
-
Cooperating RPN's Improve Few-Shot Object Detection
Learning to detect an object in an image from very few training examples...
read it
-
Few-Shot Learning with Intra-Class Knowledge Transfer
We consider the few-shot classification task with an unbalanced dataset,...
read it
-
Alpha Net: Adaptation with Composition in Classifier Space
Deep learning classification models typically train poorly on classes wi...
read it
-
Bowtie Networks: Generative Modeling for Joint Few-Shot Recognition and Novel-View Synthesis
Generative modeling has recently shown great promise in computer vision,...
read it
-
Towards Streaming Image Understanding
Embodied perception refers to the ability of an autonomous agent to perc...
read it
-
Learning Generalizable Representations via Diverse Supervision
The problem of rare category recognition has received a lot of attention...
read it
-
Growing a Brain: Fine-Tuning by Increasing Model Capacity
CNNs have made an undeniable impact on computer vision through the abili...
read it
-
Image Deformation Meta-Networks for One-Shot Learning
Humans can robustly learn novel visual concepts even when images undergo...
read it
-
Learning Compositional Representations for Few-Shot Recognition
One of the key limitations of modern deep learning based approaches lies...
read it
-
Low-Shot Learning from Imaginary Data
Humans can quickly learn new visual concepts, perhaps because they can e...
read it