Sahil Singla (@singlasahil14)
github

singlasahil14

Twitter logo Share LinkedIn logo Share Facebook logo Share

Top repositories

1

sortpool2d

A new kind of pooling layer for faster and sharper convergence
Python
76
star
2

salient_imagenet

Code for the ICLR 2022 paper. Salient Imagenet: How to discover spurious features in deep learning?
Jupyter Notebook
36
star
3

style-transfer

style transfer code for generating stylized images using content and style loss from different layers, from different loss networks (vgg-16, vgg-19, inception-v1, inception-v2, inception-v3 trained on imagenet, inception-v3 trained on openimages, inception-v4
Python
36
star
4

barlow

Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction
Jupyter Notebook
35
star
5

orthogonal-convolution

Github repo for my experiments with the orthogonal convolution idea
Python
22
star
6

loss-exps

Experiments with different loss functions for image classification
Python
20
star
7

SOC

Code for the ICML 2021 and ICLR 2022 papers: Skew Orthogonal Convolutions, Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100
Python
18
star
8

CASO

code for the paper https://arxiv.org/abs/1902.00407
Python
13
star
9

CONV-SV

A fast and efficient way to compute a differentiable bound on the singular values of convolution layers
Python
11
star
10

word-language-model

word-language-model imported and modified from pytorch-examples
Python
6
star
11

resnet-exps

Experiments with center loss function for image classification on resnet architecture
Python
6
star
12

improved_l2_robustness

Python
4
star
13

fantastic-four

Code for the ICLR paper: https://openreview.net/forum?id=JCRblSgs34Z
Python
4
star
14

so-robust

Code for ICML paper "Second-Order Provable Defenses against Adversarial Attacks"
Python
3
star
15

sparse-convolution

Code for sparse convolution written in C++
C++
2
star
16

singlasahil14.github.io

HTML
1
star
17

char-rnn

Python
1
star
18

data-augmentation

Code for fast data augmentation
Python
1
star