TL;DR
Anchored Generative Replay (AGR) is proposed, a framework that combines training-only anchoring-mode selection, prompt–key learning, relation-level distribution modeling, and balanced pseudo-feature replay to solve the problem of severe forgetting in FSCRE.
TAILS resolves cross-task ambiguity at the representation level, while leaving the original PTM, method-specific modules, and classifier unchanged, and can improve classification and task-inference performance with modest parameter overhead and negligible inference cost.
Hierarchical Response Preservation (HiRP) is proposed, a hierarchical response that keeps each historical-class probability and sums new-class probabilities, preserving historical distinctions and aggregate competition while allowing distinctions within the new class group to adapt.
LiDAR place recognition (LPR) supports long-term localization and loop closure, yet models deployed in changing environments must learn new places without forgetting previous ones. Fine-tuning adapts effectively but degrades performance on earlier domains, while existing continual LPR methods typically require memory r...
This work introduces DR.WILSS, an innovative approach to address catastrophic forgetting in continual learning using diffusion-based generative replay, which leverages language clues to guide the diffusion process, employing self-inpainting and regularization techniques to efficiently produce replay data, aiding the le...
This work proposes OCAAD, an Object-Centric Alignment and Anchor Distillation framework, and introduces two complementary modules that bridges the semantic gap between anchors and objects by transferring object-level knowledge from attention heads to anchors via overlap-aware contrastive learning.
Frequency-Decoupled Cross-Attention Knowledge Distillation (FD-CanKD) is presented as a detector-oriented framework that transfers teacher knowledge at three complementary levels: head-level prediction supervision, relation-level non-local context transfer, and frequency-level component-selective alignment.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
