Continually Learn to Map Visual Concepts to Large Language Models in Resource-constrained Environments

• URL: http://arxiv.org/abs/2407.08279v1
• Date: Thu, 11 Jul 2024 08:28:40 GMT
• Title: Continually Learn to Map Visual Concepts to Large Language Models in Resource-constrained Environments
• Authors: Clea Rebillard, Julio Hurtado, Andrii Krutsylo, Lucia Passaro, Vincenzo Lomonaco,
• Abstract summary: Continual Visual Mapping (CVM) is an approach that continually ground vision representations to a knowledge space extracted from a fixed Language model. CVM overcomes state-of-the-art continual learning methods on five benchmarks.
• Score: 7.481446615819558
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning continually from a stream of non-i.i.d. data is an open challenge in deep learning, even more so when working in resource-constrained environments such as embedded devices. Visual models that are continually updated through supervised learning are often prone to overfitting, catastrophic forgetting, and biased representations. On the other hand, large language models contain knowledge about multiple concepts and their relations, which can foster a more robust, informed and coherent learning process. This work proposes Continual Visual Mapping (CVM), an approach that continually ground vision representations to a knowledge space extracted from a fixed Language model. Specifically, CVM continually trains a small and efficient visual model to map its representations into a conceptual space established by a fixed Large Language Model. Due to their smaller nature, CVM can be used when directly adapting large visual pre-trained models is unfeasible due to computational or data constraints. CVM overcome state-of-the-art continual learning methods on five benchmarks and offers a promising avenue for addressing generalization capabilities in continual learning, even in computationally constrained devices.

Related papers

• CLEFT: Language-Image Contrastive Learning with Efficient Large Language Model and Prompt Fine-Tuning [4.004641316826348]
  We introduce a novel language-image Contrastive Learning method with an Efficient large language model and prompt Fine-Tuning (CLEFT) Our method demonstrates state-of-the-art performance on multiple chest X-ray and mammography datasets. The proposed parameter efficient framework can reduce the total trainable model size by 39% and reduce the trainable language model to only 4% compared with the current BERT encoder.
  arXiv  Detail & Related papers  (2024-07-30T17:57:32Z)
• Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models [42.182009352159]
  We present a new efficient LLVM, Mamba-based traversal of rationales (Meteor) To embed lengthy rationales containing abundant information, we employ the Mamba architecture, capable of processing sequential data with linear time complexity. Subsequently, the backbone multimodal language model (MLM) is trained to generate answers with the aid of rationale.
  arXiv  Detail & Related papers  (2024-05-24T14:04:03Z)
• Premonition: Using Generative Models to Preempt Future Data Changes in Continual Learning [63.850451635362425]
  Continual learning requires a model to adapt to ongoing changes in the data distribution. We show that the combination of a large language model and an image generation model can similarly provide useful premonitions. We find that the backbone of our pre-trained networks can learn representations useful for the downstream continual learning problem.
  arXiv  Detail & Related papers  (2024-03-12T06:29:54Z)
• Expedited Training of Visual Conditioned Language Generation via Redundancy Reduction [61.16125290912494]
  $textEVL_textGen$ is a framework designed for the pre-training of visually conditioned language generation models. We show that our approach accelerates the training of vision-language models by a factor of 5 without a noticeable impact on overall performance.
  arXiv  Detail & Related papers  (2023-10-05T03:40:06Z)
• SINC: Self-Supervised In-Context Learning for Vision-Language Tasks [64.44336003123102]
  We propose a framework to enable in-context learning in large language models. A meta-model can learn on self-supervised prompts consisting of tailored demonstrations. Experiments show that SINC outperforms gradient-based methods in various vision-language tasks.
  arXiv  Detail & Related papers  (2023-07-15T08:33:08Z)
• Recognizing Unseen Objects via Multimodal Intensive Knowledge Graph Propagation [68.13453771001522]
  We propose a multimodal intensive ZSL framework that matches regions of images with corresponding semantic embeddings. We conduct extensive experiments and evaluate our model on large-scale real-world data.
  arXiv  Detail & Related papers  (2023-06-14T13:07:48Z)
• Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning [54.67880602409801]
  In this paper, we study the problem of pre-training world models with abundant in-the-wild videos for efficient learning of visual control tasks. We introduce Contextualized World Models (ContextWM) that explicitly separate context and dynamics modeling. Our experiments show that in-the-wild video pre-training equipped with ContextWM can significantly improve the sample efficiency of model-based reinforcement learning.
  arXiv  Detail & Related papers  (2023-05-29T14:29:12Z)
• Scaling Vision-Language Models with Sparse Mixture of Experts [128.0882767889029]
  We show that mixture-of-experts (MoE) techniques can achieve state-of-the-art performance on a range of benchmarks over dense models of equivalent computational cost. Our research offers valuable insights into stabilizing the training of MoE models, understanding the impact of MoE on model interpretability, and balancing the trade-offs between compute performance when scaling vision-language models.
  arXiv  Detail & Related papers  (2023-03-13T16:00:31Z)
• Teaching Structured Vision&Language Concepts to Vision&Language Models [46.344585368641006]
  We introduce the collective notion of Structured Vision&Language Concepts (SVLC) SVLC includes object attributes, relations, and states which are present in the text and visible in the image. We propose a more elegant data-driven approach for enhancing VL models' understanding of SVLCs.
  arXiv  Detail & Related papers  (2022-11-21T18:54:10Z)
• Generalized Zero-Shot Learning using Multimodal Variational Auto-Encoder with Semantic Concepts [0.9054540533394924]
  Recent techniques try to learn a cross-modal mapping between the semantic space and the image space. We propose a Multimodal Variational Auto-Encoder (M-VAE) which can learn the shared latent space of image features and the semantic space. Our results show that our proposed model outperforms the current state-of-the-art approaches for generalized zero-shot learning.
  arXiv  Detail & Related papers  (2021-06-26T20:08:37Z)
• Does language help generalization in vision models? [0.0]
  We show that a visual model trained on a very large supervised image dataset (ImageNet-21k) can be as efficient for generalization as its multimodal counterpart (CLIP) When compared to other standard visual or language models, the latent representations of BiT-M were found to be just as "linguistic" as those of CLIP.
  arXiv  Detail & Related papers  (2021-04-16T18:54:14Z)

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.