Supplementary Materials for: Unsupervised Object Class Discovery via Saliency-Guided Multiple Class Learning
نویسندگان
چکیده
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 integrating H out:
منابع مشابه
Distinct Class-Specific Saliency Maps for Weakly Supervised Semantic Segmentation
Improved points (each point contributes 1~3pt improvement) Fully Convolutional Net Guided back propagation [2] Use the derivatives of multiple intermediate layers Aggregate multi-scale class saliency maps (3 scales) Assumption Raw saliency maps are affected by both class-specific saliency and generic object-ness The degree of class saliency factors should be larger than the generic object-ness ...
متن کاملWeakly supervised learning from images and videos∗
With the amount of on-line available digital content growing daily, large-scale, weakly supervised learning is becoming more and more important. In this talk we present some recent results for weakly supervised learning from images and videos. Standard approaches to object category localization require bounding box annotations of object instances. This time-consuming annotation process is sides...
متن کاملConsensusClusterPlus: a class discovery tool with confidence assessments and item tracking
UNLABELLED Unsupervised class discovery is a highly useful technique in cancer research, where intrinsic groups sharing biological characteristics may exist but are unknown. The consensus clustering (CC) method provides quantitative and visual stability evidence for estimating the number of unsupervised classes in a dataset. ConsensusClusterPlus implements the CC method in R and extends it with...
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 کاملClustering and Detection of Hub in a Complex Networks via the Laplacian Matrix
In clustering (also known as unsupervised learning and class discovery), the classes are unknown a priori and need to be identified from the unsupervised data. The cluster analysis is concerned about estimating the number of classes and assigning each observation to a certain class. In this article we discuss a method for clustering via the Laplacian matrix. Also, based on a similar argument, w...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2012