We describe the first mobile app for identifying plant species using automatic visual recognition. The system -called Leafsnap -identifies tree species from photographs of their leaves. Key to this system are computer vision components for discarding non-leaf images, segmenting the leaf from an untextured background, extracting features representing the curvature of the leaf's contour over multiple scales, and identifying the species from a dataset of the 184 trees in the Northeastern United States. Our system obtains state-of-the-art performance on the real-world images from the new Leafsnap Dataset -the largest of its kind. Throughout the paper, we document many of the practical steps needed to produce a computer vision system such as ours, which currently has nearly a million users.

Processor designers require estimates of the architectural vulnerability factor (AVF)

Active learning provides useful tools to reduce annotation costs without compromising classifier performance. However it traditionally views the supervisor simply as a labeling machine. Recently a new interactive learning paradigm was introduced that allows the supervisor to additionally convey useful domain knowledge using attributes. The learner first conveys its belief about an actively chosen image e.g. "I think this is a forest, what do you think?". If the learner is wrong, the supervisor provides an explanation e.g. "No, this is too open to be a forest". With access to a pre-trained set of relative attribute predictors, the learner fetches all unlabeled images more open than the query image, and uses them as negative examples of forests to update its classifier. This rich human-machine communication leads to better classification performance. In this work, we propose three improvements over this set-up. First, we incorporate a weighting scheme that instead of making a hard decision reasons about the likelihood of an image being a negative example. Second, we do away with pre-trained attributes and instead learn the attribute models on the fly, alleviating overhead and restrictions of a pre-determined attribute vocabulary. Finally, we propose an active learning framework that accounts for not just the label-but also the attributes-based feedback while selecting the next query image. We demonstrate significant improvement in classification accuracy on faces and shoes. We also collect and make available the largest relative attributes dataset containing 29 attributes of faces from 60 categories.

The huge investment in the design and production of multicore processors may be put at risk because the emerging highly miniaturized but unreliable fabrication technologies will impose significant barriers to the life-long reliable operation of future chips. Extremely complex, massively parallel, multi-core processor chips fabricated in these technologies will become more vulnerable to: (a) environmental disturbances that produce transient (or soft) errors, (b) latent manufacturing defects as well as aging/wearout phenomena that produce permanent (or hard) errors, and (c) verification inefficiencies that allow important design bugs to escape in the system. In an effort to cope with these reliability threats, several research teams have recently proposed multicore processor architectures that provide low-cost dependability guarantees against hardware errors and design bugs. This paper focuses on dependable multicore processor architectures that integrate solutions for online error detection, diagnosis, recovery, and repair during field operation. It discusses taxonomy of representative approaches and presents a qualitative comparison based on: hardware cost, performance overhead, types of faults detected, and detection latency. It also describes in more detail three recently proposed effective architectural approaches: a software-anomaly detection technique (SWAT), a dynamic verification technique (Argus), and a core salvaging methodology.

Differences in pet dogs’ and captive wolves’ ability to follow human communicative intents have led to the proposition of several hypotheses regarding the possession and development of social cognitive skills in dogs. It is possible that the social cognitive abilities of pet dogs are induced by indirect conditioning through living with humans, and studying free-ranging dogs can provide deeper insights into differentiating between innate abilities and conditioning in dogs. Free-ranging dogs are mostly scavengers, indirectly depending on humans for their sustenance. Humans can act both as food providers and as threats to these dogs, and thus understanding human gestures can be a survival need for the free-ranging dogs. We tested the responsiveness of such dogs in urban areas toward simple human pointing cues using dynamic proximal points. Our experiment showed that pups readily follow proximal pointing and exhibit weaker avoidance to humans, but stop doing so at the later stages of development. While juveniles showed frequent and prolonged gaze alternations, only adults adjusted their behaviour based on the reliability of the human experimenter after being rewarded. Thus free-ranging dogs show a tendency to respond to human pointing gestures, with a certain level of behavioural plasticity that allows learning from ontogenic experience.