Unsupervised Object Class Discovery via Saliency-Guided Multiple Class Learning
نویسندگان
چکیده
منابع مشابه
Supplementary Materials for: Unsupervised Object Class Discovery via Saliency-Guided Multiple Class Learning
1. Proof for Theorems Now we will do discriminative learning with the presence of hidden variables. Our step is similar to standard EM[3] while the primary difference is that we are given labels Y = {y1, . . . , yn} in addition to observations X = {x1, . . . , xn}, and we want to estimate the model θ that minimizes the negative log-likelihood function L(θ;Y,X) = − log Pr(Y |X; θ). We proceed by...
متن کاملDistinct Class Saliency Maps for Multiple Object Images
This paper proposes a method to obtain more distinct class saliency maps than Simonyan et al. (2014). We made three improvements over their method: (1) using CNN derivatives with respect to feature maps of the intermediate convolutional layers with up-sampling instead of an input image; (2) subtracting saliency maps of the other classes from saliency maps of the target class to differentiate ta...
متن کاملOne-Class Multiple Instance Learning via Robust PCA for Common Object Discovery
Principal component analysis (PCA), as a key component in statistical learning, has been adopted in a wide variety of applications in computer vision and machine learning. From a different angle, weakly supervised learning, more specifically multiple instance learning (MIL), allows fine-grained information to be exploited from coarsely-grained label information. In this paper, we propose an alg...
متن کاملUnsupervised Visual Object Class Recognition
Object class recognition is a very well studied problem in the domain of Computer Vision. Lately, the most successful approaches extract informative descriptors from the images, organize them and use machine learning techniques for learning and classification tasks. A common approach involves the construction of a visual vocabulary which is used to express the content of the image, and the appl...
متن کاملObject Class Recognition by Unsupervised Scale-Invariant Learning
We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. Objects are modeled as flexible constellations of parts. A probabilistic representation is used for all aspects of the object: shape, appearance, occlusion and relative scale. An entropy-based feature detector is used to select regions and their scale withi...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Pattern Analysis and Machine Intelligence
سال: 2015
ISSN: 0162-8828,2160-9292
DOI: 10.1109/tpami.2014.2353617