Unsupervised Learning of Discriminative Attributes and Visual Representations — Supplementary Material
نویسندگان
چکیده
l(bi, b + i , b − i ) = max ( 0, ρ+H(bi, b + i ))−H(bi, b − i )) ) , (1) whereH(·, ·) is the Hamming distance between hash codes, ρ is a margin between the Hamming distances of withincluster code pair {bi, b+i } and between-cluster code pair {bi, bi }. The hinge loss is a convex approximation to the 0-1 ranking error, which measures the network’s violation of the ranking order specified in the triplet. For continous optimization we relax our hashing function to:
منابع مشابه
Unsupervised Learning of Discriminative Relative Visual Attributes
Unsupervised learning of relative visual attributes is important because it is often infeasible for a human annotator to predefine and manually label all the relative attributes in large datasets. We propose a method for learning relative visual attributes given a set of images for each training class. The method is unsupervised in the sense that it does not require a set of predefined attribut...
متن کاملDeep Unsupervised Domain Adaptation for Image Classification via Low Rank Representation Learning
Domain adaptation is a powerful technique given a wide amount of labeled data from similar attributes in different domains. In real-world applications, there is a huge number of data but almost more of them are unlabeled. It is effective in image classification where it is expensive and time-consuming to obtain adequate label data. We propose a novel method named DALRRL, which consists of deep ...
متن کاملThe red one!: On learning to refer to things based on their discriminative properties
As a first step towards agents learning to communicate about their visual environment, we propose a system that, given visual representations of a referent (CAT) and a context (SOFA), identifies their discriminative attributes, i.e., properties that distinguish them (has_tail). Moreover, although supervision is only provided in terms of discriminativeness of attributes for pairs, the model lear...
متن کاملThe red one!: On learning to refer to things based on discriminative properties
As a first step towards agents learning to communicate about their visual environment, we propose a system that, given visual representations of a referent (CAT) and a context (SOFA), identifies their discriminative attributes, i.e., properties that distinguish them (has_tail). Moreover, although supervision is only provided in terms of discriminativeness of attributes for pairs, the model lear...
متن کاملDiscovering Multi-relational Latent Attributes by Visual Similarity Networks
The key problems in visual object classification are: learning discriminative feature to distinguish between two or more visually similar categories ( e.g. dogs and cats), modeling the variation of visual appearance within instances of the same class (e.g. Dalmatian and Chihuahua in the same category of dogs), and tolerate imaging distortion (3D pose). These account to within and between class ...
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 2016