RH Logo
Hubs
About
Live
Leaderboard

My Hubs
All

Trending Papers in Computer Science

Trending
Today
Trending
Today

Sign in to discover all of the research papers you care about, live as they're published.

98
Date Added: Jun 8, 2021
Authors: Amitai Armon, Ravid Shwartz-Ziv, Amitai Armon
Journal: Arxiv
Date Added: Jun 8, 2021
Authors: Amitai Armon, Ravid Shwartz-Ziv, Amitai Armon
Journal: Arxiv
A key element of AutoML systems is setting the types of models that will be used for each type of task. For classification and regression problems with tabular data, the use of tree ensemble models (like XGBoost) is usually recommended. However, several deep learning models for tabular data have recently been proposed, claiming to outperform XGBoost for some use-cases. In this paper, we explore whether these deep models should be a recommended option for tabular data, by rigorously comparing the new deep models to XGBoost on a variety of datasets. In addition to systematically comparing their accuracy, we consider the tuning and computation they require. Our study shows that XGBoost outperforms these deep models across the datasets, including datasets used in the papers that proposed the deep models. We also demonstrate that XGBoost requires much less tuning. On the positive side, we show that an ensemble of the deep models and XGBoost performs better on these datasets than XGBoost alone.
Author Profile Avatar
Author Profile Avatar
Author Profile Avatar
Paper Preview Page 1
32
Date Added: Jun 8, 2021
Authors: Geiger, Andreas, et al
Journal: Arxiv
Date Added: Jun 8, 2021
Authors: Geiger, Andreas, et al
Journal: Arxiv
In recent years, neural implicit representations gained popularity in 3D reconstruction due to their expressiveness and flexibility. However, the implicit nature of neural implicit representations results in slow inference time and requires careful initialization. In this paper, we revisit the classic yet ubiquitous point cloud representation and introduce a differentiable point-to-mesh layer using a differentiable formulation of Poisson Surface Reconstruction (PSR) that allows for a GPU-accelerated fast solution of the indicator function given an oriented point cloud. The differentiable PSR layer allows us to efficiently and differentiably bridge the explicit 3D point representation with the 3D mesh via the implicit indicator field, enabling end-to-end optimization of surface reconstruction metrics such as Chamfer distance. This duality between points and meshes hence allows us to represent shapes as oriented point clouds, which are explicit, lightweight and expressive. Compared to neural implicit representations, our Shape-As-Points (SAP) model is more interpretable, lightweight, and accelerates inference time by one order of magnitude. Compared to other explicit representations such as points, patches, and meshes, SAP produces topology-agnostic, watertight manifold surfaces. We demonstrate the effectiveness of SAP on the task of surface reconstruction from unoriented point clouds and learning-based reconstruction.
Author Profile Avatar
Author Profile Avatar
Author Profile Avatar
Paper Preview Page 1
22
Date Added: Jun 8, 2021
Authors: Fu, Bin, et al
Journal: Arxiv
Date Added: Jun 8, 2021
Authors: Fu, Bin, et al
Journal: Arxiv
Very recently, Window-based Transformers, which computed self-attention within non-overlapping local windows, demonstrated promising results on image classification, semantic segmentation, and object detection. However, less study has been devoted to the cross-window connection which is the key element to improve the representation ability. In this work, we revisit the spatial shuffle as an efficient way to build connections among windows. As a result, we propose a new vision transformer, named Shuffle Transformer, which is highly efficient and easy to implement by modifying two lines of code. Furthermore, the depth-wise convolution is introduced to complement the spatial shuffle for enhancing neighbor-window connections. The proposed architectures achieve excellent performance on a wide range of visual tasks including image-level classification, object detection, and semantic segmentation. Code will be released for reproduction.
Author Profile Avatar
Author Profile Avatar
Author Profile Avatar
Paper Preview Page 1
23
Date Added: Jun 8, 2021
Authors: William Chan, Daniel Watson, Jonathan Ho, Mohammad Norouzi, William Chan
Journal: Arxiv
Date Added: Jun 8, 2021
Authors: William Chan, Daniel Watson, Jonathan Ho, Mohammad Norouzi, William Chan
Journal: Arxiv
Denoising Diffusion Probabilistic Models (DDPMs) have emerged as a powerful family of generative models that can yield high-fidelity samples and competitive log-likelihoods across a range of domains, including image and speech synthesis. Key advantages of DDPMs include ease of training, in contrast to generative adversarial networks, and speed of generation, in contrast to autoregressive models. However, DDPMs typically require hundreds-to-thousands of steps to generate a high fidelity sample, making them prohibitively expensive for high dimensional problems. Fortunately, DDPMs allow trading generation speed for sample quality through adjusting the number of refinement steps as a post process. Prior work has been successful in improving generation speed through handcrafting the time schedule by trial and error. We instead view the selection of the inference time schedules as an optimization problem, and introduce an exact dynamic programming algorithm that finds the optimal discrete time schedules for any pre-trained DDPM. Our method exploits the fact that ELBO can be decomposed into separate KL terms, and given any computation budget, discovers the time schedule that maximizes the training ELBO exactly. Our method is efficient, has no hyper-parameters of its own, and can be applied to any pre-trained DDPM with no retraining. We discover inference time schedules requiring as few as 32 refinement steps, while sacrificing less than 0.1 bits per dimension compared to the default 4,000 steps used on ImageNet 64x64 [Ho et al., 2020; Nichol and Dhariwal, 2021].
Author Profile Avatar
Author Profile Avatar
Paper Preview Page 1
22
Date Added: Jun 10, 2021
Authors: Kolesnikov, Alexander, et al
Journal: Arxiv
Date Added: Jun 10, 2021
Authors: Kolesnikov, Alexander, et al
Journal: Arxiv
There is a growing discrepancy in computer vision between large-scale models that achieve state-of-the-art performance and models that are affordable in practical applications. In this paper we address this issue and significantly bridge the gap between these two types of models. Throughout our empirical investigation we do not aim to necessarily propose a new method, but strive to identify a robust and effective recipe for making state-of-the-art large scale models affordable in practice. We demonstrate that, when performed correctly, knowledge distillation can be a powerful tool for reducing the size of large models without compromising their performance. In particular, we uncover that there are certain implicit design choices, which may drastically affect the effectiveness of distillation. Our key contribution is the explicit identification of these design choices, which were not previously articulated in the literature. We back up our findings by a comprehensive empirical study, demonstrate compelling results on a wide range of vision datasets and, in particular, obtain a state-of-the-art ResNet-50 model for ImageNet, which achieves 82.8\% top-1 accuracy.
Paper Preview Page 1
21
Date Added: Jun 10, 2021
Authors: Mingxing Tan, Zihang Dai, Hanxiao Liu, Quoc Le, Mingxing Tan
Journal: Arxiv
Date Added: Jun 10, 2021
Authors: Mingxing Tan, Zihang Dai, Hanxiao Liu, Quoc Le, Mingxing Tan
Journal: Arxiv
Transformers have attracted increasing interests in computer vision, but they still fall behind state-of-the-art convolutional networks. In this work, we show that while Transformers tend to have larger model capacity, their generalization can be worse than convolutional networks due to the lack of the right inductive bias. To effectively combine the strengths from both architectures, we present CoAtNets(pronounced "coat" nets), a family of hybrid models built from two key insights:(1) depthwise Convolution and self-Attention can be naturally unified via simple relative attention; (2) vertically stacking convolution layers and attention layers in a principled way is surprisingly effective in improving generalization, capacity and efficiency. Experiments show that our CoAtNets achieve state-of-the-art performance under different resource constraints across various datasets. For example, CoAtNet achieves 86.0% ImageNet top-1 accuracy without extra data, and 89.77% with extra JFT data, outperforming prior arts of both convolutional networks and Transformers. Notably, when pre-trained with 13M images fromImageNet-21K, our CoAtNet achieves 88.56% top-1 accuracy, matching ViT-huge pre-trained with 300M images from JFT while using 23x less data.
Paper Preview Page 1
19
Date Added: Jun 8, 2021
Authors: Giovanni Colavizza, Giovanni Colavizza
Journal: Arxiv
Date Added: Jun 8, 2021
Authors: Giovanni Colavizza, Giovanni Colavizza
Journal: Arxiv
COVID-19 is having a dramatic impact on research and researchers. The pandemic has underlined the severity of known challenges in research and surfaced new ones, but also accelerated the adoption of innovations and manifested new opportunities. This review considers early trends emerging from meta-research on COVID-19. In particular, it focuses on the following topics: i) mapping COVID-19 research; ii) data and machine learning; iii) research practices including open access and open data, reviewing, publishing and funding; iv) communicating research to the public; v) the impact of COVID-19 on researchers, in particular with respect to gender and career trajectories. This overview finds that most early meta-research on COVID-19 has been reactive and focused on short-term questions, while more recently a shift to consider the long-term consequences of COVID-19 is taking place. Based on these findings, the author speculates that some aspects of doing research during COVID-19 are more likely to persist than others. These include: the shift to virtual for academic events such as conferences; the use of openly accessible pre-prints; the `datafication' of scholarly literature and consequent broader adoption of machine learning in science communication; the public visibility of research and researchers on social and online media.
Author Profile Avatar
Author Profile Avatar
Author Profile Avatar
Paper Preview Page 1
21
Date Added: Jun 8, 2021
Authors: Balaji Lakshminarayanan, Stanislav Fort, Jie Ren, Balaji Lakshminarayanan
Journal: Arxiv
Date Added: Jun 8, 2021
Authors: Balaji Lakshminarayanan, Stanislav Fort, Jie Ren, Balaji Lakshminarayanan
Journal: Arxiv
Near out-of-distribution detection (OOD) is a major challenge for deep neural networks. We demonstrate that large-scale pre-trained transformers can significantly improve the state-of-the-art (SOTA) on a range of near OOD tasks across different data modalities. For instance, on CIFAR-100 vs CIFAR-10 OOD detection, we improve the AUROC from 85% (current SOTA) to more than 96% using Vision Transformers pre-trained on ImageNet-21k. On a challenging genomics OOD detection benchmark, we improve the AUROC from 66% to 77% using transformers and unsupervised pre-training. To further improve performance, we explore the few-shot outlier exposure setting where a few examples from outlier classes may be available; we show that pre-trained transformers are particularly well-suited for outlier exposure, and that the AUROC of OOD detection on CIFAR-100 vs CIFAR-10 can be improved to 98.7% with just 1 image per OOD class, and 99.46% with 10 images per OOD class. For multi-modal image-text pre-trained transformers such as CLIP, we explore a new way of using just the names of outlier classes as a sole source of information without any accompanying images, and show that this outperforms previous SOTA on standard vision OOD benchmark tasks.
Author Profile Avatar
Paper Preview Page 1
16
Date Added: Jun 8, 2021
Authors: Rakotomamonjy, Alain, et al
Journal: Arxiv
Date Added: Jun 8, 2021
Authors: Rakotomamonjy, Alain, et al
Journal: Arxiv
Optical Processing Units (OPUs) -- low-power photonic chips dedicated to large scale random projections -- have been used in previous work to train deep neural networks using Direct Feedback Alignment (DFA), an effective alternative to backpropagation. Here, we demonstrate how to leverage the intrinsic noise of optical random projections to build a differentially private DFA mechanism, making OPUs a solution of choice to provide a private-by-design training. We provide a theoretical analysis of our adaptive privacy mechanism, carefully measuring how the noise of optical random projections propagates in the process and gives rise to provable Differential Privacy. Finally, we conduct experiments demonstrating the ability of our learning procedure to achieve solid end-task performance.
Author Profile Avatar
Author Profile Avatar
Author Profile Avatar
Paper Preview Page 1
14
Date Added: Jun 10, 2021
Authors: Maes, Pattie, et al
Journal: Arxiv
Date Added: Jun 10, 2021
Authors: Maes, Pattie, et al
Journal: Arxiv
Data-efficiency and generalization are key challenges in deep learning and deep reinforcement learning as many models are trained on large-scale, domain-specific, and expensive-to-label datasets. Self-supervised models trained on large-scale uncurated datasets have shown successful transfer to diverse settings. We investigate using pretrained image representations and spatio-temporal attention for state representation learning in Atari. We also explore fine-tuning pretrained representations with self-supervised techniques, i.e., contrastive predictive coding, spatio-temporal contrastive learning, and augmentations. Our results show that pretrained representations are at par with state-of-the-art self-supervised methods trained on domain-specific data. Pretrained representations, thus, yield data and compute-efficient state representations. https://github.com/PAL-ML/PEARL_v1
Paper Preview Page 1
Load More Papers