A unified framework to jointly model images, text, and human attention traces.

Last update: Oct 24, 2022

Related tags

Overview

connect-caption-and-trace

This repository contains the reference code for our paper Connecting What to Say With Where to Look by Modeling Human Attention Traces (CVPR2021).

Requirements

Python 3
PyTorch 1.5+ (along with torchvision)
coco-caption (Remember to follow initialization steps in coco-caption/README.md)

Prepare data

Our experiments cover all four datasets included in Localized Narratives: COCO2017, Flickr30k, Open Images and ADE20k. For each dataset, we need four things: (1) json file containing image info and word tokens. (DATASET_LN.json) (2) h5 file containing caption labels (DATASET_LN_label.h5) (3) The trace labels extracted from Localized Narratives (DATASET_LN_trace_box/) (4) json file for coco-caption evaluation (captions_DATASET_LN_test.json) (5) Image features (with bounding boxes) extracted by a Mask-RCNN pretrained on Visual Genome.

You can download (1--4) from here: (make a folder named data and put (1--3) in it, and put (4) under coco-caption/annotaions/)

To get (5), you can use Detectron2. First, install Detectron2, then follow Prepare COCO-style annotations for Visual Genome (We use the pre-trained Resnet101-C4 model provided there). After that you can utilize tools/extract_feats.py in Detectron2 to extract features. Finally, run scripts/prepare_feats_boxes_from_npz.py in this repo to prepare features and bounding boxes in seperate folders for training.

For COCO dataest you can also directly use the features provided by Peter Anderson here. The performance is almost the same (with around 0.2% difference.)

Training

The dataset can be chosen from the four datasets. The --task can be chosen from trace, caption, c_joint_t and pred_both. The --eval_task can be chosen from trace, caption, and pred_both.

COCO: joint training of controlled caption generation and trace generation (N=2 layers, evaluated on caption generation)

python tools/train.py --language_eval 0 --id transformer_LN_coco  --caption_model transformer --input_json data/coco_LN.json --input_att_dir Dir_to_image_features_vg --input_box_dir Dir_to_bounding_boxes_vg --input_label_h5 data/coco_LN_label.h5 --batch_size 30 --learning_rate 5e-4 --learning_rate_decay_start 0 --scheduled_sampling_start 100 --learning_rate_decay_every 3  --save_checkpoint_every 1000 --max_epochs 30 --max_length 225 --seq_per_img 1 --use_box 1   --use_trace 1  --input_trace_dir data/coco_LN_trace_box --use_trace_feat 0 --beam_size 1 --val_images_use -1 --num_layers 2 --task c_joint_t --eval_task caption --dataset_choice=coco

Open image: training of generating caption and trace at the same time (N=1 layers, evaluated on predicting both)

python tools/train.py --language_eval 0 --id transformer_LN_openimg  --caption_model transformer --input_json data/openimg_LN.json --input_att_dir Dir_to_image_features_vg --input_box_dir Dir_to_bounding_boxes_vg --input_label_h5 data/openimg_LN_label.h5 --batch_size 30 --learning_rate 5e-4 --learning_rate_decay_start 0 --scheduled_sampling_start 100 --learning_rate_decay_every 3  --save_checkpoint_every 1000 --max_epochs 30 --max_length 225 --seq_per_img 1 --use_box 1   --use_trace 1  --input_trace_dir data/openimg_LN_trace_box --use_trace_feat 0 --beam_size 1 --val_images_use -1 --num_layers 1 --task pred_both --eval_task pred_both --dataset_choice=openimg

Flickr30k: training of controlled caption generation alone (N=1 layer)

python tools/train.py --language_eval 0 --id transformer_LN_flk30k  --caption_model transformer --input_json data/flk30k_LN.json --input_att_dir Dir_to_image_features_vg --input_box_dir Dir_to_bounding_boxes_vg --input_label_h5 data/flk30k_LN_label.h5 --batch_size 30 --learning_rate 5e-4 --learning_rate_decay_start 0 --scheduled_sampling_start 100 --learning_rate_decay_every 3  --save_checkpoint_every 1000 --max_epochs 30 --max_length 225 --seq_per_img 1 --use_box 1   --use_trace 1  --input_trace_dir data/flk30k_LN_trace_box --use_trace_feat 0 --beam_size 1 --val_images_use -1 --num_layers 1 --task caption --eval_task caption --dataset_choice=flk30k

ADE20k: training of controlled trace generation alone (N=1 layer)

python tools/train.py --language_eval 0 --id transformer_LN_ade20k  --caption_model transformer --input_json data/ade20k_LN.json --input_att_dir Dir_to_image_features_vg --input_box_dir Dir_to_bounding_boxes_vg --input_label_h5 data/ade20k_LN_label.h5 --batch_size 30 --learning_rate 5e-4 --learning_rate_decay_start 0 --scheduled_sampling_start 100 --learning_rate_decay_every 3  --save_checkpoint_every 1000 --max_epochs 30 --max_length 225 --seq_per_img 1 --use_box 1   --use_trace 1  --input_trace_dir data/ade20k_LN_trace_box --use_trace_feat 0 --beam_size 1 --val_images_use -1 --num_layers 1 --task trace --eval_task trace --dataset_choice=ade20k

Evaluating

COCO: joint training of controlled caption generation and trace generation (N=2 layers, evaluated on caption generation)

python tools/train.py --language_eval 1 --id transformer_LN_coco  --caption_model transformer --input_json data/coco_LN.json --input_att_dir Dir_to_image_features_vg --input_box_dir Dir_to_bounding_boxes_vg --input_label_h5 data/coco_LN_label.h5 --batch_size 2 --learning_rate 5e-4 --learning_rate_decay_start 0 --scheduled_sampling_start 100 --learning_rate_decay_every 3  --save_checkpoint_every 1000 --max_epochs 30 --max_length 225 --seq_per_img 1 --use_box 1   --use_trace 1  --input_trace_dir data/coco_LN_trace_box --use_trace_feat 0 --beam_size 5 --val_images_use -1 --num_layers 2 --task c_joint_t --eval_task caption --dataset_choice=coco

COCO: joint training of controlled caption generation and trace generation (N=2 layers, evaluated on trace generation)

python tools/train.py --language_eval 1 --id transformer_LN_coco  --caption_model transformer --input_json data/coco_LN.json --input_att_dir Dir_to_image_features_vg --input_box_dir Dir_to_bounding_boxes_vg --input_label_h5 data/coco_LN_label.h5 --batch_size 30 --learning_rate 5e-4 --learning_rate_decay_start 0 --scheduled_sampling_start 100 --learning_rate_decay_every 3  --save_checkpoint_every 1000 --max_epochs 30 --max_length 225 --seq_per_img 1 --use_box 1   --use_trace 1  --input_trace_dir data/coco_LN_trace_box --use_trace_feat 0 --beam_size 1 --val_images_use -1 --num_layers 2 --task c_joint_t --eval_task trace --dataset_choice=coco

Open image: training of generating caption and trace at the same time (N=1 layers, evaluated on predicting both)

python tools/train.py --language_eval 1 --id transformer_LN_openimg  --caption_model transformer --input_json data/openimg_LN.json --input_att_dir Dir_to_image_features_vg --input_box_dir Dir_to_bounding_boxes_vg --input_label_h5 data/openimg_LN_label.h5 --batch_size 2 --learning_rate 5e-4 --learning_rate_decay_start 0 --scheduled_sampling_start 100 --learning_rate_decay_every 3  --save_checkpoint_every 1000 --max_epochs 30 --max_length 225 --seq_per_img 1 --use_box 1   --use_trace 1  --input_trace_dir data/openimg_LN_trace_box --use_trace_feat 0 --beam_size 5 --val_images_use -1 --num_layers 1 --task pred_both --eval_task pred_both --dataset_choice=openimg

Acknowledgements

Some components of this repo were built from Ruotian Luo's ImageCaptioning.pytorch.

A unified framework to jointly model images, text, and human attention traces.

Related tags

Overview

connect-caption-and-trace

Requirements

Prepare data

Training

COCO: joint training of controlled caption generation and trace generation (N=2 layers, evaluated on caption generation)

Open image: training of generating caption and trace at the same time (N=1 layers, evaluated on predicting both)

Flickr30k: training of controlled caption generation alone (N=1 layer)

ADE20k: training of controlled trace generation alone (N=1 layer)

Evaluating

COCO: joint training of controlled caption generation and trace generation (N=2 layers, evaluated on caption generation)

COCO: joint training of controlled caption generation and trace generation (N=2 layers, evaluated on trace generation)

Open image: training of generating caption and trace at the same time (N=1 layers, evaluated on predicting both)

Acknowledgements

Owner

Meta Research

Trained on Simulated Data, Tested in the Real World

Multi-tool reverse engineering collaboration solution.

Episodic Transformer (E.T.) is a novel attention-based architecture for vision-and-language navigation. E.T. is based on a multimodal transformer that encodes language inputs and the full episode history of visual observations and actions.

Simple data balancing baselines for worst-group-accuracy benchmarks.

Language Models Can See: Plugging Visual Controls in Text Generation

A Python library for Deep Probabilistic Modeling

An NLP library with Awesome pre-trained Transformer models and easy-to-use interface, supporting wide-range of NLP tasks from research to industrial applications.

Deep Anomaly Detection with Outlier Exposure (ICLR 2019)

Uni-Fold: Training your own deep protein-folding models

Implementation for On Provable Benefits of Depth in Training Graph Convolutional Networks

The implementation of "Bootstrapping Semantic Segmentation with Regional Contrast".

Segment axon and myelin from microscopy data using deep learning

CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiability

Painting app using Python machine learning and vision technology.

Synthetic LiDAR sequential point cloud dataset with point-wise annotations

Code to reproduce experiments in the paper "Explainability Requires Interactivity".

An open-source Deep Learning Engine for Healthcare that aims to treat & prevent major diseases

A customisable game where you have to quickly click on black tiles in order of appearance while avoiding clicking on white squares.

Object detection on multiple datasets with an automatically learned unified label space.

Gesture Volume Control v.2