Transformer Assisted Convolutional Network for Cell Instance Segmentation

by   Deepanshu Pandey, et al.

Region proposal based methods like R-CNN and Faster R-CNN models have proven to be extremely successful in object detection and segmentation tasks. Recently, Transformers have also gained popularity in the domain of Computer Vision, and are being utilised to improve the performance of conventional models. In this paper, we present a relatively new transformer based approach to enhance the performance of the conventional convolutional feature extractor in the existing region proposal based methods. Our approach merges the convolutional feature maps with transformer-based token embeddings by applying a projection operation similar to self-attention in transformers. The results of our experiments show that transformer assisted feature extractor achieves a significant improvement in mIoU (mean Intersection over Union) scores compared to vanilla convolutional backbone.


Bottleneck Transformers for Visual Recognition

We present BoTNet, a conceptually simple yet powerful backbone architect...

2D Object Detection with Transformers: A Review

Astounding performance of Transformers in natural language processing (N...

Miti-DETR: Object Detection based on Transformers with Mitigatory Self-Attention Convergence

Object Detection with Transformers (DETR) and related works reach or eve...

Less is More: Pay Less Attention in Vision Transformers

Transformers have become one of the dominant architectures in deep learn...

nnFormer: Interleaved Transformer for Volumetric Segmentation

Transformers, the default model of choices in natural language processin...

Container: Context Aggregation Network

Convolutional neural networks (CNNs) are ubiquitous in computer vision, ...

ViT-BEVSeg: A Hierarchical Transformer Network for Monocular Birds-Eye-View Segmentation

Generating a detailed near-field perceptual model of the environment is ...

Please sign up or login with your details

Forgot password? Click here to reset