Contrastive Learning with Non-Semantic Negatives

This repository is the official implementation of Robust Contrastive Learning Using Negative Samples with Diminished Semantics. Contrastive learning utilizes positive pairs which preserve semantic information while perturbing superficial features in the training images. Similarly, we propose to generate negative samples to make the model more robust, where only the superfluous instead of the semantic features are preserved.

Preparation

Install PyTorch and check preprocess/ for ImageNet-100 and ImageNet-Texture preprocessing scripts.

Training

The following code is used to pre-train MoCo-v2 + patch / texture-based NS. The major code is developed with minimal modifications from the official implementation.

python moco-non-sem-neg.py -a resnet50 --lr 0.03 --batch-size 128 --dist-url 'tcp://localhost:10001' \
  --multiprocessing-distributed --world-size 1 --rank 0 \
  --mlp --moco-t 0.2 --aug-plus --cos --moco-k 16384 \
  --robust nonsem --num-nonsem 1 --alpha 2 --epochs 200 --patch-ratio 16 72 \
  --ckpt_path ./ckpts/mocov2_mocok16384_bs128_lr0.03_nonsem_16_72_noaug_nn1_alpha2_epoch200  \
  /path/to/imagenet-100/ 

python moco-non-sem-neg.py -a resnet50 --lr 0.03 --batch-size 128 --dist-url 'tcp://localhost:10001' \
  --multiprocessing-distributed --world-size 1 --rank 0 \
  --mlp --moco-t 0.2 --aug-plus --cos --moco-k 16384 \
  --robust texture_syn --num-nonsem 1 --alpha 2 --epochs 200 \
  --ckpt_path ./ckpts/mocov2_mocok16384_bs128_lr0.03_texture_nn1_alpha2_epoch200 \
  /path/to/imagenet-100-texture/

Change /path/to/imagenet-100/ with the ImageNet-100 dataset directory.
Change --alpha and -moco-k to reproduce results with different configurations.

Linear Evaluation

Run following code is used to reproduce MoCo-v2 + patch-based NS model reported in Table 1.

python main_lincls.py -a resnet50 --lr 10.0 --batch-size 128 --epochs 60 \
  --pretrained ./ckpts/mocov2_mocok16384_bs128_lr0.03_nonsem_16_72_noaug_nn1_alpha2_epoch200/checkpoint_0199.pth.tar \
  --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 \
  --ckpt_path ./ckpts/mocov2_mocok16384_bs128_lr0.03_nonsem_16_72_noaug_nn1_alpha2_epoch200 \
  /path/to/imagenet-100/

Pre-trained Models

You can download pretrained models here:

	moco-k	alpha	ImageNet-100	Corruption	Sketch	Stylized	Rendition	Checkpoints
MoCo-v2	16384	-	77.88±0.28	43.08±0.27	28.24±0.58	16.20±0.55	32.92±0.12	Run1, Run2, Run3
+ Texture	16384	2	77.76±0.17	43.58±0.33	29.11±0.39	16.59±0.17	33.36±0.15	Run1, Run2, Run3
+ Patch	16384	2	79.35±0.12	45.13±0.35	31.76±0.88	17.37±0.19	34.78±0.15	Run1, Run2, Run3
+ Patch	16384	3	75.58±0.52	44.45±0.15	34.03±0.58	18.60±0.26	36.89±0.11	Run1, Run2, Run3
MoCo-v2	8192	-	77.73±0.38	43.22±0.39	28.45±0.36	16.83±0.12	33.19±0.44	Run1, Run2, Run3
+ Patch	8192	2	79.54±0.32	45.48±0.20	33.36±0.45	17.81±0.32	36.31±0.37	Run1, Run2, Run3

Contrastive Learning with Non-Semantic Negatives

Related tags

Overview

Contrastive Learning with Non-Semantic Negatives

Preparation

Training

Linear Evaluation

Pre-trained Models

Owner

Viperdb - A tiny log-structured key-value database written in pure Python

MPI-IS Mesh Processing Library

code associated with ACL 2021 DExperts paper

Package for extracting emotions from social media text. Tailored for financial data.

Efficiently computes derivatives of numpy code.

Reproducing code of hair style replacement method from Barbershorp.

MoCap-Solver: A Neural Solver for Optical Motion Capture Data

Code for MarioNette: Self-Supervised Sprite Learning, in NeurIPS 2021

Efficiently Disentangle Causal Representations

This program automatically runs Python code copied in clipboard

Face uncertainty quantification or estimation using PyTorch.

Training Very Deep Neural Networks Without Skip-Connections

Using fully convolutional networks for semantic segmentation with caffe for the cityscapes dataset

Hydra: an Extensible Fuzzing Framework for Finding Semantic Bugs in File Systems

Interpretable and Generalizable Person Re-Identification with Query-Adaptive Convolution and Temporal Lifting

Official Implementation for "StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery" (ICCV 2021 Oral)

Solutions of Reinforcement Learning 2nd Edition

Monocular Depth Estimation - Weighted-average prediction from multiple pre-trained depth estimation models

A toolkit for document-level event extraction, containing some SOTA model implementations

RAMA: Rapid algorithm for multicut problem