Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userYour Flamingo is My Bird: Fine-Grained, or Not
134
0
0.0
(
0
)
Added by
Dongliang Chang
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Whether what you see in Figure 1 is a flamingo or a bird, is the question we ask in this paper. While fine-grained visual classification (FGVC) strives to arrive at the former, for the majority of us non-experts just bird would probably suffice. The real question is therefore -- how can we tailor for different fine-grained definitions under divergent levels of expertise. For that, we re-envisage the traditional setting of FGVC, from single-label classification, to that of top-down traversal of a pre-defined coarse-to-fine label hierarchy -- so that our answer becomes bird-->Phoenicopteriformes-->Phoenicopteridae-->flamingo. To approach this new problem, we first conduct a comprehensive human study where we confirm that most participants prefer multi-granularity labels, regardless whether they consider themselves experts. We then discover the key intuition that: coarse-level label prediction exacerbates fine-grained feature learning, yet fine-level feature betters the learning of coarse-level classifier. This discovery enables us to design a very simple albeit surprisingly effective solution to our new problem, where we (i) leverage level-specific classification heads to disentangle coarse-level features with fine-grained ones, and (ii) allow finer-grained features to participate in coarser-grained label predictions, which in turn helps with better disentanglement. Experiments show that our method achieves superior performance in the new FGVC setting, and performs better than state-of-the-art on traditional single-label FGVC problem as well. Thanks to its simplicity, our method can be easily implemented on top of any existing FGVC frameworks and is parameter-free.
rate research
Read More
Ontology-based data integration has been one of the practical methodologies for heterogeneous legacy database integrated service construction. However, it is neither efficient nor economical to build the cross-domain ontology on top of the schemas of each legacy database for the specific integration application than to reuse the existed ontologies. Then the question lies in whether the existed ontology is compatible with the cross-domain queries and with all the legacy systems. It is highly needed an effective criteria to evaluate the compatibility as it limits the upbound quality of the integrated services. This paper studies the semantic similarity of schemas from the aspect of properties. It provides a set of in-depth criteria, namely coverage and flexibility to evaluate the compatibility among the queries, the schemas and the existing ontology. The weights of classes are extended to make precise compatibility computation. The use of such criteria in the practical project verifies the applicability of our method.
Mirrors are everywhere in our daily lives. Existing computer vision systems do not consider mirrors, and hence may get confused by the reflected content inside a mirror, resulting in a severe performance degradation. However, separating the real content outside a mirror from the reflected content inside it is non-trivial. The key challenge is that mirrors typically reflect contents similar to their surroundings, making it very difficult to differentiate the two. In this paper, we present a novel method to segment mirrors from an input image. To the best of our knowledge, this is the first work to address the mirror segmentation problem with a computational approach. We make the following contributions. First, we construct a large-scale mirror dataset that contains mirror images with corresponding manually annotated masks. This dataset covers a variety of daily life scenes, and will be made publicly available for future research. Second, we propose a novel network, called MirrorNet, for mirror segmentation, by modeling both semantical and low-level color/texture discontinuities between the contents inside and outside of the mirrors. Third, we conduct extensive experiments to evaluate the proposed method, and show that it outperforms the carefully chosen baselines from the state-of-the-art detection and segmentation methods.
Fine-Grained Visual Classification (FGVC) is an important computer vision problem that involves small diversity within the different classes, and often requires expert annotators to collect data. Utilizing this notion of small visual diversity, we revisit Maximum-Entropy learning in the context of fine-grained classification, and provide a training routine that maximizes the entropy of the output probability distribution for training convolutional neural networks on FGVC tasks. We provide a theoretical as well as empirical justification of our approach, and achieve state-of-the-art performance across a variety of classification tasks in FGVC, that can potentially be extended to any fine-tuning task. Our method is robust to different hyperparameter values, amount of training data and amount of training label noise and can hence be a valuable tool in many similar problems.
Neural networks are susceptible to catastrophic forgetting. They fail to preserve previously acquired knowledge when adapting to new tasks. Inspired by human associative memory system, we propose a brain-like approach that imitates the associative learning process to achieve continual learning. We design a heuristics mechanism to potentiatively stimulate the model, which guides the model to recall the historical episodes based on the current circumstance and obtained association experience. Besides, a distillation measure is added to depressively alter the efficacy of synaptic transmission, which dampens the feature reconstruction learning for new task. The framework is mediated by potentiation and depression stimulation that play opposing roles in directing synaptic and behavioral plasticity. It requires no access to the original data and is more similar to human cognitive process. Experiments demonstrate the effectiveness of our method in alleviating catastrophic forgetting on image-to-image translation tasks.
We present a doubly holographic prescription for computing entanglement entropy on a gravitating brane. It involves a Ryu-Takayanagi surface with a Dirichlet anchoring condition. In braneworld cosmology, a related approach was used previously in arXiv:2007.06551. There, the prescription naturally computed a co-moving entanglement entropy, and was argued to resolve the information paradox for a black hole living in the cosmology. In this paper, we show that the Dirichlet prescription leads to reasonable results, when applied to a recently studied wedge holography set up with a gravitating bath. The nature of the information paradox and its resolution in our Dirichlet problem have a natural understanding in terms of the strength of gravity on the two branes and at the anchoring location. By sliding the anchor to the defect, we demonstrate that the limit where gravity decouples from the anchor is continuous -- in other words, as far as island physics is considered, weak gravity on the anchor is identical to no gravity. The weak and (moderately) strong gravity regions on the brane are separated by a Dirichlet wall. We find an intricate interplay between various extremal surfaces, with an island coming to the rescue whenever there is an information paradox. This is despite the presence of massless gravitons in the spectrum. The overall physics is consistent with the slogan that gravity becomes more holographic, as it gets stronger. Our observations strengthen the case that the conventional Page curve is indeed of significance, when discussing the information paradox in flat space. We work in high enough dimensions so that the graviton is non-trivial, and our results are in line with the previous discussions on gravitating baths in arXiv:2005.02993 and arXiv:2007.06551.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
