Oldest Papers
CSDL | IEEE Computer Society
Unknown Author
computer.org
No abstract available
No ratings yet
View paper →Is Object Localization for Free? - Weakly-Supervised Learning With Convolutional Neural Networks
Oquab, Maxime, Bottou, Leon, Laptev, Ivan, Sivic, Josef
openaccess.thecvf.com
Successful visual object recognition methods typically rely on training datasets containing lots of richly annotated images. Annotating object bounding boxes is both expensive and subjective. We describe a weakly supervised convolutional neural network (CNN) for object classification that relies only on image-level labels, yet can learn from cluttered scenes containing multiple objects. We quantify its object classification and object location prediction performance on the Pascal VOC 2012 (20 object classes) and the much larger Microsoft COCO (80 object classes) datasets. We find that the network (i) outputs accurate image-level labels, (ii) predicts approximate locations (but not extents) of objects, and (iii) performs similar or better compared to its fully-supervised counterparts using object bounding box annotation for training.
No ratings yet
View paper →A beautiful loop: An active inference theory of consciousness
Ruben Laukkonen, Karl Friston, Shamil Chandaria
sciencedirect.com
Can active inference model consciousness? We offer three conditions implying that it can. The first condition is the simulation of a world model, which determines what can be known or acted upon; namely an epistemic field. The second is inferential competition to enter the world model. Only the inferences that coherently reduce long-term uncertainty win, evincing a selection for consciousness that we call Bayesian binding. The third is epistemic depth, which is the recurrent sharing of the Bayesian beliefs throughout the system. Due to this recursive loop in a hierarchical system (such as a brain) the world model contains the knowledge that it exists. This is distinct from self-consciousness, because the world model knows itself non-locally and continuously evidences this knowing (i.e., field-evidencing). Formally, we propose a hyper-model for precision-control, whose latent states (or parameters) encode and control the overall structure and weighting rules for all layers of inference. These globally integrated preferences for precision enact the epistemic agency and flexibility reminiscent of general intelligence. This Beautiful Loop Theory is also deeply revealing about altered states, meditation, and the full spectrum of conscious experience.
No ratings yet
View paper →