EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment
This work presents the network architecture EVP (Enhanced Visual Perception). EVP builds on the previous work VPD which paved the way to use the Stable Diffusion network for computer vision tasks. We propose two major enhancements. First, we develop the Inverse Multi-Attentive Feature Refinement (IMAFR) module which enhances feature learning capabilities by aggregating spatial information from higher pyramid levels. Second, we propose a novel image-text alignment module for improved feature extraction of the Stable Diffusion backbone. The resulting architecture is suitable for a wide variety of tasks and we demonstrate its performance in the context of single-image depth estimation with a specialized decoder using classification-based bins and referring segmentation with an off-the-shelf decoder. Comprehensive experiments conducted on established datasets show that EVP achieves state-of-the-art results in single-image depth estimation for indoor (NYU Depth v2, 11.8% RMSE improvement over VPD) and outdoor (KITTI) environments, as well as referring segmentation (RefCOCO, 2.53 IoU improvement over ReLA). The code and pre-trained models are publicly available at https://github.com/Lavreniuk/EVP.
PDF AbstractCode
Results from the Paper
Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
---|---|---|---|---|---|---|
Monocular Depth Estimation | KITTI Eigen split | EVP | absolute relative error | 0.048 | # 9 | |
RMSE | 2.015 | # 13 | ||||
Sq Rel | 0.136 | # 19 | ||||
RMSE log | 0.073 | # 10 | ||||
Delta < 1.25 | 0.980 | # 8 | ||||
Delta < 1.25^2 | 0.998 | # 1 | ||||
Delta < 1.25^3 | 1.000 | # 1 | ||||
Monocular Depth Estimation | NYU-Depth V2 | EVP | RMSE | 0.224 | # 6 | |
absolute relative error | 0.061 | # 6 | ||||
Delta < 1.25 | 0.976 | # 6 | ||||
Delta < 1.25^2 | 0.997 | # 3 | ||||
Delta < 1.25^3 | 0.999 | # 4 | ||||
log 10 | 0.027 | # 6 | ||||
Depth Estimation | NYU-Depth V2 | EVP | RMS | 0.224 | # 1 | |
Referring Expression Segmentation | RefCOCO testA | EVP | Overall IoU | 78.75 | # 1 | |
Referring Expression Segmentation | RefCOCO testB | EVP | Overall IoU | 72.94 | # 1 | |
Referring Expression Segmentation | RefCoCo val | EVP | Overall IoU | 76.35 | # 2 |