paper-with-me

Papers Incremental Learning

“Incremental Learning” 태그가 달린 논문 1,491편 · 필터 해제

Hyperbolic Geometry for Open-World Object Detection in Remote Sensing Imagery

2026-09-09 · Wuzhou Li, Jiawei Zhou, Shenghang Wang, Xiang Li arxiv

Open-world object detection (OWOD) extends closed-set detection by requiring models to identify unknown objects and incrementally learn them once annotations become available. In remote sensing imagery, object categories…

Incremental LearningObject DetectionMetric Learning

In Two Minds about Lifelong Learning: Exploring Hemispheric Redundancy and Specialisation in Neural Models

2026-08-20 · Benjamin Smith, Levin Kuhlmann, Kaushik Roy, Gideon Kowadlo arxiv

Persistent intelligent systems require the ability to learn continually, but current machine learning approaches face significant challenges in this area compared to biological learning systems. Machine learning algorith…

Incremental LearningContinual Learning

STAIL: Semantic Text-Anchored Incremental Learning for Medical Imaging via Large Language Models

2026-08-06 · Songpan Gao, Yajie Zhang, Guanxing Chen, Jiayu Qian 외 arxiv

Deep learning models applied to medical image analysis suffer from severe catastrophic forgetting when continually adapting to new clinical tasks in dynamic environments. Mainstream incremental learning methods typically…

Incremental Learning

Relative Parameter Importance in Task-Agnostic Replay-Free Continual Learning

2026-08-01 · Malavika Suresh, Ikechukwu Nkisi-Orji, Nirmalie Wiratunga arxiv

Achieving continual learning (CL) with deep neural networks requires balancing stability and plasticity while enabling knowledge transfer. In this work, we focus on offline learning algorithms under the constraints: (I) …

Incremental LearningText ClassificationContinual LearningText Generation

Compactly supported radial basis functions as probability density functions

2026-07-29 · Sergio Díaz-Elbal, Andrei Martínez-Finkelshtein, Darío Ramos-López arxiv

Compactly Supported Radial Basis Functions (CS-RBFs) are a fundamental tool in multivariate approximation theory. However, their use in statistics and probability modeling remains underexplored, having been used mainly t…

Incremental LearningGaussian ProcessesDensity Estimation

Online Variance Reduction for Domain Adaptation on Streaming Data

2026-07-22 · Andrea Napoli arxiv

This paper studies the problem of stochastic variance reduction (SVR) for the maximum mean discrepancy (MMD) and correlation alignment (CORAL) loss functions. Although various offline SVR algorithms for these losses have…

Incremental LearningDomain Adaptation

Few-Shot Domain Incremental Learning via Continual Vision-Language Consolidation

2026-06-29 · Naeem Paeedeh, Mahardhika Pratama, Wolfgang Mayer, Mukesh Prasad 외 arxiv

Existing domain-incremental learning (DIL) strategies call for massive amounts of data to adapt to new domains and suffer from the overfitting problem in the case of data scarcity. This paper puts forward a relatively un…

parameter-efficient fine-tuningIncremental LearningGeneral Knowledge

Transformer-Based Active Learning for Data-Efficient Vaccine Epitope Selection in PRRS

2026-06-27 · Aspen Erlandsson Brisebois, Zahed Khatooni, Connor Burbridge, Brook Byrns 외 arxiv

High-fidelity molecular docking simulations can produce biologically relevant estimates of epitope-receptor binding affinity but are computationally expensive and therefore limit the number of candidates that can be scre…

Hyperparameter OptimizationIncremental LearningActive Learning

Domain-incremental audio classification using domain-specific experts and prototype classifier

2026-06-22 · Jongyeon Park, Do-Hyeon Lim, Sang-won Park, Hong Kook Kim 외 arxiv

This technical report presents submission systems for Task 7(domain-incremental audio classification) of the DCASE 2026 Challenge. The main obstacle is that, the system is unable to access to past or future domain's data…

Incremental LearningAudio Classification

Incremental Learning in Mirror Flows

2026-06-22 · Raphaël Berthier, Loucas Pillaud-Vivien arxiv

We study mirror flows generated by a convex quadratic loss and a general convex lower semicontinuous mirror potential. We show that, when initialized near the boundary of the domain of the mirror potential, their rescale…

Incremental Learning

C^2GR: Coupled Comprehensive Generative Replay for a Continually Learnable Universal Segmentation Model

2026-06-22 · Wei Li, Jingyang Zhang, Guoan Wang, Junzhi Ning 외 arxiv

Universal segmentation models exhibit significant potential for diverse tasks involving different imaging modalities and segmentation objectives. Task-Incremental Learning provides a privacy-preserving approach to contin…

Incremental Learning

Fast and Slow Variational Continual Learning

2026-06-22 · Subarnaduti Paul, Yohan Jung, Mohammad Emtiyaz Khan, Siddharth Swaroop 외 arxiv

Continual learning remains a major challenge for modern deep networks, partly because commonly used optimizers lack inherent mechanisms for continual adaptation. One such natural mechanism is fast and slow adaptation to …

Incremental LearningContinual Learning

Physics-Informed Domain-Invariant Feature Learning with Autoencoder-Driven Gaussian Clustering for Robust Non-line-of-Sight Scenarios

2026-06-21 · Nisha L. Raichur, Lucas Heublein, Dominik Seuß, Frank Deinzer 외 arxiv

Jamming and spoofing pose significant threats to wireless and satellite navigation by disrupting radio-frequency (RF) signals and compromising availability and integrity. Robust RF interference direction finding through …

Domain GeneralizationIncremental Learning

CoRDE: Concept-Prior Routed Diffusion Experts for Structural Generalization in Robot Manipulation

2026-06-20 · Haidong Huang, Xixin Zhao, Yaohua Zhou, Jiayu Song 외 arxiv

Diffusion models excel at capturing multi-modal action distributions in robot imitation learning. However, in multi-task and long-horizon scenarios, monolithic architectures lack structural generalization capabilities, s…

Incremental LearningRobot Manipulation

Task-Differentiated Atomic Skill Expansion and Routing for Continual Learning Across Highly Heterogeneous Tasks

2026-06-19 · Jiacheng Wang, Xinjia He, Qi Ding, Yutao Yang 외 arxiv

Continual learning (CL) is commonly studied under the assumption that sequential tasks are semantically related or structurally similar. However, in highly heterogeneous settings, where tasks differ substantially in reas…

Incremental LearningContinual Learning

Focus, Align, and Sustain: Counteracting Gradient Dilution in Incremental Object Detection

2026-06-13 · Aoting Zhang, Dongbao Yang, Chang Liu, Xiaopeng Hong 외 arxiv

Adapting Detection Transformers to Incremental Object Detection (IOD) poses a systemic challenge, as set-based optimization is inherently destabilized by sequential learning. In this work, we identify Gradient Dilution a…

Incremental LearningObject Detection

ECA: Efficient Continual Alignment for Open-Ended Image-to-Text Generation

2026-06-10 · Jiangtao Kong, Peijun Zhao, Chun-Fu Chen, Youngwook Do 외 arxiv

Incremental Learning (IL) for Open-ended Image-to-Text Generation (OpenITG) enables models to continuously generate accurate, contextually relevant text for new images while preserving previously acquired knowledge. Unli…

Incremental LearningText Generation

OLIVE: Online Low-Rank Incremental Learning for Efficient Adaptive Exoskeletons

2026-06-03 · Dong Liu, Yanxuan Yu, Ben Lengerich, Tony Geng 외 arxiv

Wearable exoskeleton systems hold promise for restoring mobility in individuals with physical impairments, yet most existing controllers rely on static gait policies that cannot adapt to dynamic real-world environments o…

Incremental Learning

Weakly Supervised Incremental Segmentation via Semantic Anchors and Spatial Arbitration

2026-06-02 · Zhonggai Wang, Kai Fang, Guangyu Gao arxiv

Weakly Incremental Learning for Semantic Segmentation (WILSS) suffers from the continuous introduction of noisy supervision, which progressively corrupts class-level representations, leading to severe feature drift and s…

Semantic SegmentationIncremental Learning

Remembering by Reconstructing: Domain Incremental Learning With Test-Time Training on Video Streams

2026-05-29 · Jonathan Swinnen, Tinne Tuytelaars arxiv

In this work we introduce a novel approach to domain incremental learning, adapting models over time to evolving, non-stationary data. In contrast to other works, we do not attempt to avoid catastrophic forgetting, but r…

Semantic SegmentationIncremental LearningAction Recognition
1–20 / 1,491 다음 →