We generalize the class vectors found in neural networks to linear subsp...
In recommendation systems, items are likely to be exposed to various use...
Class-incremental learning (CIL) has been widely studied under the setti...
Most of the existing Out-Of-Distribution (OOD) detection algorithms depe...
We present MMOCR-an open-source toolbox which provides a comprehensive
p...
Traditionally, distillation has been used to train a student model to em...
A learning curve models a classifier's test error as a function of the n...
In this paper, we build an outfit evaluation system which provides feedb...
We introduce DeepInversion, a new method for synthesizing images from th...
Solving goal-oriented tasks is an important but challenging problem in
r...
The estimation of advantage is crucial for a number of reinforcement lea...
We introduce a novel domain adaptation formulation from synthetic datase...
Counter to the intuition that unfamiliarity should lead to lack of
confi...
In recent years, more and more machine learning algorithms have been app...
Inferring the location, shape, and class of each object in a single imag...
Specialized classifiers, namely those dedicated to a subset of classes, ...
A number of studies have shown that increasing the depth or width of
con...
When building a unified vision system or gradually adding new capabiliti...