اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدWhat Is Around The Camera?
68
0
0.0
(
0
)
نشر من قبل
Konstantinos Rematas
تاريخ النشر
2016
مجال البحث
الهندسة المعلوماتية
والبحث باللغة
English
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
How much does a single image reveal about the environment it was taken in? In this paper, we investigate how much of that information can be retrieved from a foreground object, combined with the background (i.e. the visible part of the environment). Assuming it is not perfectly diffuse, the foreground object acts as a complexly shaped and far-from-perfect mirror. An additional challenge is that its appearance confounds the light coming from the environment with the unknown materials it is made of. We propose a learning-based approach to predict the environment from multiple reflectance maps that are computed from approximate surface normals. The proposed method allows us to jointly model the statistics of environments and material properties. We train our system from synthesized training data, but demonstrate its applicability to real-world data. Interestingly, our analysis shows that the information obtained from objects made out of multiple materials often is complementary and leads to better performance.
قيم البحث
اقرأ أيضاً
In this article we study the problem of document image representation based on visual features. We propose a comprehensive experimental study that compares three types of visual document image representations: (1) traditional so-called shallow featur
es, such as the RunLength and the Fisher-Vector descriptors, (2) deep features based on Convolutional Neural Networks, and (3) features extracted from hybrid architectures that take inspiration from the two previous ones. We evaluate these features in several tasks (i.e. classification, clustering, and retrieval) and in different setups (e.g. domain transfer) using several public and in-house datasets. Our results show that deep features generally outperform other types of features when there is no domain shift and the new task is closely related to the one used to train the model. However, when a large domain or task shift is present, the Fisher-Vector shallow features generalize better and often obtain the best results.
This is an opinion paper. We hope to deliver a key message that current visual recognition systems are far from complete, i.e., recognizing everything that human can recognize, yet it is very unlikely that the gap can be bridged by continuously incre
asing human annotations. Based on the observation, we advocate for a new type of pre-training task named learning-by-compression. The computational models (e.g., a deep network) are optimized to represent the visual data using compact features, and the features preserve the ability to recover the original data. Semantic annotations, when available, play the role of weak supervision. An important yet challenging issue is the evaluation of image recovery, where we suggest some design principles and future research directions. We hope our proposal can inspire the community to pursue the compression-recovery tradeoff rather than the accuracy-complexity tradeoff.
(This paper was written in November 2011 and never published. It is posted on arXiv.org in its original form in June 2016). Many recent object recognition systems have proposed using a two phase training procedure to learn sparse convolutional featur
e hierarchies: unsupervised pre-training followed by supervised fine-tuning. Recent results suggest that these methods provide little improvement over purely supervised systems when the appropriate nonlinearities are included. This paper presents an empirical exploration of the space of learning procedures for sparse convolutional networks to assess which method produces the best performance. In our study, we introduce an augmentation of the Predictive Sparse Decomposition method that includes a discriminative term (DPSD). We also introduce a new single phase supervised learning procedure that places an L1 penalty on the output state of each layer of the network. This forces the network to produce sparse codes without the expensive pre-training phase. Using DPSD with a new, complex predictor that incorporates lateral inhibition, combined with multi-scale feature pooling, and supervised refinement, the system achieves a 70.6% recognition rate on Caltech-101. With the addition of convolutional training, a 77% recognition was obtained on the CIfAR-10 dataset.
This paper aims at providing a global perspective on electromagnetic nonreciprocity and clarifying confusions that arose in the recent developments of the field. It provides a general definition of nonreciprocity and classifies nonreciprocal systems
according to their linear time-invariant (LTI), linear time-variant (LTV) or nonlinear nonreciprocal natures. The theory of nonlinear systems is established on the foundation of the concepts of time reversal, time-reversal symmetry, time-reversal symmetry breaking and related Onsager- Casimir relations. Special attention is given to LTI systems, as the most common nonreciprocal systems, for which a generalized form of the Lorentz reciprocity theorem is derived. The delicate issue of loss in nonreciprocal systems is demystified and the so-called thermodynamics paradox is resolved from energy conservation considerations. The fundamental characteristics and applications of LTI, LTV and nonlinear nonreciprocal systems are overviewed with the help of pedagogical examples. Finally, asymmetric structures with fallacious nonreciprocal appearances are debunked.
General acceptance of a mathematical proposition $P$ as a theorem requires convincing evidence that a proof of $P$ exists. But what constitutes convincing evidence? I will argue that, given the types of evidence that are currently accepted as convinc
ing, it is inconsistent to deny similar acceptance to the evidence provided for the existence of proofs by certain randomized computations.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
