alinlab/Confident_classifier alinlab/Confident_classifier

  • Stars
    star
    178
  • Rank 214,989 (Top 5 %)
  • Language
    Python
  • License
    MIT License
  • Created almost 7 years ago
  • Updated over 4 years ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
alinlab/Confident_classifier
github

alinlab

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Training Confidence-Calibrated Classifier for Detecting Out-of-Distribution Samples / ICLR 2018

Training Confidence-Calibrated Classifier for Detecting Out-of-Distribution Samples

This project is for the paper "Training Confidence-Calibrated Classifier for Detecting Out-of-Distribution Samples". Some codes are from odin-pytorch.

Preliminaries

It is tested under Ubuntu Linux 16.04.1 and Python 2.7 environment, and requries Pytorch package to be installed:

  • Pytorch: Only GPU version is available.

Downloading Out-of-Distribtion Datasets

We use download links of two out-of-distributin datasets from odin-pytorch:

Training scripts

Test scripts

  • test.sh --dataset --out_dataset --pre_trained_net
    --dataset = name of in-distribution (svhn or cifar10)
    --out_dataset = name of out-of-distribution (svhn, cifar10, lsun or imagenet)
    --pre_trained_net = path to pre_trained_net

More Repositories

1

CSI

CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances (NeurIPS 2020)
Python
273
star
2

L2T-ww

Learning What and Where to Transfer (ICML 2019)
Python
251
star
3

cs-kd

Regularizing Class-wise Predictions via Self-knowledge Distillation (CVPR 2020)
Python
107
star
4

M2m

Code for the paper "M2m: Imbalanced Classification via Major-to-minor Translation" (CVPR 2020)
Python
92
star
5

LfF

Learning from Failure: Training Debiased Classifier from Biased Classifier (NeurIPS 2020)
Python
89
star
6

ifseg

IFSeg: Image-free Semantic Segmentation via Vision-Language Model (CVPR 2023)
Python
80
star
7

SelfPatch

Python
57
star
8

consistency-adversarial

Consistency Regularization for Adversarial Robustness (AAAI 2022)
Python
52
star
9

PsCo

Unsupervised Meta-Learning via Few-shot Pseudo-supervised Contrastive Learning (ICLR 2023)
Python
52
star
10

MASKER

MASKER: Masked Keyword Regularization for Reliable Text Classification (AAAI 2021)
Python
51
star
11

object-aware-contrastive

Object-aware Contrastive Learning for Debiased Scene Representation (NeurIPS 2021)
Python
45
star
12

s-clip

S-CLIP: Semi-supervised Vision-Language Pre-training using Few Specialist Captions
Python
43
star
13

lookahead_pruning

Lookahead: A Far-sighted Alternative of Magnitude-based Pruning (ICLR 2020)
Python
33
star
14

temporal-selfsupervision

Python
31
star
15

BAR

The repository for the official Biased Action Recognition (BAR) dataset for the paper Learning from Failure: Training Debiased Classifier from Biased Classifier (NeurIPS 2020) by Junhyun Nam et al.
30
star
16

HOMER

Official implementation of Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs (ICLR 2024).
Python
27
star
17

oreo

Python
23
star
18

b2t

Bias-to-Text: Debiasing Unknown Visual Biases through Language Interpretation
Python
23
star
19

OpenCoS

Python
15
star
20

MetaMAE

Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encoder (NeurIPS 2023)
Python
10
star
21

SURF

Python
8
star
22

lime-cam-pytorch

Pytorch implemenation of LIME-CAM
Python
7
star
23

OAMixer

OAMixer: Object-aware Mixing Layer for Vision Transformers (CVPRW 2022)
Python
6
star
24

smoothing-catrs

Code for the paper "Confidence-aware Training of Smoothed Classifiers for Certified Robustness" (AAAI 2023)
Python
6
star
25

ml-papers-classification

Python
1
star