paper-with-me

홈 › Papers

FDCNet: Feature Drift Compensation Network for Class-Incremental Weakly Supervised Object Localization

2023-09-17 · Sejin Park, Taehyung Lee, Yeejin Lee, Byeongkeun Kang

This work addresses the task of class-incremental weakly supervised object localization (CI-WSOL). The goal is to incrementally learn object localization for novel classes using only image-level annotations while retaining the ability to localize previously learned classes. This task is important because annotating bounding boxes for every new incoming data is expensive, although object localization is crucial in various applications. To the best of our knowledge, we are the first to address this task. Thus, we first present a strong baseline method for CI-WSOL by adapting the strategies of class-incremental classifiers to mitigate catastrophic forgetting. These strategies include applying knowledge distillation, maintaining a small data set from previous tasks, and using cosine normalization. We then propose the feature drift compensation network to compensate for the effects of feature drifts on class scores and localization maps. Since updating network parameters to learn new tasks causes feature drifts, compensating for the final outputs is necessary. Finally, we evaluate our proposed method by conducting experiments on two publicly available datasets (ImageNet-100 and CUB-200). The experimental results demonstrate that the proposed method outperforms other baseline methods.

📄 PDF Abstract BibTeX arXiv:2309.09122

Code (1)

Vision-sejin/FDCNet 공식 구현 pytorch

Tasks

class-incremental learningIncremental LearningKnowledge DistillationObjectObject LocalizationWeakly-Supervised Object Localization

Similar Papers 제목 키워드 기반

Dual Compensation Residual Networks for Class Imbalanced Learning

2023-08-25 · Ruibing Hou, Hong Chang, Bingpeng Ma, Shiguang Shan 외

Learning generalizable representation and classifier for class-imbalanced data is challenging for data-driven deep models. Most studies attempt to re-balance the data distribution, which is prone to overfitting on tail c…

Exemplar-free Continual Representation Learning via Learnable Drift Compensation

2024-07-11 · Alex Gomez-Villa, Dipam Goswami, Kai Wang, Andrew D. Bagdanov 외

Exemplar-free class-incremental learning using a backbone trained from scratch and starting from a small first task presents a significant challenge for continual representation learning. Prototype-based approaches, when…

class-incremental learningClass Incremental LearningContinual LearningExemplar-Free+2

Exemplar-free Continual Learning of Vision Transformers via Gated Class-Attention and Cascaded Feature Drift Compensation

2022-11-22 · Marco Cotogni, Fei Yang, Claudio Cusano, Andrew D. Bagdanov 외

We propose a new method for exemplar-free class incremental training of ViTs. The main challenge of exemplar-free continual learning is maintaining plasticity of the learner without causing catastrophic forgetting of pre…

Continual LearningExemplar-Free

PTMs-TSCIL Pre-Trained Models Based Class-Incremental Learning

2025-03-10 · Yuanlong Wu, Mingxing Nie, Tao Zhu, Liming Chen 외

Class-incremental learning (CIL) for time series data faces critical challenges in balancing stability against catastrophic forgetting and plasticity for new knowledge acquisition, particularly under real-world constrain…

class-incremental learningClass Incremental LearningContinual LearningIncremental Learning+2

Data-Free Reservoir Features for Efficient Long-Horizon Cold-Start Continual Learning

2026-06-25 · Augustinas Jučas, Yangchen Pan arxiv

Cold-start exemplar-free class-incremental learning requires learning a growing set of classes without replay, external pretraining, or a large initial task. Existing cold-start methods typically either train the backbon…

class-incremental learningImage ClassificationContinual Learning