# Transformer Assisted Convolutional Network for Cell Instance Segmentation

Source: [Transformer Assisted Convolutional Network for Cell Instance Segmentation](<https://www.sota2.com/research/paper/68fa6aee1e209131cea2b213>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:49.999Z

Authors: Deepanshu Pandey, Pradyumna Gupta, Sumit Bhattacharya, Aman Sinha, Rohit Agarwal

Published: 2021-10-05T18:18:31.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2110.02270>)

[PDF](<https://arxiv.org/pdf/2110.02270.pdf>)
