This document discusses generative adversarial networks (GANs) and their relationship to reinforcement learning. It begins with an introduction to GANs, explaining how they can generate images without explicitly defining a probability distribution by using an adversarial training process. The second half discusses how GANs are related to actor-critic models and inverse reinforcement learning in reinforcement learning. It explains how GANs can be viewed as training a generator to fool a discriminator, similar to how policies are trained in reinforcement learning.
Several recent papers have explored self-supervised learning methods for vision transformers (ViT). Key approaches include:
1. Masked prediction tasks that predict masked patches of the input image.
2. Contrastive learning using techniques like MoCo to learn representations by contrasting augmented views of the same image.
3. Self-distillation methods like DINO that distill a teacher ViT into a student ViT using different views of the same image.
4. Hybrid approaches that combine masked prediction with self-distillation, such as iBOT.
1. The document discusses energy-based models (EBMs) and how they can be applied to classifiers. It introduces noise contrastive estimation and flow contrastive estimation as methods to train EBMs.
2. One paper presented trains energy-based models using flow contrastive estimation by passing data through a flow-based generator. This allows implicit modeling with EBMs.
3. Another paper argues that classifiers can be viewed as joint energy-based models over inputs and outputs, and should be treated as such. It introduces a method to train classifiers as EBMs using contrastive divergence.
Several recent papers have explored self-supervised learning methods for vision transformers (ViT). Key approaches include:
1. Masked prediction tasks that predict masked patches of the input image.
2. Contrastive learning using techniques like MoCo to learn representations by contrasting augmented views of the same image.
3. Self-distillation methods like DINO that distill a teacher ViT into a student ViT using different views of the same image.
4. Hybrid approaches that combine masked prediction with self-distillation, such as iBOT.
1. The document discusses energy-based models (EBMs) and how they can be applied to classifiers. It introduces noise contrastive estimation and flow contrastive estimation as methods to train EBMs.
2. One paper presented trains energy-based models using flow contrastive estimation by passing data through a flow-based generator. This allows implicit modeling with EBMs.
3. Another paper argues that classifiers can be viewed as joint energy-based models over inputs and outputs, and should be treated as such. It introduces a method to train classifiers as EBMs using contrastive divergence.
[DL輪読会]Generative Models of Visually Grounded ImaginationDeep Learning JP
The document proposes a new model for visually grounded semantic imagination that can generate images from linguistic descriptions of concepts specified by attributes. The model uses a variational autoencoder with three inference networks to handle images, attributes, and missing modalities. It represents the attribute inference distribution as the product of expert Gaussians, allowing generation of concepts not seen during training by combining learned attributes. The paper introduces three criteria for evaluating such models: correctness, coverage, and compositionality.
2017年春季研究発表会の発表資料です.
邦題: 形態素解析も辞書も言語モデルもいらないend-to-end音声認識
英題: End-to-end Japanese ASR without using morphological analyzer, pronunciation dictionary and language model