Non-Hierarchical Transformers for Pedestrian Segmentation
We propose a methodology to address the challenge of instance segmentation in autonomous systems, specifically targeting accessibility and inclusivity. Our approach utilizes a non-hierarchical Vision Transformer variant, EVA-02, combined with a Cascade Mask R-CNN mask head. Through fine-tuning on the AVA instance segmentation challenge dataset, we achieved a promising mean Average Precision (mAP) of 52.68\% on the test set. Our results demonstrate the efficacy of ViT-based architectures in enhancing vision capabilities and accommodating the unique needs of individuals with disabilities.
PDF Abstract
Datasets
Add Datasets
introduced or used in this paper
Results from the Paper
Submit
results from this paper
to get state-of-the-art GitHub badges and help the
community compare results to other papers.
Methods
Absolute Position Encodings •
Adam •
BPE •
Cascade Mask R-CNN •
Convolution •
Dense Connections •
Dropout •
Label Smoothing •
Layer Normalization •
Linear Layer •
Mask R-CNN •
Multi-Head Attention •
Position-Wise Feed-Forward Layer •
Residual Connection •
RoIAlign •
RPN •
Scaled Dot-Product Attention •
Softmax •
Transformer •
Vision Transformer
