Code repo for "Towards Interpretable Deep Networks for Monocular Depth Estimation" paper.

Zunzhi You

Last update: Aug 12, 2022

Related tags

Deep Learning InterpretableMDE

Overview

InterpretableMDE

A PyTorch implementation for "Towards Interpretable Deep Networks for Monocular Depth Estimation" paper.

arXiv link: https://arxiv.org/abs/2108.05312

Data and Model

For MFF models, we use the dataset they released here, and you can download their models as the baselines here. For BTS models, they use a different set of NYUv2 training images (24,231 instead of 50,688), and you download it here. We put all of our models here.

Evaluation

In this project we use yacs to manage the configurations. To evaluate the performance of a model, for example, the MFF model with SENet backbone using our assigning method, simply run

python eval.py MODEL_WEIGHTS_FILE [PATH_TO_MODEL/mff_senet_asn]

from the root directory.

To evaluate the depth selectivity, run

python dissect.py MODEL_WEIGHTS_FILE [PATH_TO_MODEL/mff_senet_asn] LAYERS D_MFF ON_TRAINING_DATA True

then get the depth selectivity and the dissection result of each unit. Layers' names are seperated by _.

Training

To train a model from scratch, run

python train.py MODEL_NAME MFF_resnet

We currently provide four options for MODEL_NAME, and the training scheme will automatically be switched to align with the original ones when using BTS models.

Acknowledgement

The model part of our code is adapted from Revisiting_Single_Depth_Estimation and bts. Some snippets are adapted from monodepth2.

Bibtex

@inproceedings{you2021iccv,
 title = {Towards Interpretable Deep Networks for Monocular Depth Estimation},
 author = {Zunzhi You and Yi-Hsuan Tsai and Wei-Chen Chiu and Guanbin Li},
 booktitle = {International Conference on Computer Vision (ICCV)},
 year = {2021}
}

You might also like...

This repo is a PyTorch implementation for Paper "Unsupervised Learning for Cuboid Shape Abstraction via Joint Segmentation from Point Clouds"

Unsupervised Learning for Cuboid Shape Abstraction via Joint Segmentation from Point Clouds This repository is a PyTorch implementation for paper: Uns

42 Dec 9, 2022

Recall Loss for Semantic Segmentation (This repo implements the paper: Recall Loss for Semantic Segmentation)

Recall Loss for Semantic Segmentation (This repo implements the paper: Recall Loss for Semantic Segmentation) Download Synthia dataset The model uses

32 Sep 21, 2022

The official repo of the CVPR 2021 paper Group Collaborative Learning for Co-Salient Object Detection .

GCoNet The official repo of the CVPR 2021 paper Group Collaborative Learning for Co-Salient Object Detection . Trained model Download final_gconet.pth

46 Nov 17, 2022

This repo in the implementation of EMNLP'21 paper "SPARQLing Database Queries from Intermediate Question Decompositions" by Irina Saparina, Anton Osokin

SPARQLing Database Queries from Intermediate Question Decompositions This repo is the implementation of the following paper: SPARQLing Database Querie

20 Dec 19, 2022

Repo for WWW 2022 paper: Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval

BiDR Repo for WWW 2022 paper: Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval. Requirements torch==

11 Oct 20, 2022

Comments

U may update the wrong paper version on arxiv

Is this the camera-ready version of your paper? (https://arxiv.org/abs/2108.05312) I believe most people will feel confused when they see "MFF" on the first page but finding the explanation in section 5. Please update the correct version if that is available, thanks for your time.

opened by lidongyv 0

Code repo for "Towards Interpretable Deep Networks for Monocular Depth Estimation" paper.

Related tags

Overview

InterpretableMDE

Data and Model

Evaluation

Training

Acknowledgement

Bibtex

You might also like...

This repo is a PyTorch implementation for Paper "Unsupervised Learning for Cuboid Shape Abstraction via Joint Segmentation from Point Clouds"

Recall Loss for Semantic Segmentation (This repo implements the paper: Recall Loss for Semantic Segmentation)

The official repo of the CVPR 2021 paper Group Collaborative Learning for Co-Salient Object Detection .

This repo in the implementation of EMNLP'21 paper "SPARQLing Database Queries from Intermediate Question Decompositions" by Irina Saparina, Anton Osokin

Official Repo for ICCV2021 Paper: Learning to Regress Bodies from Images using Differentiable Semantic Rendering

Official repo for BMVC2021 paper ASFormer: Transformer for Action Segmentation

Repo for the paper "DiLBERT: Cheap Embeddings for Disease Related Medical NLP"

Repo for the paper Extrapolating from a Single Image to a Thousand Classes using Distillation

Repo for WWW 2022 paper: Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval

Comments

U may update the wrong paper version on arxiv

Owner

Zunzhi You

This repo contains the code and data used in the paper "Wizard of Search Engine: Access to Information Through Conversations with Search Engines"

Code Repo for the ACL21 paper "Common Sense Beyond English: Evaluating and Improving Multilingual LMs for Commonsense Reasoning"

Code repo for EMNLP21 paper "Zero-Shot Information Extraction as a Unified Text-to-Triple Translation"

This repo is the code release of EMNLP 2021 conference paper "Connect-the-Dots: Bridging Semantics between Words and Definitions via Aligning Word Sense Inventories".

The LaTeX and Python code for generating the paper, experiments' results and visualizations reported in each paper is available (whenever possible) in the paper's directory

Repo for CVPR2021 paper "QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information"

The official repo of the CVPR2021 oral paper: Representative Batch Normalization with Feature Calibration

The repo of the preprinting paper "Labels Are Not Perfect: Inferring Spatial Uncertainty in Object Detection"

This Repo is the official CUDA implementation of ICCV 2019 Oral paper for CARAFE: Content-Aware ReAssembly of FEatures

This is the repo for the paper `SumGNN: Multi-typed Drug Interaction Prediction via Efficient Knowledge Graph Summarization'. (published in Bioinformatics'21)