首页/论文/2007.02693

arXiv 2007.026932020-07cs.CVcs.LGstat.ML

Auxiliary Learning by Implicit Differentiation

Bar-Ilan University（巴伊兰大学）；NVIDIA（英伟达）

Aviv Navon, Idan Achituve, Haggai Maron, Gal Chechik, Ethan Fetaya

备注：: Published at ICLR 2021

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Training neural networks with auxiliary tasks is a common practice for improving the performance on a main task of interest. Two main challenges arise in this multi-task learning setting: (i) designing useful auxiliary tasks; and (ii) combining auxiliary tasks into a single coherent loss. Here, we propose a novel framework, AuxiLearn, that targets both challenges based on implicit differentiation. First, when useful auxiliaries are known, we propose learning a network that combines all losses into a single coherent objective function. This network can learn non-linear interactions between tasks. Second, when no useful auxiliary task is known, we describe how to learn a network that generates a meaningful, novel auxiliary task. We evaluate AuxiLearn in a series of tasks and domains, including image segmentation and learning with attributes in the low data regime, and find that it consistently outperforms competing methods.

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

CGiS-Net: Aggregating Colour, Geometry and Implicit Semantic Features for Indoor Place Recognition

University of Bristol（布里斯托大学）；Zhejiang University（浙江大学）

We describe a novel approach to indoor place recognition from RGB point clouds based on aggregating low-level colour and geometry features with high-level implicit semantic features. It uses a 2-stage deep learning framework, in which the first stage is trained for the auxiliary task of semantic segmentation and the second stage uses features from layers in the first stage to generate discriminate descriptors for place recognition. The auxiliary task encourages the features to be semantically meaningful, hence aggregating the geometry and colour in the RGB point cloud data with implicit semant…

2022-07-11cs.CV

MINI: Mining Implicit Novel Instances for Few-Shot Object Detection

Shanghai AI Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）；SenseTime Research（商汤科技研究院）

Learning from a few training samples is a desirable ability of an object detector, inspiring the explorations of Few-Shot Object Detection (FSOD). Most existing approaches employ a pretrain-transfer paradigm. The model is first pre-trained on base classes with abundant data and then transferred to novel classes with a few annotated samples. Despite the substantial progress, the FSOD performance is still far behind satisfactory. During pre-training, due to the co-occurrence between base and novel classes, the model is learned to treat the co-occurred novel classes as backgrounds. During transfe…

2022-05-06cs.CV

A Unified Framework for Implicit Sinkhorn Differentiation

Technical University of Munich（慕尼黑工业大学）；University of Bonn（波恩大学）

The Sinkhorn operator has recently experienced a surge of popularity in computer vision and related fields. One major reason is its ease of integration into deep learning frameworks. To allow for an efficient training of respective neural networks, we propose an algorithm that obtains analytical gradients of a Sinkhorn layer via implicit differentiation. In comparison to prior work, our framework is based on the most general formulation of the Sinkhorn operator. It allows for any type of loss function, while both the target capacities and cost matrices are differentiated jointly. We further co…

2022-05-13cs.CV

Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiation

University of California, Berkeley（加州大学伯克利分校）；Princeton University（普林斯顿大学）

Iterative refinement -- start with a random guess, then iteratively improve the guess -- is a useful paradigm for representation learning because it offers a way to break symmetries among equally plausible explanations for the data. This property enables the application of such methods to infer representations of sets of entities, such as objects in physical scenes, structurally resembling clustering algorithms in latent space. However, most prior works differentiate through the unrolled refinement process, which can make optimization challenging. We observe that such methods can be made diffe…

2023-01-01cs.AIcs.CVcs.LG

AutoDO: Robust AutoAugment for Biased Data with Label Noise via Scalable Probabilistic Implicit Differentiation

Panasonic AI Lab（松下人工智能实验室）；AIoli Labs（AIoli实验室）；Panasonic Technology Division（松下技术部门）

AutoAugment has sparked an interest in automated augmentation methods for deep learning models. These methods estimate image transformation policies for train data that improve generalization to test data. While recent papers evolved in the direction of decreasing policy search complexity, we show that those methods are not robust when applied to biased and noisy data. To overcome these limitations, we reformulate AutoAugment as a generalized automated dataset optimization (AutoDO) task that minimizes the distribution shift between test data and distorted train dataset. In our AutoDO model, we…

2021-03-11cs.AIcs.CVcs.LG

局部子空间的隐式多维投影

Implicit Multidimensional Projection of Local Subspaces

Shandong University（山东大学）；Peking University（北京大学）；CNIC, CAS（中国科学院计算机网络信息中心）；University of Utah（犹他大学）；University of Stuttgart（斯图加特大学）

本研究提出一种基于隐函数微分的可视化方法，通过拟合多维椭圆分析局部子空间的形状与方向，结合网页可视化工具的交互功能，借助多类基准数据集验证了其在理解多维投影对局部子空间影响方面的有效性。

2023-07-20cs.CVcs.GRcs.LG

更多相关论文收起更多论文

基于隐式微分的鲁棒双视图几何估计

Robust Two-View Geometry Estimation with Implicit Differentiation

Skolkovo Institute of Science and Technology (Skoltech)（斯科尔科沃科学技术研究所（斯科尔泰克））；AI Foundation and Algorithm Lab（人工智能基金会与算法实验室）；MTS AI Group（MTS人工智能集团）

本文提出将鲁棒基础矩阵估计作为隐式层，并结合匹配置信度可学习权重，构建端到端可训练的双视图几何估计框架，在相机位姿估计任务上显著超越现有方法。

2024-10-23cs.CVcs.RO

Learning to Augment via Implicit Differentiation for Domain Generalization

University of Surrey（萨里大学）；Samsung AI Center（三星人工智能中心）；Nanyang Technological University（南洋理工大学）

Machine learning models are intrinsically vulnerable to domain shift between training and testing data, resulting in poor performance in novel domains. Domain generalization (DG) aims to overcome the problem by leveraging multiple source domains to learn a domain-generalizable model. In this paper, we propose a novel augmentation-based DG approach, dubbed AugLearn. Different from existing data augmentation methods, our AugLearn views a data augmentation module as hyper-parameters of a classification model and optimizes the module together with the model via meta-learning. Specifically, at each…

2022-10-25cs.CV

Re-basin via implicit Sinkhorn differentiation

École de Technologie Supérieure（高等技术学院）

The recent emergence of new algorithms for permuting models into functionally equivalent regions of the solution space has shed some light on the complexity of error surfaces, and some promising properties like mode connectivity. However, finding the right permutation is challenging, and current optimization techniques are not differentiable, which makes it difficult to integrate into a gradient-based optimization, and often leads to sub-optimal solutions. In this paper, we propose a Sinkhorn re-basin network with the ability to obtain the transportation plan that better suits a given objectiv…

2022-12-22cs.CV

IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation

ShanghaiTech University（上海科技大学）；Shanghai Advanced Research Institute, Chinese Academy of Sciences（中国科学院上海高等研究院）；University of Chinese Academy of Sciences（中国科学院大学）；Shanghai Engineering Research Center of Intelligent Vision and Imaging（上海智能视觉与成像工程技术研究中心）

This paper presents an inverse kinematic optimization layer (IKOL) for 3D human pose and shape estimation that leverages the strength of both optimization- and regression-based methods within an end-to-end framework. IKOL involves a nonconvex optimization that establishes an implicit mapping from an image's 3D keypoints and body shapes to the relative body-part rotations. The 3D keypoints and the body shapes are the inputs and the relative body-part rotations are the solutions. However, this procedure is implicit and hard to make differentiable. So, to overcome this issue, we designed a Gauss-…

2023-02-12cs.CV

SPIDE: A Purely Spike-based Method for Training Feedback Spiking Neural Networks

Peking University（北京大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）；Peng Cheng Laboratory（鹏城实验室）

Spiking neural networks (SNNs) with event-based computation are promising brain-inspired models for energy-efficient applications on neuromorphic hardware. However, most supervised SNN training methods, such as conversion from artificial neural networks or direct training with surrogate gradients, require complex computation rather than spike-based operations of spiking neurons during training. In this paper, we study spike-based implicit differentiation on the equilibrium state (SPIDE) that extends the recently proposed training method, implicit differentiation on the equilibrium state (IDE),…

2023-02-01cs.CVcs.LGcs.NE

透过玻璃观察：针对高镜面反射的神经表面重建

Looking Through the Glass: Neural Surface Reconstruction Against High Specular Reflections

Nankai University（南开大学）；Zhejiang University（浙江大学）

针对透过玻璃拍摄时高镜面反射破坏多视图一致性的问题，本文提出NeuS-HSR框架，通过将渲染图像分解为目标物体和辅助平面两种外观，并结合物理假设与神经网络，实现准确且鲁棒的神经隐式表面重建。

2023-04-18cs.CV

通过多模态数据和辅助任务集成优化皮肤病变分类

Optimizing Skin Lesion Classification via Multimodal Data and Auxiliary Task Integration

Indian Institute of Technology Jodhpur（印度理工学院焦特布尔分校）

本研究提出一种融合智能手机图像与临床信息的多模态皮肤病变分类方法，并引入超分辨率图像预测辅助任务以增强特征提取和类间区分，在PAD-UFES20数据集上的实验验证了其有效性和在资源不足环境中的适用性。

2024-02-16cs.CV