Visual Memorability for Robotic Interestingness via Unsupervised Online Learning (ECCV 2020 Oral and TRO)

Last update: Sep 08, 2022

Overview

Visual Interestingness

Refer to the project description for more details.
This code based on the following paper.

Chen Wang, Yuheng Qiu, Wenshan Wang, Yafei Hu, Seungchan Kim and Sebastian Scherer, Unsupervised Online Learning for Robotic Interestingness with Visual Memory, IEEE Transactions on Robotics (T-RO), 2021.
It is an extended version of the conference paper:

Chen Wang, Wenshan Wang, Yuheng Qiu, Yafei Hu, and Sebastian Scherer, Visual Memorability for Robotic Interestingness via Unsupervised Online Learning, European Conference on Computer Vision (ECCV), 2020.
If you want the original version, go to the ECCV Branch instead.
We also provide ROS wrapper for this project, you may go to interestingness_ros.

Install Dependencies

This version is tested in PyTorch 1.7

  pip3 install -r requirements.txt

Long-term Learning

You may skip this step, if you download the pre-trained vgg16.pt into folder "saves".

Download coco dataset into folder [data-root]:

bash download_coco.sh [data-root] # replace [data-root] by your desired location

The dataset will be look like:

data-root
├──coco
   ├── annotations
   │   ├── annotations_trainval2017
   │   └── image_info_test2017
   └── images
       ├── test2017
       ├── train2017
       └── val2017

Run

python3 longterm.py --data-root [data-root] --model-save saves/vgg16.pt

# This requires a long time for training on single GPU.
# Create a folder "saves" manually and a model named "ae.pt" will be saved.

Short-term Learning

Dowload the SubT front camera data (SubTF) and put into folder "data-root", so that it looks like:

data-root
├──SubTF
   ├── 0817-ugv0-tunnel0
   ├── 0817-ugv1-tunnel0
   ├── 0818-ugv0-tunnel1
   ├── 0818-ugv1-tunnel1
   ├── 0820-ugv0-tunnel1
   ├── 0821-ugv0-tunnel0
   ├── 0821-ugv1-tunnel0
   ├── ground-truth
   └── train

Run

python3 shortterm.py --data-root [data-root] --model-save saves/vgg16.pt --dataset SubTF --memory-size 100 --save-flag n100usage

# This will read the previous model "ae.pt".
# A new model "ae.pt.SubTF.n1000.mse" will be generated.

You may skip this step, if you download the pre-trained vgg16.pt.SubTF.n100usage.mse into folder "saves".

On-line Learning

Run

  python3 online.py --data-root [data-root] --model-save saves/vgg16.pt.SubTF.n100usage.mse --dataset SubTF --test-data 0 --save-flag n100usage

  # --test-data The sequence ID in the dataset SubTF, [0-6] is avaiable
  # This will read the trained model "vgg16.pt.SubTF.n100usage.mse" from short-term learning.

Alternatively, you may test all sequences by running
```
  bash test.sh
```
This will generate results files in folder "results".
You may skip this step, if you download our generated results.

Evaluation

We follow the SubT tutorial for evaluation, simply run

python performance.py --data-root [data-root] --save-flag n100usage --category normal --delta 1 2 3
# mean accuracy: [0.64455275 0.8368784  0.92165116 0.95906876]

python performance.py --data-root [data-root] --save-flag n100usage --category difficult --delta 1 2 4
# mean accuracy: [0.42088688 0.57836163 0.67878168 0.75491805]

This will generate performance figures and create data curves for two categories in folder "performance".

Citation

      @inproceedings{wang2020visual,
        title={Visual memorability for robotic interestingness via unsupervised online learning},
        author={Wang, Chen and Wang, Wenshan and Qiu, Yuheng and Hu, Yafei and Scherer, Sebastian},
        booktitle={European Conference on Computer Vision (ECCV)},
        year={2020},
        organization={Springer}
      }
      
      @article{wang2021unsupervised,
        title={Unsupervised Online Learning for Robotic Interestingness with Visual Memory},
        author={Wang, Chen and  Qiu, Yuheng and Wang, Wenshan and Hu, Yafei anad Kim, Seungchan and Scherer, Sebastian},
        journal={IEEE Transactions on Robotics (T-RO)},
        year={2021},
        publisher={IEEE}
      }

Download conferencec version paper.
Download journal version paper.

You may watch the following video to catch the idea of this work.

Code for the paper "Improving Vision-and-Language Navigation with Image-Text Pairs from the Web" (ECCV 2020)

Improving Vision-and-Language Navigation with Image-Text Pairs from the Web Arjun Majumdar, Ayush Shrivastava, Stefan Lee, Peter Anderson, Devi Parikh

44 Dec 14, 2022

Code for ECCV 2020 paper "Contacts and Human Dynamics from Monocular Video".

Contact and Human Dynamics from Monocular Video This is the official implementation for the ECCV 2020 spotlight paper by Davis Rempe, Leonidas J. Guib

207 Jan 5, 2023

Repository for Traffic Accident Benchmark for Causality Recognition (ECCV 2020)

Causality In Traffic Accident (Under Construction) Repository for Traffic Accident Benchmark for Causality Recognition (ECCV 2020) Overview Data Prepa

21 Nov 20, 2022

Code for our paper at ECCV 2020: Post-Training Piecewise Linear Quantization for Deep Neural Networks

PWLQ Updates 2020/07/16 - We are working on getting permission from our institution to release our source code. We will release it once we are granted

54 Dec 15, 2022

dataset for ECCV 2020 "Motion Capture from Internet Videos"

Motion Capture from Internet Videos Motion Capture from Internet Videos Junting Dong*, Qing Shuai*, Yuanqing Zhang, Xian Liu, Xiaowei Zhou, Hujun Bao

98 Dec 7, 2022

Code for the paper: Adversarial Training Against Location-Optimized Adversarial Patches. ECCV-W 2020.

Adversarial Training Against Location-Optimized Adversarial Patches arXiv | Paper | Code | Video | Slides Code for the paper: Sukrut Rao, David Stutz,

32 Dec 13, 2022

SNE-RoadSeg in PyTorch, ECCV 2020

SNE-RoadSeg Introduction This is the official PyTorch implementation of SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentati

242 Dec 20, 2022

[ECCV 2020] Gradient-Induced Co-Saliency Detection

Gradient-Induced Co-Saliency Detection Zhao Zhang*, Wenda Jin*, Jun Xu, Ming-Ming Cheng ⭐ Project Home » The official repo of the ECCV 2020 paper Grad

35 Nov 25, 2022

Code for Towards Streaming Perception (ECCV 2020) :car:

sAP — Code for Towards Streaming Perception ECCV Best Paper Honorable Mention Award Feb 2021: Announcing the Streaming Perception Challenge (CVPR 2021

85 Dec 22, 2022

Comments

Variable

https://github.com/wang-chen/interestingness/blob/6994d50bd47d14b617f34f5c36c1beaba03acfdc/test_interest.py#L94

I think using Variable() will just return a tensor object in the new pytorch version.

opened by haleqiu 2

Visual Memorability for Robotic Interestingness via Unsupervised Online Learning (ECCV 2020 Oral and TRO)

Related tags

Overview

Visual Interestingness

Install Dependencies

Long-term Learning

Short-term Learning

On-line Learning

Evaluation

Citation

You might also like...

Code for the paper "Improving Vision-and-Language Navigation with Image-Text Pairs from the Web" (ECCV 2020)

Code for ECCV 2020 paper "Contacts and Human Dynamics from Monocular Video".

Repository for Traffic Accident Benchmark for Causality Recognition (ECCV 2020)

Code for our paper at ECCV 2020: Post-Training Piecewise Linear Quantization for Deep Neural Networks

dataset for ECCV 2020 "Motion Capture from Internet Videos"

Code for the paper: Adversarial Training Against Location-Optimized Adversarial Patches. ECCV-W 2020.

SNE-RoadSeg in PyTorch, ECCV 2020

[ECCV 2020] Gradient-Induced Co-Saliency Detection

Code for Towards Streaming Perception (ECCV 2020) :car:

Comments

Variable

Releases(v2.0)

v2.0(Apr 12, 2021)

v1.0(Jun 19, 2020)

Owner

Chen Wang

This is the official implementation of the paper "Object Propagation via Inter-Frame Attentions for Temporally Stable Video Instance Segmentation".

Empowering journalists and whistleblowers

We simulate traveling back in time with a modern camera to rephotograph famous historical subjects.

Lightweight tool to perform MITM attack on local network

Improving Non-autoregressive Generation with Mixup Training

Official PyTorch implementation of the paper "Graph-based Generative Face Anonymisation with Pose Preservation" in ICIAP 2021

An interactive DNN Model deployed on web that predicts the chance of heart failure for a patient with an accuracy of 98%

Official implementation of the PICASO: Permutation-Invariant Cascaded Attentional Set Operator

Understanding and Overcoming the Challenges of Efficient Transformer Quantization

Implementation of several Bayesian multi-target tracking algorithms, including Poisson multi-Bernoulli mixture filters for sets of targets and sets of trajectories. The repository also includes the GOSPA metric and a metric for sets of trajectories to evaluate performance.

HEAM: High-Efficiency Approximate Multiplier Optimization for Deep Neural Networks

Code for paper entitled "Improving Novelty Detection using the Reconstructions of Nearest Neighbours"

A denoising diffusion probabilistic model synthesises galaxies that are qualitatively and physically indistinguishable from the real thing.

RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition

BitPack is a practical tool to efficiently save ultra-low precision/mixed-precision quantized models.

Repository of our paper 'Refer-it-in-RGBD' in CVPR 2021

A collection of implementations of deep domain adaptation algorithms

🔮 Execution time predictions for deep neural network training iterations across different GPUs.

KITTI-360 Annotation Tool is a framework that developed based on python(cherrypy + jinja2 + sqlite3) as the server end and javascript + WebGL as the front end.

Source code for CVPR2022 paper "Abandoning the Bayer-Filter to See in the Dark"