paper-with-me

Papers

I2I: Initializing Adapters with Improvised Knowledge

2023-04-04 · Tejas Srinivasan, Furong Jia, Mohammad Rostami, Jesse Thomason

Adapters present a promising solution to the catastrophic forgetting problem in continual learning. However, training independent Adapter modules for every new task misses an opportunity for cross-task knowledge transfer. We propose Improvise to Initialize (I2I), a continual learning algorithm that initializes Adapters for incoming tasks by distilling knowledge from previously-learned tasks' Adapters. We evaluate I2I on CLiMB, a multimodal continual learning benchmark, by conducting experiments on sequences of visual question answering tasks. Adapters trained with I2I consistently achieve better task accuracy than independently-trained Adapters, demonstrating that our algorithm facilitates knowledge transfer between task Adapters. I2I also results in better cross-task knowledge transfer than the state-of-the-art AdapterFusion without incurring the associated parametric cost.

📄 PDF Abstract BibTeX arXiv:2304.02168

Code (1)

glamor-usc/climb 공식 구현 pytorch

Tasks

Continual LearningQuestion AnsweringTransfer LearningVisual Question Answering

Methods 이 논문이 사용한 방법론

Adapter 설명 없음

Similar Papers 제목 키워드 기반

Linked Adapters: Linking Past and Future to Present for Effective Continual Learning

2024-12-14 · Dupati Srikar Chandra, P. K. Srijith, Dana Rezazadegan, Chris McCarthy

Continual learning allows the system to learn and adapt to new tasks while retaining the knowledge acquired from previous tasks. However, deep learning models suffer from catastrophic forgetting of knowledge learned from…

Continual Learningimage-classificationImage ClassificationTransfer Learning

Acted vs. Improvised: Domain Adaptation for Elicitation Approaches in Audio-Visual Emotion Recognition

2021-04-05 · Haoqi Li, Yelin Kim, Cheng-Hao Kuo, Shrikanth Narayanan

Key challenges in developing generalized automatic emotion recognition systems include scarcity of labeled data and lack of gold-standard references. Even for the cues that are labeled as the same emotion category, the v…

Domain AdaptationEmotion RecognitionTransfer Learning

Auto-selected Knowledge Adapters for Lifelong Person Re-identification

2024-05-29 · Xuelin Qian, Ruiqi Wu, Gong Cheng, Junwei Han

Lifelong Person Re-Identification (LReID) extends traditional ReID by requiring systems to continually learn from non-overlapping datasets across different times and locations, adapting to new identities while preserving…

Lifelong learningPerson Re-Identification

Harnessing Diffusion-Yielded Score Priors for Image Restoration

2025-07-28 · Xinqi Lin, Fanghua Yu, Jinfan Hu, Zhiyuan You 외 arxiv

Deep image restoration models aim to learn a mapping from degraded image space to natural image space. However, they face several critical challenges: removing degradation, generating realistic details, and ensuring pixe…

Image Restoration

On The Cross-Modal Transfer from Natural Language to Code through Adapter Modules

2022-04-19 · Divyam Goel, Ramansh Grover, Fatemeh H. Fard

Pre-trained neural Language Models (PTLM), such as CodeBERT, are recently used in software engineering as models pre-trained on large source code corpora. Their knowledge is transferred to downstream tasks (e.g. code clo…

Clone DetectionCloze TestTransfer Learning