Due to the widespread use of complex machine learning models in real-wor...
Generalized Additive Models (GAMs) have quickly become the leading choic...
A visual counterfactual explanation replaces image regions in a query im...
Model pre-training is a cornerstone of modern visual recognition systems...
Domain generalization involves learning a classifier from a heterogeneou...
We study the problem of learning how to predict attribute-object composi...
Invariant approaches have been remarkably successful in tackling the pro...
Weakly supervised instance segmentation reduces the cost of annotations
...
Object proposal generation is often the first step in many detection mod...
Existing models often leverage co-occurrences between objects and their
...
Despite the increasing visibility of fine-grained recognition in our fie...
Blind or no-reference (NR) perceptual picture quality prediction is a
di...
Pre-training convolutional neural networks with weakly-supervised and
se...
The visual and audio modalities are highly correlated yet they contain
d...
Self-supervised learning aims to learn representations from the data its...
Current fully-supervised video datasets consist of only a few hundred
th...
This paper presents a study of semi-supervised learning with large
convo...
Weakly supervised object detection aims at reducing the amount of superv...
A plethora of recent work has shown that convolutional networks are not
...
State-of-the-art visual perception models for a wide range of tasks rely...
Deep learning involves a difficult non-convex optimization problem with ...
For many applications, an ensemble of base classifiers is an effective
s...
Latency to end-users and regulatory requirements push large companies to...