首页/论文/2005.12563

arXiv 2005.125632020-05-26cs.CV

Learning to map between ferns with differentiable binary embedding networks

Institute of Medical Informatics, Universität zu Lübeck（吕贝克大学医学信息学研究所）

Max Blendowski, Mattias P. Heinrich

英文摘要：

Current deep learning methods are based on the repeated, expensive application of convolutions with parameter-intensive weight matrices. In this work, we present a novel concept that enables the application of differentiable random ferns in end-to-end networks. It can then be used as multiplication-free convolutional layer alternative in deep network architectures. Our experiments on the binary classification task of the TUPAC'16 challenge demonstrate improved results over the state-of-the-art binary XNOR net and only slightly worse performance than its 2x more parameter intensive floating point CNN counterpart.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

像素嵌入：具有可微查找表的完全量化卷积神经网络

Pixel Embedding: Fully Quantized Convolutional Neural Network with Differentiable Lookup Table

LeapMind Inc.（LeapMind公司）；Woven by Toyota, Inc.（丰田旗下Woven公司）；Mirai Hoshu K.K.（Mirai Hoshu株式会社）

提出像素嵌入方法，通过可微查找表将输入像素替换为低比特向量，实现完全量化神经网络，在ImageNet和CIFAR-100上显著降低量化误差并加速推理。

2024-07-23cs.AIcs.CVcs.LG

Cherry-Picking Gradients: Learning Low-Rank Embeddings of Visual Data via Differentiable Cross-Approximation

ETH Zürich（苏黎世联邦理工学院）；IE University（IE大学）；HSE University（俄罗斯高等经济学院）

We propose an end-to-end trainable framework that processes large-scale visual data tensors by looking at a fraction of their entries only. Our method combines a neural network encoder with a tensor train decomposition to learn a low-rank latent encoding, coupled with cross-approximation (CA) to learn the representation through a subset of the original samples. CA is an adaptive sampling algorithm that is native to tensor decompositions and avoids working with the full high-resolution data explicitly. Instead, it actively selects local representative samples that we fetch out-of-core and on-de…

2021-11-12cs.CVcs.LG

Learning Deep Embeddings with Histogram Loss

Skolkovo Institute of Science and Technology（斯科尔科沃科学技术学院）

We suggest a loss for learning deep embeddings. The new loss does not introduce parameters that need to be tuned and results in very good embeddings across a range of datasets and problems. The loss is computed by estimating two distribution of similarities for positive (matching) and negative (non-matching) sample pairs, and then computing the probability of a positive pair to have a lower similarity score than a negative pair based on the estimated similarity distributions. We show that such operations can be performed in a simple and piecewise-differentiable manner using 1D histograms with …

2016-11-02cs.CV

Recurrent Pixel Embedding for Instance Grouping

University of California, Irvine（加州大学欧文分校）

We introduce a differentiable, end-to-end trainable framework for solving pixel-level grouping problems such as instance segmentation consisting of two novel components. First, we regress pixels into a hyper-spherical embedding space so that pixels from the same group have high cosine similarity while those from different groups have similarity below a specified margin. We analyze the choice of embedding dimension and margin, relating them to theoretical results on the problem of distributing points uniformly on the sphere. Second, to group instances, we utilize a variant of mean-shift cluster…

2017-12-22cs.CVcs.LGcs.MM

Deep Metric Learning with BIER: Boosting Independent Embeddings Robustly

Graz University of Technology（格拉茨技术大学）

Learning similarity functions between image pairs with deep neural networks yields highly correlated activations of embeddings. In this work, we show how to improve the robustness of such embeddings by exploiting the independence within ensembles. To this end, we divide the last embedding layer of a deep network into an embedding ensemble and formulate training this ensemble as an online gradient boosting problem. Each learner receives a reweighted training sample from the previous learners. Further, we propose two loss functions which increase the diversity in our ensemble. These loss functio…

2018-01-15cs.CV

Differentiable Mapping Networks: Learning Structured Map Representations for Sparse Visual Localization

Google（谷歌）；National University of Singapore（新加坡国立大学）

Mapping and localization, preferably from a small number of observations, are fundamental tasks in robotics. We address these tasks by combining spatial structure (differentiable mapping) and end-to-end learning in a novel neural network architecture: the Differentiable Mapping Network (DMN). The DMN constructs a spatially structured view-embedding map and uses it for subsequent visual localization with a particle filter. Since the DMN architecture is end-to-end differentiable, we can jointly learn the map representation and localization using gradient descent. We apply the DMN to sparse visua…

2020-05-19cs.CVcs.LGcs.RO

更多相关论文收起更多论文

Learning Surrogates via Deep Embedding

Czech Technical University in Prague（布拉格捷克理工大学）

This paper proposes a technique for training a neural network by minimizing a surrogate loss that approximates the target evaluation metric, which may be non-differentiable. The surrogate is learned via a deep embedding where the Euclidean distance between the prediction and the ground truth corresponds to the value of the evaluation metric. The effectiveness of the proposed technique is demonstrated in a post-tuning setup, where a trained model is tuned using the learned surrogate. Without a significant computational overhead and any bells and whistles, improvements are demonstrated on challe…

2020-07-17cs.CV

Learning Combinatorial Embedding Networks for Deep Graph Matching

Shanghai Jiao Tong University（上海交通大学）

Graph matching refers to finding node correspondence between graphs, such that the corresponding node and edge's affinity can be maximized. In addition with its NP-completeness nature, another important challenge is effective modeling of the node-wise and structure-wise affinity across graphs and the resulting objective, to guide the matching procedure effectively finding the true matching against noises. To this end, this paper devises an end-to-end differentiable deep network pipeline to learn the affinity for graph matching. It involves a supervised permutation loss regarding with node corr…

2019-09-26cs.CV

Towards real-world navigation with deep differentiable planners

Visual Geometry Group（视觉几何组）；University of Oxford（牛津大学）

We train embodied neural networks to plan and navigate unseen complex 3D environments, emphasising real-world deployment. Rather than requiring prior knowledge of the agent or environment, the planner learns to model the state transitions and rewards. To avoid the potentially hazardous trial-and-error of reinforcement learning, we focus on differentiable planners such as Value Iteration Networks (VIN), which are trained offline from safe expert demonstrations. Although they work well in small simulations, we address two major limitations that hinder their deployment. First, we observed that cu…

2022-06-02cs.AIcs.CVcs.LG

Temporal Cycle-Consistency Learning

Google Brain（谷歌大脑）；DeepMind（深度思考（DeepMind））

We introduce a self-supervised representation learning method based on the task of temporal alignment between videos. The method trains a network using temporal cycle consistency (TCC), a differentiable cycle-consistency loss that can be used to find correspondences across time in multiple videos. The resulting per-frame embeddings can be used to align videos by simply matching frames using the nearest-neighbors in the learned embedding space. To evaluate the power of the embeddings, we densely label the Pouring and Penn Action video datasets for action phases. We show that (i) the learned emb…

2019-04-16cs.CVcs.LG

轮廓损失：深度表示的可微全局结构学习

Silhouette Loss: Differentiable Global Structure Learning for Deep Representations

本文提出Soft Silhouette Loss，通过全局结构学习提升深度表示的判别性，结合交叉熵和对比学习，实验证明其在多个数据集上有效提升性能且计算开销低。

2026-03-27cs.AIcs.CVcs.LG

Smooth Variational Graph Embeddings for Efficient Neural Architecture Search

University of Mannheim（曼海姆大学）；University of Freiburg（弗莱堡大学）；Bosch Center for Artificial Intelligence（博世人工智能中心）

Neural architecture search (NAS) has recently been addressed from various directions, including discrete, sampling-based methods and efficient differentiable approaches. While the former are notoriously expensive, the latter suffer from imposing strong constraints on the search space. Architecture optimization from a learned embedding space for example through graph neural network based variational autoencoders builds a middle ground and leverages advantages from both sides. Such approaches have recently shown good performance on several benchmarks. Yet, their stability and predictive power he…

2021-05-12cs.AIcs.CVcs.LG

Distortion Agnostic Deep Watermarking

Google Research（谷歌研究院）；Stanford University（斯坦福大学）

Watermarking is the process of embedding information into an image that can survive under distortions, while requiring the encoded image to have little or no perceptual difference from the original image. Recently, deep learning-based methods achieved impressive results in both visual quality and message payload under a wide variety of image distortions. However, these methods all require differentiable models for the image distortions at training time, and may generalize poorly to unknown distortions. This is undesirable since the types of distortions applied to watermarked images are usually…

2020-01-14cs.CVcs.LGcs.MM

Deep 3D-to-2D Watermarking: Embedding Messages in 3D Meshes and Extracting Them from 2D Renderings

Google Research（谷歌研究院）；Google LLC（谷歌有限责任公司）；Microsoft Azure AI（微软Azure人工智能部门）

Digital watermarking is widely used for copyright protection. Traditional 3D watermarking approaches or commercial software are typically designed to embed messages into 3D meshes, and later retrieve the messages directly from distorted/undistorted watermarked 3D meshes. However, in many cases, users only have access to rendered 2D images instead of 3D meshes. Unfortunately, retrieving messages from 2D renderings of 3D meshes is still challenging and underexplored. We introduce a novel end-to-end learning framework to solve this problem through: 1) an encoder to covertly embed messages in both…

2022-03-29cs.CRcs.CVcs.LG