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 …