HCV: Hierarchy-Consistency Verification for Incremental Implicitly-Refined Classification

2021-10-21 · Kai Wang, Xialei Liu, Luis Herranz, Joost Van de Weijer

Human beings learn and accumulate hierarchical knowledge over their lifetime. This knowledge is associated with previous concepts for consolidation and hierarchical construction. However, current incremental learning methods lack the ability to build a concept hierarchy by associating new concepts to old ones. A more realistic setting tackling this problem is referred to as Incremental Implicitly-Refined Classification (IIRC), which simulates the recognition process from coarse-grained categories to fine-grained categories. To overcome forgetting in this benchmark, we propose Hierarchy-Consistency Verification (HCV) as an enhancement to existing continual learning methods. Our method incrementally discovers the hierarchical relations between classes. We then show how this knowledge can be exploited during both training and inference. Experiments on three setups of varying difficulty demonstrate that our HCV module improves performance of existing continual learning methods under this IIRC setting by a large margin. Code is available in https://github.com/wangkai930418/HCV_IIRC.

📄 PDF Abstract BibTeX arXiv:2110.11148

Code (1)

wangkai930418/hcv_iirc 공식 구현 pytorch

Tasks

Classification Continual Learning Incremental Learning

Multi-Teacher Knowledge Distillation for Incremental Implicitly-Refined Classification

2022-02-23 · Longhui Yu, Zhenyu Weng, Yuqing Wang, Yuesheng Zhu

Incremental learning methods can learn new classes continually by distilling knowledge from the last model (as a teacher model) to the current model (as a student model) in the sequentially learning process. However, the…

Classification Incremental Learning Knowledge Distillation

IIRC: Incremental Implicitly-Refined Classification

2020-12-23 · CVPR 2021 1 · Mohamed Abdelsalam, Mojtaba Faramarzi, Shagun Sodhani, Sarath Chandar

We introduce the "Incremental Implicitly-Refined Classi-fication (IIRC)" setup, an extension to the class incremental learning setup where the incoming batches of classes have two granularity levels. i.e., each sample co…

Classification class-incremental learning Class Incremental Learning General Classification+2

Incremental Neural Network Verification via Learned Conflicts

2026-03-12 · Raya Elsaleh, Liam Davis, Haoze Wu, Guy Katz arxiv

Neural network verification is often used as a core component within larger analysis procedures, which generate sequences of closely related verification queries over the same network. In existing neural network verifier…

Multi-Model Hypothesize-and-Verify Approach for Incremental Loop Closure Verification

2016-08-06 · Kanji Tanaka

Loop closure detection, which is the task of identifying locations revisited by a robot in a sequence of odometry and perceptual observations, is typically formulated as a visual place recognition (VPR) task. However, ev…

Loop Closure Detection Robot Navigation Visual Odometry Visual Place Recognition

CorridorVLA: Explicit Spatial Constraints for Generative Action Heads via Sparse Anchors

2026-04-23 · Dachong Li, ZhuangZhuang Chen, Jin Zhang, Jianqiang Li arxiv

Vision--Language--Action (VLA) models often use intermediate representations to connect multimodal inputs with continuous control, yet spatial guidance is often injected implicitly through latent features. We propose Cor…

Continuous Control