From a non-central panorama, 3D lines can be recovered by geometric reasoning. However, their sensitivity to noise and the complex geometric modeling required has led these panoramas being very little investigated. In...
详细信息
ISBN:
(纸本)9781665448994
From a non-central panorama, 3D lines can be recovered by geometric reasoning. However, their sensitivity to noise and the complex geometric modeling required has led these panoramas being very little investigated. In this work we present a novel approach for 3D layout recovery of indoor environments using single non-central panoramas. We obtain the boundaries of the structural lines of the room from a non-central panorama using deep learning and exploit the properties of non-central projection systems in a new geometrical processing to recover the scaled layout. We solve the problem for Manhattan environments, handling occlusions, and also for Atlanta environments in an unified method. The experiments performed improve the state-of-the-art methods for 3D layout recovery from a single panorama. Our approach is the first work using deep learning with non-central panoramas and recovering the scale of single panorama layouts.
Recently, deep face recognition has achieved significant progress because of Convolutional Neural Networks (CNNs) and large-scale datasets. However, training CNNs on a large-scale face recognition dataset with limited...
详细信息
ISBN:
(纸本)9781665445092
Recently, deep face recognition has achieved significant progress because of Convolutional Neural Networks (CNNs) and large-scale datasets. However, training CNNs on a large-scale face recognition dataset with limited computational resources is still a challenge. This is because the classification paradigm needs to train a fully-connected layer as the category classifier, and its parameters will be in the hundreds of millions if the training dataset contains millions of identities. This requires many computational resources, such as GPU memory. The metric learning paradigm is an economical computation method, but its performance is greatly inferior to that of the classification paradigm. To address this challenge, we propose a simple but effective CNN layer called the Virtual fully-connected (Virtual FC) layer to reduce the computational consumption of the classification paradigm. Without bells and whistles, the proposed Virtual FC reduces the parameters by more than 100 times with respect to the fully-connected layer and achieves competitive performance on mainstream face recognition evaluation datasets. Moreover, the performance of our Virtual FC layer on the evaluation datasets is superior to that of the metric learning paradigm by a significant margin. Our code will be released in hopes of disseminating our idea to other domains1.
The laws of model size, data volume, computation and model performance have been extensively studied in the field of Natural Language Processing (NLP). However, the scaling laws in Scene Text recognition (STR) have no...
详细信息
ISBN:
(数字)9798350353006
ISBN:
(纸本)9798350353013
The laws of model size, data volume, computation and model performance have been extensively studied in the field of Natural Language Processing (NLP). However, the scaling laws in Scene Text recognition (STR) have not yet been investigated. To address this, we conducted comprehensive studies that involved examining the correlations between performance and the scale of models, data volume and computation in the field of text recognition. Conclusively, the study demonstrates smooth power laws between performance and model size, as well as training data volume, when other influencing factors are held constant. Additionally, we have constructed a large-scale dataset called REBU-Syn, which comprises 6 M real samples and 18 M synthetic samples. Based on the disclosed scaling law and new dataset, we successfully trained a scene text recognition model, achieving a new state-of-the-art on 6 common test benchmarks with top-1 average accuracy of 97.42%. The models and dataset are publicly available at ***.
Despite the success of machine learning applications in science, industry, and society in general, many approaches are known to be non-robust, often relying on spurious correlations to make predictions. Spuriousness o...
详细信息
ISBN:
(纸本)9781665445092
Despite the success of machine learning applications in science, industry, and society in general, many approaches are known to be non-robust, often relying on spurious correlations to make predictions. Spuriousness occurs when some features correlate with labels but are not causal;relying on such features prevents models from generalizing to unseen environments where such correlations break. In this work, we focus on image classification and propose two data generation processes to reduce spuriousness. Given human annotations of the subset of the features responsible (causal) for the labels (e.g. bounding boxes), we modify this causal set to generate a surrogate image that no longer has the same label (i.e. a counterfactual image). We also alter non-causal features to generate images still recognized as the original labels, which helps to learn a model invariant to these features. In several challenging datasets, our data generations outperform state-of-the-art methods in accuracy when spurious correlations break, and increase the saliency focus on causal features providing better explanations.
The Capsule Network is widely believed to be more robust than Convolutional Networks. However, there are no comprehensive comparisons between these two networks, and it is also unknown which components in the CapsNet ...
详细信息
ISBN:
(纸本)9781665445092
The Capsule Network is widely believed to be more robust than Convolutional Networks. However, there are no comprehensive comparisons between these two networks, and it is also unknown which components in the CapsNet affect its robustness. In this paper, we first carefully examine the special designs in CapsNet that differ from that of a ConvNet commonly used for image classification. The examination reveals five major new/different components in CapsNet: a transformation process, a dynamic routing layer, a squashing function, a marginal loss other than cross-entropy loss, and an additional class-conditional reconstruction loss for regularization. Along with these major differences, we conduct comprehensive ablation studies on three kinds of robustness, including affine transformation, overlapping digits, and semantic representation. The study reveals that some designs, which are thought critical to CapsNet, actually can harm its robustness, i.e., the dynamic routing layer and the transformation process, while others are beneficial for the robustness. Based on these findings, we propose enhanced ConvNets simply by introducing the essential components behind the CapsNet's success. The proposed simple ConvNets can achieve better robustness than the CapsNet.
Designed to learn long-range interactions on sequential data, transformers continue to show state-of-the-art results on a wide variety of tasks. In contrast to CNNs, they contain no inductive bias that prioritizes loc...
详细信息
ISBN:
(纸本)9781665445092
Designed to learn long-range interactions on sequential data, transformers continue to show state-of-the-art results on a wide variety of tasks. In contrast to CNNs, they contain no inductive bias that prioritizes local interactions. This makes them expressive, but also computationally infeasible for long sequences, such as high-resolution images. We demonstrate how combining the effectiveness of the inductive bias of CNNs with the expressivity of transformers enables them to model and thereby synthesize high-resolution images. We show how to (i) use CNNs to learn a contextrich vocabulary of image constituents, and in turn (ii) utilize transformers to efficiently model their composition within high-resolution images. Our approach is readily applied to conditional synthesis tasks, where both non-spatial information, such as object classes, and spatial information, such as segmentations, can control the generated image. In particular, we present the first results on semantically-guided synthesis of megapixel images with transformers. Project page at https://***/JLlvY.
We present MaX-DeepLab, the first end-to-end model for panoptic segmentation. Our approach simplifies the current pipeline that depends heavily on surrogate sub-tasks and hand-designed components, such as box detectio...
详细信息
ISBN:
(纸本)9781665445092
We present MaX-DeepLab, the first end-to-end model for panoptic segmentation. Our approach simplifies the current pipeline that depends heavily on surrogate sub-tasks and hand-designed components, such as box detection, non-maximum suppression, thing-stuff merging, etc. Although these sub-tasks are tackled by area experts, they fail to comprehensively solve the target task. By contrast, our MaX-DeepLab directly predicts class-labeled masks with a mask transformer, and is trained with a panoptic quality inspired loss via bipartite matching. Our mask transformer employs a dual-path architecture that introduces a global memory path in addition to a CNN path, allowing direct communication with any CNN layers. As a result, MaX-DeepLab shows a significant 7.1% PQ gain in the box-free regime on the challenging COCO dataset, closing the gap between box-based and box-free methods for the first time. A small variant of MaX-DeepLab improves 3.0% PQ over DETR with similar parameters and M-Adds. Furthermore, MaX-DeepLab, without test time augmentation, achieves new state-of-the-art 51.3% PQ on COCO test-dev set.
Combining Natural Language with vision represents a unique and interesting challenge in the domain of Artificial Intelligence. The AI City Challenge Track 5 for Natural Language-Based Vehicle Retrieval focuses on the ...
详细信息
ISBN:
(纸本)9781665448994
Combining Natural Language with vision represents a unique and interesting challenge in the domain of Artificial Intelligence. The AI City Challenge Track 5 for Natural Language-Based Vehicle Retrieval focuses on the problem of combining visual and textual information, applied to a smart-city use case. In this paper, we present All You Can Embed (AYCE), a modular solution to correlate single-vehicle tracking sequences with natural language. The main building blocks of the proposed architecture are (i) BERT to provide an embedding of the textual descriptions, (ii) a convolutional backbone along with a Transformer model to embed the visual information. For the training of the retrieval model, a variation of the Triplet Margin Loss is proposed to learn a distance measure between the visual and language embeddings. The code is publicly available at https://***/cscribano/AYCE_2021.
Contemporary neural networks are limited in their ability to learn from evolving streams of training data. When trained sequentially on new or evolving tasks, their accuracy drops sharply, making them unsuitable for m...
详细信息
ISBN:
(纸本)9781665448994
Contemporary neural networks are limited in their ability to learn from evolving streams of training data. When trained sequentially on new or evolving tasks, their accuracy drops sharply, making them unsuitable for many real-world applications. In this work, we shed light on the causes of this well known yet unsolved phenomenon often referred to as catastrophic forgetting - in a class-incremental setup. We show that a combination of simple components and a loss that balances intra-task and inter-task learning can already resolve forgetting to the same extent as more complex measures proposed in literature. Moreover, we identify poor quality of the learned representation as another reason for catastrophic forgetting in class-IL. We show that performance is correlated with secondary class information (dark knowledge) learned by the model and it can be improved by an appropriate regularizer. With these lessons learned, class-incremental learning results on CIFAR-100 and ImageNet improve over the state-of-the-art by a large margin, while keeping the approach simple.
Sketch-based image retrieval (SBIR) has undergone an increasing interest in the community of computervision bringing high impact in real applications. For instance, SBIR brings an increased benefit to eCommerce searc...
详细信息
ISBN:
(纸本)9781665448994
Sketch-based image retrieval (SBIR) has undergone an increasing interest in the community of computervision bringing high impact in real applications. For instance, SBIR brings an increased benefit to eCommerce search engines because it allows users to formulate a query just by drawing what they need to buy. However, current methods showing high precision in retrieval work in a high dimensional space, which negatively affects aspects like memory consumption and time processing. Although some authors have also proposed compact representations, these drastically degrade the performance in a low dimension. Therefore in this work, we present different results of evaluating methods for producing compact embeddings in the context of sketch-based image retrieval. Our main interest is in strategies aiming to keep the local structure of the original space. The recent unsupervised local-topology preserving dimension reduction method UMAP fits our requirements and shows outstanding performance, improving even the precision achieved by SOTA methods. We evaluate six methods in two different datasets. We use Flickr15K and eCommerce datasets;the latter is another contribution of this work. We show that UMAP allows us to have feature vectors of 16 bytes improving precision by more than 35%.
暂无评论