Existing image classification datasets used in computer vision tend to have a uniform
distribution of images across object categories. In contrast, the natural world is heavily …

Low-shot visual learning--the ability to recognize novel object categories from very few
examples--is a hallmark of human visual intelligence. Existing machine learning approaches …

Low-light is an inescapable element of our daily surroundings that greatly affects the
efficiency of our vision. Research works on low-light imagery have seen a steady growth …

Humans can quickly learn new visual concepts, perhaps because they can easily visualize
or imagine what novel objects look like from different views. Incorporating this ability to …

This paper presents a novel image dataset with high intrinsic ambiguity and a longtailed
distribution built from the database of Pl@ ntNet citizen observatory. It consists of 306,146 …

In recent years, large image data sets such as" ImageNet"," TinyImages" or ever-growing
social networks like" Flickr" have emerged, posing new challenges to image classification …

The number of digital images is growing extremely rapidly, and so is the need for their
classification. But, as more images of pre-defined categories become available, they also …

We are interested in large-scale image classification and especially in the setting where
images corresponding to new or existing classes are continuously added to the training set …

We study large-scale image classification methods that can incorporate new classes and
training images continuously over time at negligible cost. To this end, we consider two …

Real world data often have a long-tailed and open-ended distribution. A practical
recognition system must classify among majority and minority classes, generalize from a few …