اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدGenerative Models as a Data Source for Multiview Representation Learning
110
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Generative models are now capable of producing highly realistic images that look nearly indistinguishable from the data on which they are trained. This raises the question: if we have good enough generative models, do we still need datasets? We investigate this question in the setting of learning general-purpose visual representations from a black-box generative model rather than directly from data. Given an off-the-shelf image generator without any access to its training data, we train representations from the samples output by this generator. We compare several representation learning methods that can be applied to this setting, using the latent space of the generator to generate multiple views of the same semantic content. We show that for contrastive methods, this multiview data can naturally be used to identify positive pairs (nearby in latent space) and negative pairs (far apart in latent space). We find that the resulting representations rival those learned directly from real data, but that good performance requires care in the sampling strategy applied and the training method. Generative models can be viewed as a compressed and organized copy of a dataset, and we envision a future where more and more model zoos proliferate while datasets become increasingly unwieldy, missing, or private. This paper suggests several techniques for dealing with visual representation learning in such a future. Code is released on our project page: https://ali-design.github.io/GenRep/
قيم البحث
اقرأ أيضاً
emph{Objective and Impact Statement}. With the renaissance of deep learning, automatic diagnostic systems for computed tomography (CT) have achieved many successful applications. However, they are mostly attributed to careful expert annotations, whic
h are often scarce in practice. This drives our interest to the unsupervised representation learning. emph{Introduction}. Recent studies have shown that self-supervised learning is an effective approach for learning representations, but most of them rely on the empirical design of transformations and pretext tasks. emph{Methods}. To avoid the subjectivity associated with these methods, we propose the MVCNet, a novel unsupervised three dimensional (3D) representation learning method working in a transformation-free manner. We view each 3D lesion from different orientations to collect multiple two dimensional (2D) views. Then, an embedding function is learned by minimizing a contrastive loss so that the 2D views of the same 3D lesion are aggregated, and the 2D views of different lesions are separated. We evaluate the representations by training a simple classification head upon the embedding layer. emph{Results}. Experimental results show that MVCNet achieves state-of-the-art accuracies on the LIDC-IDRI (89.55%), LNDb (77.69%) and TianChi (79.96%) datasets for emph{unsupervised representation learning}. When fine-tuned on 10% of the labeled data, the accuracies are comparable to the supervised learning model (89.46% vs. 85.03%, 73.85% vs. 73.44%, 83.56% vs. 83.34% on the three datasets, respectively). emph{Conclusion}. Results indicate the superiority of MVCNet in emph{learning representations with limited annotations}.
Finding compact representation of videos is an essential component in almost every problem related to video processing or understanding. In this paper, we propose a generative model to learn compact latent codes that can efficiently represent and rec
onstruct a video sequence from its missing or under-sampled measurements. We use a generative network that is trained to map a compact code into an image. We first demonstrate that if a video sequence belongs to the range of the pretrained generative network, then we can recover it by estimating the underlying compact latent codes. Then we demonstrate that even if the video sequence does not belong to the range of a pretrained network, we can still recover the true video sequence by jointly updating the latent codes and the weights of the generative network. To avoid overfitting in our model, we regularize the recovery problem by imposing low-rank and similarity constraints on the latent codes of the neighboring frames in the video sequence. We use our methods to recover a variety of videos from compressive measurements at different compression rates. We also demonstrate that we can generate missing frames in a video sequence by interpolating the latent codes of the observed frames in the low-dimensional space.
As a kind of generative self-supervised learning methods, generative adversarial nets have been widely studied in the field of anomaly detection. However, the representation learning ability of the generator is limited since it pays too much attentio
n to pixel-level details, and generator is difficult to learn abstract semantic representations from label prediction pretext tasks as effective as discriminator. In order to improve the representation learning ability of generator, we propose a self-supervised learning framework combining generative methods and discriminative methods. The generator no longer learns representation by reconstruction error, but the guidance of discriminator, and could benefit from pretext tasks designed for discriminative methods. Our discriminative-generative representation learning method has performance close to discriminative methods and has a great advantage in speed. Our method used in one-class anomaly detection task significantly outperforms several state-of-the-arts on multiple benchmark data sets, increases the performance of the top-performing GAN-based baseline by 6% on CIFAR-10 and 2% on MVTAD.
In this paper, we present a conditional GAN with two generators and a common discriminator for multiview learning problems where observations have two views, but one of them may be missing for some of the training samples. This is for example the cas
e for multilingual collections where documents are not available in all languages. Some studies tackled this problem by assuming the existence of view generation functions to approximately complete the missing views; for example Machine Translation to translate documents into the missing languages. These functions generally require an external resource to be set and their quality has a direct impact on the performance of the learned multiview classifier over the completed training set. Our proposed approach addresses this problem by jointly learning the missing views and the multiview classifier using a tripartite game with two generators and a discriminator. Each of the generators is associated to one of the views and tries to fool the discriminator by generating the other missing view conditionally on the corresponding observed view. The discriminator then tries to identify if for an observation, one of its views is completed by one of the generators or if both views are completed along with its class. Our results on a subset of Reuters RCV1/RCV2 collections show that the discriminator achieves significant classification performance; and that the generators learn the missing views with high quality without the need of any consequent external resource.
We propose a novel loss for generative models, dubbed as GRaWD (Generative Random Walk Deviation), to improve learning representations of unexplored visual spaces. Quality learning representation of unseen classes (or styles) is crucial to facilitate
novel image generation and better generative understanding of unseen visual classes (a.k.a. Zero-Shot Learning, ZSL). By generating representations of unseen classes from their semantic descriptions, such as attributes or text, Generative ZSL aims at identifying unseen categories discriminatively from seen ones. We define GRaWD by constructing a dynamic graph, including the seen class/style centers and generated samples in the current mini-batch. Our loss starts a random walk probability from each center through visual generations produced from hallucinated unseen classes. As a deviation signal, we encourage the random walk to eventually land after t steps in a feature representation that is hard to classify to any of the seen classes. We show that our loss can improve unseen class representation quality on four text-based ZSL benchmarks on CUB and NABirds datasets and three attribute-based ZSL benchmarks on AWA2, SUN, and aPY datasets. We also study our losss ability to produce meaningful novel visual art generations on WikiArt dataset. Our experiments and human studies show that our loss can improve StyleGAN1 and StyleGAN2 generation quality, creating novel art that is significantly more preferred. Code will be made available.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
