Automatic caption evaluation metric based on typicality analysis.

Related tags

Deep LearningSMURF
Overview

SeMantic and linguistic UndeRstanding Fusion (SMURF)

made-with-python License: MIT

Automatic caption evaluation metric described in the paper "SMURF: SeMantic and linguistic UndeRstanding Fusion for Caption Evaluation via Typicality Analysis" (ACL 2021).

arXiv: https://arxiv.org/abs/2106.01444

ACL Anthology: https://aclanthology.org/2021.acl-long.175/

Overview

SMURF is an automatic caption evaluation metric that combines a novel semantic evaluation algorithm (SPARCS) and novel fluency evaluation algorithms (SPURTS and MIMA) for both caption-level and system-level analysis. These evaluations were developed to be generalizable and as a result demonstrate a high correlation with human judgment across many relevant datasets. See paper for more details.

Requirements

You can run requirements/install.sh to quickly install all the requirements in an Anaconda environment. The requirements are:

  • python 3
  • torch>=1.0.0
  • numpy
  • nltk>=3.5.0
  • pandas>=1.0.1
  • matplotlib
  • transformers>=3.0.0
  • shapely
  • sklearn
  • sentencepiece

Usage

./smurf_example.py provides working examples of the following functions:

Caption-Level Scoring

Returns a dictionary with scores for semantic similarity between reference captions and candidate captions (SPARCS), style/diction quality of candidate text (SPURTS), grammar outlier penalty of candidate text (MIMA), and the fusion of these scores (SMURF). Input sentences should be preprocessed before being fed into the smurf_eval_captions object as shown in the example. Evaluations with SPARCS require a list of reference sentences while evaluations with SPURTS and MIMA do not use reference sentences.

System-Level Analysis

After reading in and standardizing caption-level scores, generates a plot that can be used to give an overall evaluation of captioner performances along with relevant system-level scores (intersection with reference captioner and total grammar outlier penalties) for each captioner. An example of such a plot is shown below:

The number of captioners you are comparing should be specified when instantiating a smurf_system_analysis object. In order to generate the plot correctly, the captions fed into the caption-level scoring for each candidate captioner (C1, C2,...) should be organized in the following format with the C1 captioner as the ground truth:

[C1 image 1 output, C2 image 1 output,..., C1 image 2 output, C2 image 2 output,...].

Author/Maintainer:

Joshua Feinglass (https://scholar.google.com/citations?user=V2h3z7oAAAAJ&hl=en)

If you find this repo useful, please cite:

@inproceedings{feinglass2021smurf,
  title={SMURF: SeMantic and linguistic UndeRstanding Fusion for Caption Evaluation via Typicality Analysis},
  author={Joshua Feinglass and Yezhou Yang},
  booktitle={Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},
  year={2021},
  url={https://aclanthology.org/2021.acl-long.175/}
}
Owner
Joshua Feinglass
Joshua Feinglass
Transfer style api - An API to use with Tranfer Style App, where you can use two image and transfer the style

Transfer Style API It's an API to use with Tranfer Style App, where you can use

Brian Alejandro 1 Feb 13, 2022
Official repository of PanoAVQA: Grounded Audio-Visual Question Answering in 360° Videos (ICCV 2021)

Pano-AVQA Official repository of PanoAVQA: Grounded Audio-Visual Question Answering in 360° Videos (ICCV 2021) [Paper] [Poster] [Video] Getting Starte

Heeseung Yun 9 Dec 23, 2022
QKeras: a quantization deep learning library for Tensorflow Keras

QKeras github.com/google/qkeras QKeras 0.8 highlights: Automatic quantization using QKeras; Stochastic behavior (including stochastic rouding) is disa

Google 437 Jan 03, 2023
Weakly Supervised Scene Text Detection using Deep Reinforcement Learning

Weakly Supervised Scene Text Detection using Deep Reinforcement Learning This repository contains the setup for all experiments performed in our Paper

Emanuel Metzenthin 3 Dec 16, 2022
SoGCN: Second-Order Graph Convolutional Networks

SoGCN: Second-Order Graph Convolutional Networks This is the authors' implementation of paper "SoGCN: Second-Order Graph Convolutional Networks" in Py

Yuehao 7 Aug 16, 2022
Learning Continuous Signed Distance Functions for Shape Representation

DeepSDF This is an implementation of the CVPR '19 paper "DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation" by Park et a

Meta Research 1.1k Jan 01, 2023
NPBG++: Accelerating Neural Point-Based Graphics

[CVPR 2022] NPBG++: Accelerating Neural Point-Based Graphics Project Page | Paper This repository contains the official Python implementation of the p

Ruslan Rakhimov 57 Dec 03, 2022
Simple ONNX operation generator. Simple Operation Generator for ONNX.

sog4onnx Simple ONNX operation generator. Simple Operation Generator for ONNX. https://github.com/PINTO0309/simple-onnx-processing-tools Key concept V

Katsuya Hyodo 6 May 15, 2022
Autoregressive Models in PyTorch.

Autoregressive This repository contains all the necessary PyTorch code, tailored to my presentation, to train and generate data from WaveNet-like auto

Christoph Heindl 41 Oct 09, 2022
This project deals with the detection of skin lesions within the ISICs dataset using YOLOv3 Object Detection with Darknet.

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. Skin Lesion detection using YOLO This project deal

Lalith Veerabhadrappa Badiger 1 Nov 22, 2021
School of Artificial Intelligence at the Nanjing University (NJU)School of Artificial Intelligence at the Nanjing University (NJU)

F-Principle This is an exercise problem of the digital signal processing (DSP) course at School of Artificial Intelligence at the Nanjing University (

Thyrix 5 Nov 23, 2022
Unofficial implementation of Fast-SCNN: Fast Semantic Segmentation Network

Fast-SCNN: Fast Semantic Segmentation Network Unofficial implementation of the model architecture of Fast-SCNN. Real-time Semantic Segmentation and mo

Philip Popien 69 Aug 11, 2022
Independent and minimal implementations of some reinforcement learning algorithms using PyTorch (including PPO, A3C, A2C, ...).

PyTorch RL Minimal Implementations There are implementations of some reinforcement learning algorithms, whose characteristics are as follow: Less pack

Gemini Light 4 Dec 31, 2022
Face recognition with trained classifiers for detecting objects using OpenCV

Face_Detector Face recognition with trained classifiers for detecting objects using OpenCV Libraries required to be installed using pip Command: cv2 n

Chumui Tripura 0 Oct 31, 2021
A PyTorch implementation of "CoAtNet: Marrying Convolution and Attention for All Data Sizes".

CoAtNet Overview This is a PyTorch implementation of CoAtNet specified in "CoAtNet: Marrying Convolution and Attention for All Data Sizes", arXiv 2021

Justin Wu 268 Jan 07, 2023
Deep learning models for change detection of remote sensing images

Change Detection Models (Remote Sensing) Python library with Neural Networks for Change Detection based on PyTorch. ⚡ ⚡ ⚡ I am trying to build this pr

Kaiyu Li 176 Dec 24, 2022
Code of the lileonardo team for the 2021 Emotion and Theme Recognition in Music task of MediaEval 2021

Emotion and Theme Recognition in Music The repository contains code for the submission of the lileonardo team to the 2021 Emotion and Theme Recognitio

Vincent Bour 8 Aug 02, 2022
MAU: A Motion-Aware Unit for Video Prediction and Beyond, NeurIPS2021

MAU (NeurIPS2021) Zheng Chang, Xinfeng Zhang, Shanshe Wang, Siwei Ma, Yan Ye, Xinguang Xiang, Wen GAo. Official PyTorch Code for "MAU: A Motion-Aware

ZhengChang 20 Nov 25, 2022
Jittor 64*64 implementation of StyleGAN

StyleGanJittor (Tsinghua university computer graphics course) Overview Jittor 64

Song Shengyu 3 Jan 20, 2022