DAM: Dynamic Adapter Merging for Continual Video QA Learning

• URL: http://arxiv.org/abs/2403.08755v2
• Date: Mon, 22 Apr 2024 19:17:49 GMT
• Title: DAM: Dynamic Adapter Merging for Continual Video QA Learning
• Authors: Feng Cheng, Ziyang Wang, Yi-Lin Sung, Yan-Bo Lin, Mohit Bansal, Gedas Bertasius,
• Abstract summary: We present a parameter-efficient method for continual video question-answering (VidQA) learning. Our method uses the proposed Dynamic Adapter Merging to (i) mitigate catastrophic forgetting, (ii) enable efficient adaptation to continually arriving datasets, and (iv) enable knowledge sharing across similar dataset domains. Our DAM model outperforms prior state-of-the-art continual learning approaches by 9.1% while exhibiting 1.9% less forgetting on 6 VidQA datasets spanning various domains.
• Score: 66.43360542692355
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present a parameter-efficient method for continual video question-answering (VidQA) learning. Our method, named DAM, uses the proposed Dynamic Adapter Merging to (i) mitigate catastrophic forgetting, (ii) enable efficient adaptation to continually arriving datasets, (iii) handle inputs from unknown datasets during inference, and (iv) enable knowledge sharing across similar dataset domains. Given a set of continually streaming VidQA datasets, we sequentially train dataset-specific adapters for each dataset while freezing the parameters of a large pretrained video-language backbone. During inference, given a video-question sample from an unknown domain, our method first uses the proposed non-parametric router function to compute a probability for each adapter, reflecting how relevant that adapter is to the current video-question input instance. Subsequently, the proposed dynamic adapter merging scheme aggregates all the adapter weights into a new adapter instance tailored for that particular test sample to compute the final VidQA prediction, mitigating the impact of inaccurate router predictions and facilitating knowledge sharing across domains. Our DAM model outperforms prior state-of-the-art continual learning approaches by 9.1% while exhibiting 1.9% less forgetting on 6 VidQA datasets spanning various domains. We further extend DAM to continual image classification and image QA and outperform prior methods by a large margin. The code is publicly available at: https://github.com/klauscc/DAM

Related papers

• Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis [51.14136878142034]
  Point cloud analysis has achieved outstanding performance by transferring point cloud pre-trained models. Existing methods for model adaptation usually update all model parameters, which is inefficient as it relies on high computational costs. In this paper, we aim to study parameter-efficient transfer learning for point cloud analysis with an ideal trade-off between task performance and parameter efficiency.
  arXiv  Detail & Related papers  (2024-03-03T08:25:04Z)
• p-Laplacian Adaptation for Generative Pre-trained Vision-Language Models [10.713680139939354]
  Vision-Language models (VLMs) pre-trained on large corpora have demonstrated notable success across a range of downstream tasks. PETL has garnered attention as a viable alternative to full fine-tuning. We propose a new adapter architecture, $p$-adapter, which employs $p$-Laplacian message passing in Graph Neural Networks (GNNs)
  arXiv  Detail & Related papers  (2023-12-17T05:30:35Z)
• Object-based (yet Class-agnostic) Video Domain Adaptation [78.34712426922519]
  We present Object-based (yet Class-agnostic) Video Domain Adaptation (ODAPT) ODAPT is a simple yet effective framework for adapting the existing action recognition systems to new domains. Our model achieves a +6.5 increase when adapting across kitchens in Epic-Kitchens and a +3.1 increase adapting between Epic-Kitchens and the EGTEA dataset.
  arXiv  Detail & Related papers  (2023-11-29T01:17:38Z)
• Test-Time Adaptation for Point Cloud Upsampling Using Meta-Learning [17.980649681325406]
  We propose a test-time adaption approach to enhance model generality of point cloud upsampling. The proposed approach leverages meta-learning to explicitly learn network parameters for test-time adaption. Our framework is generic and can be applied in a plug-and-play manner with existing backbone networks in point cloud upsampling.
  arXiv  Detail & Related papers  (2023-08-31T06:44:59Z)
• MerA: Merging Pretrained Adapters For Few-Shot Learning [71.44422347502409]
  We propose textbftextttMerging Pretrained Adapters (MerA) that efficiently incorporates pretrained adapters to a single model through model fusion. Experiments on two PLMs demonstrate that MerA substantial improvements compared to both single adapters and AdapterFusion.
  arXiv  Detail & Related papers  (2023-08-30T12:10:17Z)
• Parameter-Efficient Sparse Retrievers and Rerankers using Adapters [4.9545244468634655]
  We study adapters for SPLADE, a sparse retriever, for which adapters retain the efficiency and effectiveness otherwise achieved by finetuning. We also address domain adaptation of neural retrieval thanks to adapters on cross-domain BEIR datasets and TripClick.
  arXiv  Detail & Related papers  (2023-03-23T12:34:30Z)
• Back to the Source: Diffusion-Driven Test-Time Adaptation [77.4229736436935]
  Test-time adaptation harnesses test inputs to improve accuracy of a model trained on source data when tested on shifted target data. We instead update the target data, by projecting all test inputs toward the source domain with a generative diffusion model.
  arXiv  Detail & Related papers  (2022-07-07T17:14:10Z)
• Human Instance Segmentation and Tracking via Data Association and Single-stage Detector [17.46922710432633]
  Human video instance segmentation plays an important role in computer understanding of human activities. Most current VIS methods are based on Mask-RCNN framework. We develop a new method for human video instance segmentation based on single-stage detector.
  arXiv  Detail & Related papers  (2022-03-31T11:36:09Z)
• One to Many: Adaptive Instrument Segmentation via Meta Learning and Dynamic Online Adaptation in Robotic Surgical Video [71.43912903508765]
  MDAL is a dynamic online adaptive learning scheme for instrument segmentation in robot-assisted surgery. It learns the general knowledge of instruments and the fast adaptation ability through the video-specific meta-learning paradigm. It outperforms other state-of-the-art methods on two datasets.
  arXiv  Detail & Related papers  (2021-03-24T05:02:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.