# simCrossTrans: A Simple Cross-Modality Transfer Learning for Object Detection with ConvNets or Vision Transformers

arXiv: https://arxiv.org/abs/2203.10456 · HTML: https://mlsanity.com/paper/2203.10456/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 50 references that are in the map.
- First posted on arXiv 20 Mar 2022.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Frustum PointNets for 3D Object Detection from RGB-D Data](https://mlsanity.com/paper/1711.08488/) (2017)
- [Intriguing Properties of Vision Transformers](https://mlsanity.com/paper/2105.10497/) (2021)
- [On the Relationship between Self-Attention and Convolutional Layers](https://mlsanity.com/paper/1911.03584/) (2019)
- [Learning Rich Features from RGB-D Images for Object Detection and Segmentation](https://mlsanity.com/paper/1407.5736/) (2014)
- [Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images](https://mlsanity.com/paper/1511.02300/) (2015)
- [Visualizing and Understanding the Effectiveness of BERT](https://mlsanity.com/paper/1908.05620/) (2019)
- [Pruning Convolutional Neural Networks for Resource Efficient Inference](https://mlsanity.com/paper/1611.06440/) (2016)
- [Frustum VoxNet for 3D object detection from RGB-D or Depth images](https://mlsanity.com/paper/1910.05483/) (2019)
- [A survey of Object Classification and Detection based on 2D/3D data](https://mlsanity.com/paper/1905.12683/) (2019)

## Built on by (most cited first, 2 of 2)

- [Depth-based 6DoF Object Pose Estimation using Swin Transformer](https://mlsanity.com/paper/2303.02133/) (2023)
- [Cross-domain and Cross-dimension Learning for Image-to-Graph Transformers](https://mlsanity.com/paper/2403.06601/) (2024)

## Abstract (arXiv)

Transfer learning is widely used in computer vision (CV), natural language processing (NLP) and achieves great success. Most transfer learning systems are based on the same modality (e.g. RGB image in CV and text in NLP). However, the cross-modality transfer learning (CMTL) systems are scarce. In this work, we study CMTL from 2D to 3D sensor to explore the upper bound performance of 3D sensor only systems, which play critical roles in robotic navigation and perform well in low light scenarios. While most CMTL pipelines from 2D to 3D vision are complicated and based on Convolutional Neural Networks (ConvNets), ours is easy to implement, expand and based on both ConvNets and Vision transformers(ViTs): 1) By converting point clouds to pseudo-images, we can use an almost identical network from pre-trained models based on 2D images. This makes our system easy to implement and expand. 2) Recently ViTs have been showing good performance and robustness to occlusions, one of the key reasons for poor performance of 3D vision systems. We explored both ViT and ConvNet with similar model sizes to investigate the performance difference. We name our approach simCrossTrans: simple cross-modality transfer learning with ConvNets or ViTs. Experiments on SUN RGB-D dataset show: with simCrossTrans we achieve 13.2% and 16.1% absolute performance gain based on ConvNets and ViTs separately. We also observed the ViTs based performs 9.7% better than the ConvNets one, showing the power of simCrossTrans with ViT. simCrossTrans with ViTs surpasses the previous state-of-the-art (SOTA) by a large margin of +15.4% mAP50. Compared with the previous 2D detection SOTA based RGB images, our depth image only system only has a 1% gap. The code, training/inference logs and models are publicly available at https://github.com/liketheflower/simCrossTrans