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

ML models and internal tensors 3D visualizer

🏎️ Accelerate training and inference of 🤗 Transformers with easy to use hardware optimization tools

Hierarchical User Intent Graph Network for Multimedia Recommendation

IGCN : Image-to-graph convolutional network

Tree LSTM implementation in PyTorch

Light-Head R-CNN

The ICS Chat System project for NYU Shanghai Fall 2021

Bringing sanity to world of messed-up data

A Python reference implementation of the CF data model

공공장소에서 눈만 돌리면 CCTV가 보인다는 말이 과언이 아닐 정도로 CCTV가 우리 생활에 깊숙이 자리 잡았습니다.

PyTorch implementation of Towards Accurate Alignment in Real-time 3D Hand-Mesh Reconstruction (ICCV 2021).

Vrcwatch - Supply the local time to VRChat as Avatar Parameters through OSC

[WWW 2022] Zero-Shot Stance Detection via Contrastive Learning

paper: Hyperspectral Remote Sensing Image Classification Using Deep Convolutional Capsule Network

Compare outputs between layers written in Tensorflow and layers written in Pytorch

Exploring Image Deblurring via Blur Kernel Space (CVPR'21)

RE3: State Entropy Maximization with Random Encoders for Efficient Exploration

PaSST: Efficient Training of Audio Transformers with Patchout

Joint Unsupervised Learning (JULE) of Deep Representations and Image Clusters.

This repository collects 100 papers related to negative sampling methods.