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

Implementation of Enformer, Deepmind's attention network for predicting gene expression, in Pytorch

Posterior predictive distributions quantify uncertainties ignored by point estimates.

This is a TensorFlow implementation for C2-Rec

Learnable Boundary Guided Adversarial Training (ICCV2021)

Robustness via Cross-Domain Ensembles

FindFunc is an IDA PRO plugin to find code functions that contain a certain assembly or byte pattern, reference a certain name or string, or conform to various other constraints.

Weakly supervised medical named entity classification

Phy-Q: A Benchmark for Physical Reasoning

[ICCV'21] Neural Radiance Flow for 4D View Synthesis and Video Processing

A collection of differentiable SVD methods and also the official implementation of the ICCV21 paper "Why Approximate Matrix Square Root Outperforms Accurate SVD in Global Covariance Pooling?"

Deep Learning Package based on TensorFlow

Official Implementation of Neural Splines

code for our paper "Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer"

TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.

YoloV3 Implemented in Tensorflow 2.0

automated systems to assist guarding corona Virus precautions for Closed Rooms (e.g. Halls, offices, etc..)

PyTorch code for the ICCV'21 paper: "Always Be Dreaming: A New Approach for Class-Incremental Learning"

Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.

[CVPR 2021] Few-shot 3D Point Cloud Semantic Segmentation

A Temporal Extension Library for PyTorch Geometric