اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدMONet: Unsupervised Scene Decomposition and Representation
126
0
0.0
(
0
)
نشر من قبل
Christopher Burgess
تاريخ النشر
2019
مجال البحث
الهندسة المعلوماتية
والبحث باللغة
English
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
The ability to decompose scenes in terms of abstract building blocks is crucial for general intelligence. Where those basic building blocks share meaningful properties, interactions and other regularities across scenes, such decompositions can simplify reasoning and facilitate imagination of novel scenarios. In particular, representing perceptual observations in terms of entities should improve data efficiency and transfer performance on a wide range of tasks. Thus we need models capable of discovering useful decompositions of scenes by identifying units with such regularities and representing them in a common format. To address this problem, we have developed the Multi-Object Network (MONet). In this model, a VAE is trained end-to-end together with a recurrent attention network -- in a purely unsupervised manner -- to provide attention masks around, and reconstructions of, regions of images. We show that this model is capable of learning to decompose and represent challenging 3D scenes into semantically meaningful components, such as objects and background elements.
قيم البحث
اقرأ أيضاً
Contrastive self-supervised learning has largely narrowed the gap to supervised pre-training on ImageNet. However, its success highly relies on the object-centric priors of ImageNet, i.e., different augmented views of the same image correspond to the
same object. Such a heavily curated constraint becomes immediately infeasible when pre-trained on more complex scene images with many objects. To overcome this limitation, we introduce Object-level Representation Learning (ORL), a new self-supervised learning framework towards scene images. Our key insight is to leverage image-level self-supervised pre-training as the prior to discover object-level semantic correspondence, thus realizing object-level representation learning from scene images. Extensive experiments on COCO show that ORL significantly improves the performance of self-supervised learning on scene images, even surpassing supervised ImageNet pre-training on several downstream tasks. Furthermore, ORL improves the downstream performance when more unlabeled scene images are available, demonstrating its great potential of harnessing unlabeled data in the wild. We hope our approach can motivate future research on more general-purpose unsupervised representation learning from scene data. Project page: https://www.mmlab-ntu.com/project/orl/.
Existing research in scene image classification has focused on either content features (e.g., visual information) or context features (e.g., annotations). As they capture different information about images which can be complementary and useful to dis
criminate images of different classes, we suppose the fusion of them will improve classification results. In this paper, we propose new techniques to compute content features and context features, and then fuse them together. For content features, we design multi-scale deep features based on background and foreground information in images. For context features, we use annotations of similar images available in the web to design a filter words (codebook). Our experiments in three widely used benchmark scene datasets using support vector machine classifier reveal that our proposed context and content features produce better results than existing context and content features, respectively. The fusion of the proposed two types of features significantly outperform numerous state-of-the-art features.
One significant factor we expect the video representation learning to capture, especially in contrast with the image representation learning, is the object motion. However, we found that in the current mainstream video datasets, some action categorie
s are highly related with the scene where the action happens, making the model tend to degrade to a solution where only the scene information is encoded. For example, a trained model may predict a video as playing football simply because it sees the field, neglecting that the subject is dancing as a cheerleader on the field. This is against our original intention towards the video representation learning and may bring scene bias on different dataset that can not be ignored. In order to tackle this problem, we propose to decouple the scene and the motion (DSM) with two simple operations, so that the model attention towards the motion information is better paid. Specifically, we construct a positive clip and a negative clip for each video. Compared to the original video, the positive/negative is motion-untouched/broken but scene-broken/untouched by Spatial Local Disturbance and Temporal Local Disturbance. Our objective is to pull the positive closer while pushing the negative farther to the original clip in the latent space. In this way, the impact of the scene is weakened while the temporal sensitivity of the network is further enhanced. We conduct experiments on two tasks with various backbones and different pre-training datasets, and find that our method surpass the SOTA methods with a remarkable 8.1% and 8.8% improvement towards action recognition task on the UCF101 and HMDB51 datasets respectively using the same backbone.
Unsupervised learning methods based on contrastive learning have drawn increasing attention and achieved promising results. Most of them aim to learn representations invariant to instance-level variations, which are provided by different views of the
same instance. In this paper, we propose Invariance Propagation to focus on learning representations invariant to category-level variations, which are provided by different instances from the same category. Our method recursively discovers semantically consistent samples residing in the same high-density regions in representation space. We demonstrate a hard sampling strategy to concentrate on maximizing the agreement between the anchor sample and its hard positive samples, which provide more intra-class variations to help capture more abstract invariance. As a result, with a ResNet-50 as the backbone, our method achieves 71.3% top-1 accuracy on ImageNet linear classification and 78.2% top-5 accuracy fine-tuning on only 1% labels, surpassing previous results. We also achieve state-of-the-art performance on other downstream tasks, including linear classification on Places205 and Pascal VOC, and transfer learning on small scale datasets.
Previous methods for representing scene images based on deep learning primarily consider either the foreground or background information as the discriminating clues for the classification task. However, scene images also require additional informatio
n (hybrid) to cope with the inter-class similarity and intra-class variation problems. In this paper, we propose to use hybrid features in addition to foreground and background features to represent scene images. We suppose that these three types of information could jointly help to represent scene image more accurately. To this end, we adopt three VGG-16 architectures pre-trained on ImageNet, Places, and Hybrid (both ImageNet and Places) datasets for the corresponding extraction of foreground, background and hybrid information. All these three types of deep features are further aggregated to achieve our final features for the representation of scene images. Extensive experiments on two large benchmark scene datasets (MIT-67 and SUN-397) show that our method produces the state-of-the-art classification performance.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
