4 citations · 4 across the 2 of their papers we have counts for
4 papers
Towards Rotation Invariance in Object Detection
Agastya Kalra, Guy Stoppi, Bradley Brown +2
Rotation augmentations generally improve a model's invariance/equivariance to rotation - except in object detection. In object detection the shape is not known, therefore rotation…
MatrixNets: A New Scale and Aspect Ratio Aware Architecture for Object Detection
Abdullah Rashwan, Rishav Agarwal, Agastya Kalra +1
We present MatrixNets (xNets), a new deep architecture for object detection. xNets map objects with similar sizes and aspect ratios into many specialized layers, allowing xNets to…
Matrix Nets: A New Deep Architecture for Object Detection
Abdullah Rashwan, Agastya Kalra, Pascal Poupart
We present Matrix Nets (xNets), a new deep architecture for object detection. xNets map objects with different sizes and aspect ratios into layers where the sizes and the aspect ra…
Photofeeler-D3: A Neural Network with Voter Modeling for Dating Photo Impression Prediction
Agastya Kalra, Ben Peterson
In just a few years, online dating has become the dominant way that young people meet to date, making the deceptively error-prone task of picking good dating profile photos vital t…