Search Results for author: Ashutosh Agarwal

Found 3 papers, 2 papers with code

Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention

1 code implementation17 Oct 2022 Ashutosh Agarwal, Chetan Arora

Typically, a skip connection module is used to fuse the encoder and decoder features, which comprises of feature map concatenation followed by a convolution operation.

Ranked #16 on Monocular Depth Estimation on KITTI Eigen split (using extra training data)

Depth Prediction Monocular Depth Estimation

Depthformer : Multiscale Vision Transformer For Monocular Depth Estimation With Local Global Information Fusion

1 code implementation10 Jul 2022 Ashutosh Agarwal, Chetan Arora

We also propose a Transbins module that divides the depth range into bins whose center value is estimated adaptively per image.

Ranked #26 on Monocular Depth Estimation on KITTI Eigen split (using extra training data)

Depth Prediction Monocular Depth Estimation +1

Attention Guided Cosine Margin For Overcoming Class-Imbalance in Few-Shot Road Object Detection

no code implementations12 Nov 2021 Ashutosh Agarwal, Anay Majee, Anbumani Subramanian, Chetan Arora

To overcome these pitfalls in metric learning based FSOD techniques, we introduce Attention Guided Cosine Margin (AGCM) that facilitates the creation of tighter and well separated class-specific feature clusters in the classification head of the object detector.

Few-Shot Object Detection Meta-Learning +2

Cannot find the paper you are looking for? You can Submit a new open access paper.