level class labels. Firstly, inspired by the latent semantic discovery, we use the typical probabilistic Latent Semantic Analysis (pLSA) to learn the latent categories, which can represent objects, object parts or backgrounds. Secondly, to determine which category contains the target object, we propose a category selection method evaluating each category's discrimination. We evaluate the method on the PASCAL VOC 2007 database and ILSVRC 2013 detection challenge. On VOC 2007, the proposed method yields the annotation accuracy of 48%, which outperforms previous results by 10%. More importantly, we achieve the detection average precision of 30.9%, which improves previous results by 8% and can be competitive with the supervised deformable part model (DPM) 5.0 baseline 33.7%. On ILSVRC 2013 detection, the method yields the precision of 6.0%, which is also competitive with the DPM 5.0.
We have discovered a new, ultrafast therapy for treating skin cancer that is extremely effective with a total electric field exposure time of only 180 lsec. The application of 300 high-voltage (40 kV/ cm), ultrashort (300 nsec) electrical pulses to murine melanomas in vivo triggers both necrosis and apoptosis, resulting in complete tumor remission within an average of 47 days in the 17 animals treated. None of these melanomas recurred during a 4-month period after the initial melanoma had disappeared. These pulses generate small, long-lasting, rectifying nanopores in the plasma membrane of exposed cells, resulting in increased membrane permeability to small molecules and ions, as well as an increase in intracellular Ca 21 , DNA fragmentation, disruption of the tumor's blood supply and the initiation of apoptosis. Apoptosis was indicated by a 3-fold increase in Bad labeling and a 72% decrease in Bcl-2 labeling. In addition, microvessel density within the treated tumors fell by 93%. This new therapy utilizing nanosecond pulsed electric fields has the advantages of highly localized targeting of tumor cells and a total exposure time of only 180 lsec. These pulses penetrate into the interior of every tumor cell and initiate DNA fragmentation and apoptosis while at the same time reducing blood flow to the tumor. This new physical tumor therapy is drug free, highly localized, uses low energy, has no significant side effects and results in very little scarring. ' 2009 UICC
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.