English
Related papers

Related papers: Instance-Conditional Timescales of Decay for Non-S…

200 papers

Classification tasks are usually evaluated in terms of accuracy. However, accuracy is discontinuous and cannot be directly optimized using gradient ascent. Popular methods minimize cross-entropy, hinge loss, or other surrogate losses, which…

Machine Learning · Computer Science 2024-07-25 Ivan Karpukhin , Stanislav Dereka , Sergey Kolesnikov

We propose a Dynamic Scale Training paradigm (abbreviated as DST) to mitigate scale variation challenge in object detection. Previous strategies like image pyramid, multi-scale training, and their variants are aiming at preparing…

Computer Vision and Pattern Recognition · Computer Science 2021-03-16 Yukang Chen , Peizhen Zhang , Zeming Li , Yanwei Li , Xiangyu Zhang , Lu Qi , Jian Sun , Jiaya Jia

Modern learning systems increasingly rely on amortized learning - the idea of reusing computation or inductive biases shared across tasks to enable rapid generalization to novel problems. This principle spans a range of approaches,…

Machine Learning · Computer Science 2025-10-14 Sarthak Mittal , Divyat Mahajan , Guillaume Lajoie , Mohammad Pezeshki

In class-incremental learning, the objective is to learn a number of classes sequentially without having access to the whole training data. However, due to a problem known as catastrophic forgetting, neural networks suffer substantial…

Machine Learning · Computer Science 2021-06-01 Sobirdzhon Bobiev , Adil Khan , Syed Muhammad Ahsan Raza Kazmi

The design of machines and algorithms capable of learning in a dynamically changing environment has become an increasingly topical problem with the increase of the size and heterogeneity of data available to learning systems. As a…

Computer Vision and Pattern Recognition · Computer Science 2022-05-02 Francesco Pelosin , Andrea Torsello

Class-incremental learning deals with sequential data streams composed of batches of classes. Various algorithms have been proposed to address the challenging case where samples from past classes cannot be stored. However, selecting an…

Machine Learning · Computer Science 2024-03-28 Eva Feillet , Adrian Popescu , Céline Hudelot

Efficient learning from demonstration for long-horizon tasks remains an open challenge in robotics. While significant effort has been directed toward learning trajectories, a recent resurgence of object-centric approaches has demonstrated…

Robotics · Computer Science 2025-12-01 Adrian Röfer , Russell Buchanan , Max Argus , Sethu Vijayakumar , Abhinav Valada

Fine-tuning pretrained models has become a standard approach to adapting pretrained knowledge to improve the accuracy on new sparse, imbalance datasets. However, issues arise when optimization falls into a collapsed state, where the model…

Machine Learning · Computer Science 2026-05-01 Nghia Bui , Lijing Wang

We propose continual instance learning - a method that applies the concept of continual learning to the task of distinguishing instances of the same object category. We specifically focus on the car object, and incrementally learn to…

Computer Vision and Pattern Recognition · Computer Science 2020-04-24 Kishan Parshotam , Mert Kilickaya

Data pruning, or instance selection, is an important problem in machine learning especially in terms of nearest neighbour classifier. However, in data pruning which speeds up the prediction phase, there is an issue related to the speed and…

Machine Learning · Computer Science 2025-01-22 Marcin Blachnik , Piotr Ciepliński

Visual object tracking performance has been dramatically improved in recent years, but some severe challenges remain open, like distractors and occlusions. We suspect the reason is that the feature representations of the tracking targets…

Computer Vision and Pattern Recognition · Computer Science 2021-10-29 Mengmeng Wang , Xiaoqian Yang , Yong Liu

In Continual learning (CL) balancing effective adaptation while combating catastrophic forgetting is a central challenge. Many of the recent best-performing methods utilize various forms of prior task data, e.g. a replay buffer, to tackle…

Machine Learning · Computer Science 2023-06-07 Nader Asadi , MohammadReza Davari , Sudhir Mudur , Rahaf Aljundi , Eugene Belilovsky

The training of modern machine learning models often consists in solving high-dimensional non-convex optimisation problems that are subject to large-scale data. In this context, momentum-based stochastic optimisation algorithms have become…

Optimization and Control · Mathematics 2024-11-06 Kexin Jin , Jonas Latz , Chenguang Liu , Alessandro Scagliotti

Robots and autonomous vehicles should be aware of what happens in their surroundings. The segmentation and tracking of moving objects are essential for reliable path planning, including collision avoidance. We investigate this estimation…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Matthias Zeller , Daniel Casado Herraez , Jens Behley , Michael Heidingsfeld , Cyrill Stachniss

Not all instances in a data set are equally beneficial for inferring a model of the data. Some instances (such as outliers) are detrimental to inferring a model of the data. Several machine learning techniques treat instances in a data set…

Machine Learning · Computer Science 2013-12-19 Michael R. Smith , Tony Martinez

Deep learning architectures have shown remarkable results in scene understanding problems, however they exhibit a critical drop of performances when they are required to learn incrementally new tasks without forgetting old ones. This…

Computer Vision and Pattern Recognition · Computer Science 2021-01-22 Umberto Michieli , Pietro Zanuttigh

We propose new continuous-time formulations for first-order stochastic optimization algorithms such as mini-batch gradient descent and variance-reduced methods. We exploit these continuous-time models, together with simple Lyapunov analysis…

Optimization and Control · Mathematics 2020-03-12 Antonio Orvieto , Aurelien Lucchi

In machine learning practice, early stopping has been widely used to regularize models and can save computational costs by halting the training process when the model's performance on a validation set stops improving. However, conventional…

Machine Learning · Computer Science 2025-02-12 Suqin Yuan , Runqi Lin , Lei Feng , Bo Han , Tongliang Liu

Modern statistical inference tasks often require iterative optimization methods to compute the solution. Convergence analysis from an optimization viewpoint only informs us how well the solution is approximated numerically but overlooks the…

Machine Learning · Statistics 2020-07-27 Tengyuan Liang , Weijie Su

The convergence of stochastic gradient descent is highly dependent on the step-size, especially on non-convex problems such as neural network training. Step decay step-size schedules (constant and then cut) are widely used in practice…

Optimization and Control · Mathematics 2021-02-19 Xiaoyu Wang , Sindri Magnússon , Mikael Johansson