English
Related papers

Related papers: Rethinking Spatially-Adaptive Normalization

200 papers

Learning visual features from unlabeled image data is an important yet challenging task, which is often achieved by training a model on some annotation-free information. We consider spatial contexts, for which we solve so-called jigsaw…

Computer Vision and Pattern Recognition · Computer Science 2018-12-04 Chen Wei , Lingxi Xie , Xutong Ren , Yingda Xia , Chi Su , Jiaying Liu , Qi Tian , Alan L. Yuille

Deep neural networks often require copious amount of labeled-data to train their scads of parameters. Training larger and deeper networks is hard without appropriate regularization, particularly while using a small dataset. Laterally,…

Computer Vision and Pattern Recognition · Computer Science 2019-05-31 Xiang Xu , Xiong Zhou , Ragav Venkatesan , Gurumurthy Swaminathan , Orchid Majumder

This paper presents a new supervised representation learning framework, namely structured probabilistic coding (SPC), to learn compact and informative representations from input related to the target task. SPC is an encoder-only…

Computation and Language · Computer Science 2024-05-03 Dou Hu , Lingwei Wei , Yaxin Liu , Wei Zhou , Songlin Hu

Semi-supervised domain adaptation (SSDA), which aims to learn models in a partially labeled target domain with the assistance of the fully labeled source domain, attracts increasing attention in recent years. To explicitly leverage the…

Computer Vision and Pattern Recognition · Computer Science 2021-01-06 Qijun Luo , Zhili Liu , Lanqing Hong , Chongxuan Li , Kuo Yang , Liyuan Wang , Fengwei Zhou , Guilin Li , Zhenguo Li , Jun Zhu

Sorted $\ell_1$ Penalized Estimator (SLOPE) is a relatively new convex regularization method for fitting high-dimensional regression models. SLOPE allows to reduce the model dimension by shrinking some estimates of the regression…

Statistics Theory · Mathematics 2022-06-17 Tomasz Skalski , Piotr Graczyk , Bartosz Kołodziejek , Maciej Wilczyński

The problem of keyword spotting i.e. identifying keywords in a real-time audio stream is mainly solved by applying a neural network over successive sliding windows. Due to the difficulty of the task, baseline models are usually large,…

Machine Learning · Computer Science 2018-11-19 Tom Véniat , Olivier Schwander , Ludovic Denoyer

Domain adaptation (DA) is a representation learning methodology that transfers knowledge from a label-sufficient source domain to a label-scarce target domain. While most of early methods are focused on unsupervised DA (UDA), several…

Computer Vision and Pattern Recognition · Computer Science 2021-04-02 Yoonhyung Kim , Changick Kim

For best performance, today's semantic segmentation methods use large and carefully labeled datasets, requiring expensive annotation budgets. In this work, we show that coarse annotation is a low-cost but highly effective alternative for…

Computer Vision and Pattern Recognition · Computer Science 2022-12-16 Anurag Das , Yongqin Xian , Yang He , Zeynep Akata , Bernt Schiele

Sharpness-Aware Minimization (SAM) has emerged as a powerful method for improving generalization in machine learning models by minimizing the sharpness of the loss landscape. However, despite its success, several important questions…

Optimization and Control · Mathematics 2025-03-05 Dimitris Oikonomou , Nicolas Loizou

Few-shot image classification requires the classifier to robustly cope with unseen classes even if there are only a few samples for each class. Recent advances benefit from the meta-learning process where episodic tasks are formed to train…

Computer Vision and Pattern Recognition · Computer Science 2020-03-10 Da Chen , Yongliang Yang , Zunlei Feng , Xiang Wu , Mingli Song , Wenbin Li , Yuan He , Hui Xue , Feng Mao

Neural Laplace is a unified framework for learning diverse classes of differential equations (DE). For different classes of DE, this framework outperforms other approaches relying on neural networks that aim to learn classes of ordinary…

Machine Learning · Computer Science 2024-06-10 Adrien Carrel

Real-noise denoising is a challenging task because the statistics of real-noise do not follow the normal distribution, and they are also spatially and temporally changing. In order to cope with various and complex real-noise, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2020-03-17 Yoonsik Kim , Jae Woong Soh , Gu Yong Park , Nam Ik Cho

Despite the successes of deep neural networks on many challenging vision tasks, they often fail to generalize to new test domains that are not distributed identically to the training data. The domain adaptation becomes more challenging for…

Computer Vision and Pattern Recognition · Computer Science 2021-03-08 Devavrat Tomar , Manana Lortkipanidze , Guillaume Vray , Behzad Bozorgtabar , Jean-Philippe Thiran

In neural Information Retrieval (IR), ongoing research is directed towards improving the first retriever in ranking pipelines. Learning dense embeddings to conduct retrieval using efficient approximate nearest neighbors methods has proven…

Information Retrieval · Computer Science 2021-09-22 Thibault Formal , Carlos Lassance , Benjamin Piwowarski , Stéphane Clinchant

Learning generalized representations from limited training samples is crucial for applying deep neural networks in low-resource scenarios. Recently, methods based on Contrastive Language-Image Pre-training (CLIP) have exhibited promising…

Computer Vision and Pattern Recognition · Computer Science 2023-12-08 Yao Zhu , Yuefeng Chen , Wei Wang , Xiaofeng Mao , Xiu Yan , Yue Wang , Zhigang Li , Wang lu , Jindong Wang , Xiangyang Ji

In this paper, we propose SPACE, a novel anomaly detection methodology that integrates a Feature Encoder (FE) into the structure of the Student-Teacher method. The proposed method has two key elements: Spatial Consistency regularization…

Computer Vision and Pattern Recognition · Computer Science 2024-11-12 Daehwan Kim , Hyungmin Kim , Daun Jeong , Sungho Suh , Hansang Cho

Contrastive language--audio pretraining (CLAP) has achieved remarkable success as an audio--text embedding framework, but existing approaches are limited to monaural or single-source conditions and cannot fully capture spatial information.…

Transformer-based large-scale pre-trained models achieve great success. Fine-tuning is the standard practice for leveraging these models in downstream tasks. Among the fine-tuning methods, adapter-tuning provides a parameter-efficient…

Computation and Language · Computer Science 2025-05-16 Hyegang Son , Yonglak Son , Changhoon Kim , Young Geun Kim

The Latent Stochastic Differential Equation (SDE) is a powerful tool for time series and sequence modeling. However, training Latent SDEs typically relies on adjoint sensitivity methods, which depend on simulation and backpropagation…

Machine Learning · Statistics 2025-06-27 Grigory Bartosh , Dmitry Vetrov , Christian A. Naesseth

Implicit neural representations are powerful for geometric modeling, but their practical use is often limited by the high computational cost of network evaluations. We observe that implicit representations require progressively lower…

Graphics · Computer Science 2026-04-30 Chuanxiang Yang , Junhui Hou , Yuan Liu , Siyu Ren , Guangshun Wei , Taku Komura , Yuanfeng Zhou , Wenping Wang