paper-with-me

Papers

Large Scale Adversarial Representation Learning

2019-07-04 · NeurIPS 2019 12 · Jeff Donahue, Karen Simonyan

Adversarially trained generative models (GANs) have recently achieved compelling image synthesis results. But despite early successes in using GANs for unsupervised representation learning, they have since been superseded by approaches based on self-supervision. In this work we show that progress in image generation quality translates to substantially improved representation learning performance. Our approach, BigBiGAN, builds upon the state-of-the-art BigGAN model, extending it to representation learning by adding an encoder and modifying the discriminator. We extensively evaluate the representation learning and generation capabilities of these BigBiGAN models, demonstrating that these generation-based models achieve the state of the art in unsupervised representation learning on ImageNet, as well as in unconditional image generation. Pretrained BigBiGAN models -- including image generators and encoders -- are available on TensorFlow Hub (https://tfhub.dev/s?publisher=deepmind&q=bigbigan).

📄 PDF Abstract BibTeX arXiv:1907.02544

Code (4)

LEGO999/BIgBiGAN tf
LEGO999/BigBiGAN-TensorFlow2.0 tf
lukemelas/unsupervised-image-segmentation pytorch
rkorzeniowski/bigbigan-pytorch pytorch

Tasks

Contrastive LearningImage GenerationRepresentation LearningSelf-Supervised Image ClassificationSemi-Supervised Image ClassificationUnconditional Image Generation

Methods 이 논문이 사용한 방법론

HuMan(Expedia)||How do I get a human at Expedia? How do I get a human at Expedia? How Do I Get a Human at Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Real-Time Help & Exclusive…
Reversible Residual Block 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
CReLU 설명 없음
RevNet A Reversible Residual Network, or RevNet, is a variant of a ResNet where each layer’s activations can be reconstructed exactly…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…

Similar Papers 제목 키워드 기반

Large-Scale Adversarial Training for Vision-and-Language Representation Learning

2020-06-11 · NeurIPS 2020 12 · Zhe Gan, Yen-Chun Chen, Linjie Li, Chen Zhu 외

We present VILLA, the first known effort on large-scale adversarial training for vision-and-language (V+L) representation learning. VILLA consists of two training stages: (i) task-agnostic adversarial pre-training; follo…

Image-text RetrievalQuestion AnsweringReferring ExpressionReferring Expression Comprehension+8

MHTN: Modal-adversarial Hybrid Transfer Network for Cross-modal Retrieval

2017-08-08 · Xin Huang, Yuxin Peng, Mingkuan Yuan

Cross-modal retrieval has drawn wide interest for retrieval across different modalities of data. However, existing methods based on DNN face the challenge of insufficient cross-modal training data, which limits the train…

Cross-Modal RetrievalRepresentation LearningRetrievalTransfer Learning

Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective

2024-01-26 · Yue Xing, Xiaofeng Lin, Qifan Song, Yi Xu 외

Pre-training is known to generate universal representations for downstream tasks in large-scale deep learning such as large language models. Existing literature, e.g., \cite{kim2020adversarial}, empirically observe that …

Adversarial RobustnessContrastive Learningvalid

Calibrated Domain-Invariant Learning for Highly Generalizable Large Scale Re-Identification

2019-11-26 · Ye Yuan, Wuyang Chen, Tianlong Chen, Yang Yang 외

Many real-world applications, such as city-scale traffic monitoring and control, requires large-scale re-identification. However, previous ReID methods often failed to address two limitations in existing ReID benchmarks,…

Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selection

2023-02-08 · NeurIPS 2023 11 · Xilie Xu, Jingfeng Zhang, Feng Liu, Masashi Sugiyama 외

Adversarial contrastive learning (ACL) does not require expensive data annotations but outputs a robust representation that withstands adversarial attacks and also generalizes to a wide range of downstream tasks. However…

Contrastive Learning