[NeurIPS 2021] Introspective Distillation for Robust Question Answering

Related tags

Deep Learning introd
Overview

Introspective Distillation (IntroD)

This repository is the Pytorch implementation of our paper "Introspective Distillation for Robust Question Answering" in NeurIPS 2021. The code will be released before the conference.

You might also like...
covid question answering datasets and fine tuned models

Covid-QA Fine tuned models for question answering on Covid-19 data. Hosted Inference This model has been contributed to huggingface.Click here to see

NExT-QA: Next Phase of Question-Answering to Explaining Temporal Actions (CVPR2021)
NExT-QA: Next Phase of Question-Answering to Explaining Temporal Actions (CVPR2021)

NExT-QA We reproduce some SOTA VideoQA methods to provide benchmark results for our NExT-QA dataset accepted to CVPR2021 (with 1 'Strong Accept' and 2

FeTaQA: Free-form Table Question Answering

FeTaQA: Free-form Table Question Answering FeTaQA is a Free-form Table Question Answering dataset with 10K Wikipedia-based {table, question, free-form

improvement of CLIP features over the traditional resnet features on the visual question answering, image captioning, navigation and visual entailment tasks.

CLIP-ViL In our paper "How Much Can CLIP Benefit Vision-and-Language Tasks?", we show the improvement of CLIP features over the traditional resnet fea

Pytorch implementation for the EMNLP 2020 (Findings) paper: Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering

Path-Generator-QA This is a Pytorch implementation for the EMNLP 2020 (Findings) paper: Connecting the Dots: A Knowledgeable Path Generator for Common

This is the official implementation of
This is the official implementation of "One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval".

CORA This is the official implementation of the following paper: Akari Asai, Xinyan Yu, Jungo Kasai and Hannaneh Hajishirzi. One Question Answering Mo

Bilinear attention networks for visual question answering
Bilinear attention networks for visual question answering

Bilinear Attention Networks This repository is the implementation of Bilinear Attention Networks for the visual question answering and Flickr30k Entit

Visual Question Answering in Pytorch
Visual Question Answering in Pytorch

Visual Question Answering in pytorch /!\ New version of pytorch for VQA available here: https://github.com/Cadene/block.bootstrap.pytorch This repo wa

This reporistory contains the test-dev data of the paper "xGQA: Cross-lingual Visual Question Answering".

This reporistory contains the test-dev data of the paper "xGQA: Cross-lingual Visual Question Answering".

Comments
  • about css two teacher

    about css two teacher

    Hello, Yu Lei, I would like to ask whether there should be two teacher models for the CSS part, and then predict the mixing. It seems that I don't see this part of the code in the code. Maybe I didn't notice. Can you tell me what this part of the code is.

    opened by 156aasdfg 2
  • ValueError in Optimizer

    ValueError in Optimizer

    Hello Yulei, thank you for your paper and code, which benefit me a lot. When I tried to run cfvqa, I may have encountered some problems due to my incorrect usage. I hope that you could answer them. After training the teacher model, the student model encountered the following error when loading the Optimizer:

    [I 2022-12-04 22:48:30] ...fvqa/engines/engine.py.87: Loading last checkpoint
    [I 2022-12-04 22:48:30] ...fvqa/engines/engine.py.395: Loading model...
    [I 2022-12-04 22:48:30] ...fvqa/engines/engine.py.401: Loading optimizer...
    [I 2022-12-04 22:48:30] ...qa/cfint1/cfvqa/run.py.120: Traceback (most recent call last):
      File "/mnt/home/lxpvqa/cfint1/cfvqa/run.py", line 113, in main
        run(path_opts=path_opts)
      File "/mnt/home/lxpvqa/cfint1/cfvqa/run.py", line 92, in run
        engine.resume()
      File "/mnt/home/lxpvqa/cfint1/cfvqa/cfvqa/engines/engine.py", line 91, in resume
        map_location=map_location)
      File "/mnt/home/lxpvqa/cfint1/cfvqa/cfvqa/engines/engine.py", line 403, in load
        optimizer.load_state_dict(optimizer_state)
      File "/usr/local/lib/python3.6/dist-packages/block/optimizers/lr_scheduler.py", line 123, in load_state_dict
        self.optimizer.load_state_dict(state['optimizer'])
      File "/usr/local/lib/python3.6/dist-packages/torch/optim/optimizer.py", line 124, in load_state_dict
        raise ValueError("loaded state dict contains a parameter group "
    ValueError: loaded state dict contains a parameter group that doesn't match the size of optimizer's group
    

    The run commands I used are as follows:

    python -m bootstrap.run -o cfvqa/options/vqa2/smrl_cfvqa_sum.yaml
    #mkdir ./logs/vqa2/smrl_cfvqaintrod_sum/
    cp -r ./logs/vqa2/smrl_cfvqa_sum/ ./logs/vqa2/smrl_cfvqaintrod_sum/
    python -m run -o ./cfvqa/options/vqa2/smrl_cfvqaintrod_sum.yaml
    

    The following shows the contents of the optimizer in smrl_cfvqaintrod_sum:

    optimizer:
      import: cfvqa.optimizers.factory
      name: Adam
      lr: 0.0003
      gradual_warmup_steps: [0.5, 2.0, 7.0] #torch.linspace
      gradual_warmup_steps_mm: [0.5, 2.0, 7.0] #torch.linspace
      lr_decay_epochs: [14, 24, 2] #range
      lr_decay_rate: .25
    

    Could you please tell me how to solve this problem? Thanks a lot.

    opened by lvxinpeng1 0
Owner
Yulei Niu
Yulei Niu
Designing a Minimal Retrieve-and-Read System for Open-Domain Question Answering (NAACL 2021)

Designing a Minimal Retrieve-and-Read System for Open-Domain Question Answering Abstract In open-domain question answering (QA), retrieve-and-read mec

Clova AI Research 34 Apr 13, 2022
Official repository with code and data accompanying the NAACL 2021 paper "Hurdles to Progress in Long-form Question Answering" (https://arxiv.org/abs/2103.06332).

Hurdles to Progress in Long-form Question Answering This repository contains the official scripts and datasets accompanying our NAACL 2021 paper, "Hur

Kalpesh Krishna 41 Nov 8, 2022
EMNLP 2021: Single-dataset Experts for Multi-dataset Question-Answering

MADE (Multi-Adapter Dataset Experts) This repository contains the implementation of MADE (Multi-adapter dataset experts), which is described in the pa

Princeton Natural Language Processing 68 Jul 18, 2022
EMNLP 2021: Single-dataset Experts for Multi-dataset Question-Answering

MADE (Multi-Adapter Dataset Experts) This repository contains the implementation of MADE (Multi-adapter dataset experts), which is described in the pa

Princeton Natural Language Processing 39 Oct 5, 2021
Pytorch implementation for our ICCV 2021 paper "TRAR: Routing the Attention Spans in Transformers for Visual Question Answering".

TRAnsformer Routing Networks (TRAR) This is an official implementation for ICCV 2021 paper "TRAR: Routing the Attention Spans in Transformers for Visu

Ren Tianhe 49 Nov 10, 2022
This is the official pytorch implementation for our ICCV 2021 paper "TRAR: Routing the Attention Spans in Transformers for Visual Question Answering" on VQA Task

?? ERASOR (RA-L'21 with ICRA Option) Official page of "ERASOR: Egocentric Ratio of Pseudo Occupancy-based Dynamic Object Removal for Static 3D Point C

Hyungtae Lim 225 Dec 29, 2022
TF2 implementation of knowledge distillation using the "function matching" hypothesis from the paper Knowledge distillation: A good teacher is patient and consistent by Beyer et al.

FunMatch-Distillation TF2 implementation of knowledge distillation using the "function matching" hypothesis from the paper Knowledge distillation: A g

Sayak Paul 67 Dec 20, 2022
QA-GNN: Question Answering using Language Models and Knowledge Graphs

QA-GNN: Question Answering using Language Models and Knowledge Graphs This repo provides the source code & data of our paper: QA-GNN: Reasoning with L

Michihiro Yasunaga 434 Jan 4, 2023
GrailQA: Strongly Generalizable Question Answering

GrailQA is a new large-scale, high-quality KBQA dataset with 64,331 questions annotated with both answers and corresponding logical forms in different syntax (i.e., SPARQL, S-expression, etc.). It can be used to test three levels of generalization in KBQA: i.i.d., compositional, and zero-shot.

OSU DKI Lab 76 Dec 21, 2022
Binary Passage Retriever (BPR) - an efficient passage retriever for open-domain question answering

BPR Binary Passage Retriever (BPR) is an efficient neural retrieval model for open-domain question answering. BPR integrates a learning-to-hash techni

Studio Ousia 147 Dec 7, 2022