Active Data Curation Effectively Distills Large-Scale Multimodal Models

• URL: http://arxiv.org/abs/2411.18674v1
• Date: Wed, 27 Nov 2024 18:50:15 GMT
• Title: Active Data Curation Effectively Distills Large-Scale Multimodal Models
• Authors: Vishaal Udandarao, Nikhil Parthasarathy, Muhammad Ferjad Naeem, Talfan Evans, Samuel Albanie, Federico Tombari, Yongqin Xian, Alessio Tonioni, Olivier J. Hénaff,
• Abstract summary: Knowledge distillation (KD) is the de facto standard for compressing large-scale models into smaller ones. In this work we explore an alternative, yet simple approach -- active data curation as effective distillation for contrastive multimodal pretraining. Our simple online batch selection method, ACID, outperforms strong KD baselines across various model-, data- and compute-configurations.
• Score: 66.23057263509027
• License:
• Abstract: Knowledge distillation (KD) is the de facto standard for compressing large-scale models into smaller ones. Prior works have explored ever more complex KD strategies involving different objective functions, teacher-ensembles, and weight inheritance. In this work we explore an alternative, yet simple approach -- active data curation as effective distillation for contrastive multimodal pretraining. Our simple online batch selection method, ACID, outperforms strong KD baselines across various model-, data- and compute-configurations. Further, we find such an active data curation strategy to in fact be complementary to standard KD, and can be effectively combined to train highly performant inference-efficient models. Our simple and scalable pretraining framework, ACED, achieves state-of-the-art results across 27 zero-shot classification and retrieval tasks with upto 11% less inference FLOPs. We further demonstrate that our ACED models yield strong vision-encoders for training generative multimodal models in the LiT-Decoder setting, outperforming larger vision encoders for image-captioning and visual question-answering tasks.

Related papers

• CLIP-CID: Efficient CLIP Distillation via Cluster-Instance Discrimination [28.061239778773423]
  Contrastive Language-Image Pre-training (CLIP) has achieved excellent performance over a wide range of tasks. CLIP heavily relies on a substantial corpus of pre-training data, resulting in notable consumption of computational resources. We introduce CLIP-CID, a novel distillation mechanism that effectively transfers knowledge from a large vision-language foundation model to a smaller model.
  arXiv  Detail & Related papers  (2024-08-18T11:23:21Z)
• Dynamic Self-adaptive Multiscale Distillation from Pre-trained Multimodal Large Model for Efficient Cross-modal Representation Learning [12.00246872965739]
  We propose a novel dynamic self-adaptive multiscale distillation from pre-trained multimodal large model. Our strategy employs a multiscale perspective, enabling the extraction structural knowledge across from the pre-trained multimodal large model. Our methodology streamlines pre-trained multimodal large models using only their output features and original image-level information.
  arXiv  Detail & Related papers  (2024-04-16T18:22:49Z)
• DistiLLM: Towards Streamlined Distillation for Large Language Models [53.46759297929675]
  DistiLLM is a more effective and efficient KD framework for auto-regressive language models. DisiLLM comprises two components: (1) a novel skew Kullback-Leibler divergence loss, where we unveil and leverage its theoretical properties, and (2) an adaptive off-policy approach designed to enhance the efficiency in utilizing student-generated outputs.
  arXiv  Detail & Related papers  (2024-02-06T11:10:35Z)
• Robustness-Reinforced Knowledge Distillation with Correlation Distance and Network Pruning [3.1423836318272773]
  Knowledge distillation (KD) improves the performance of efficient and lightweight models. Most existing KD techniques rely on Kullback-Leibler (KL) divergence. We propose a Robustness-Reinforced Knowledge Distillation (R2KD) that leverages correlation distance and network pruning.
  arXiv  Detail & Related papers  (2023-11-23T11:34:48Z)
• One-stop Training of Multiple Capacity Models [74.87789190840527]
  We propose a novel one-stop training framework to jointly train high-capacity and low-capactiy models. Unlike knowledge distillation, where multiple capacity models are trained from scratch separately, our approach integrates supervisions from different capacity models simultaneously.
  arXiv  Detail & Related papers  (2023-05-23T13:44:09Z)
• eP-ALM: Efficient Perceptual Augmentation of Language Models [70.47962271121389]
  We propose to direct effort to efficient adaptations of existing models, and propose to augment Language Models with perception. Existing approaches for adapting pretrained models for vision-language tasks still rely on several key components that hinder their efficiency. We show that by freezing more than 99% of total parameters, training only one linear projection layer, and prepending only one trainable token, our approach (dubbed eP-ALM) significantly outperforms other baselines on VQA and Captioning.
  arXiv  Detail & Related papers  (2023-03-20T19:20:34Z)
• Knowledge Distillation for Adaptive MRI Prostate Segmentation Based on Limit-Trained Multi-Teacher Models [4.711401719735324]
  Knowledge Distillation (KD) has been proposed as a compression method and an acceleration technology. KD is an efficient learning strategy that can transfer knowledge from a burdensome model to a lightweight model. We develop a KD-based deep model for prostate MRI segmentation in this work by combining features-based distillation with Kullback-Leibler divergence, Lovasz, and Dice losses.
  arXiv  Detail & Related papers  (2023-03-16T17:15:08Z)
• Unifying Synergies between Self-supervised Learning and Dynamic Computation [53.66628188936682]
  We present a novel perspective on the interplay between SSL and DC paradigms. We show that it is feasible to simultaneously learn a dense and gated sub-network from scratch in a SSL setting. The co-evolution during pre-training of both dense and gated encoder offers a good accuracy-efficiency trade-off.
  arXiv  Detail & Related papers  (2023-01-22T17:12:58Z)
• Modality-specific Distillation [30.190082262375395]
  We propose modality-specific distillation (MSD) to effectively transfer knowledge from a teacher on multimodal datasets. Our idea aims at mimicking a teacher's modality-specific predictions by introducing an auxiliary loss term for each modality. Because each modality has different importance for predictions, we also propose weighting approaches for the auxiliary losses.
  arXiv  Detail & Related papers  (2021-01-06T05:45:07Z)
• MixKD: Towards Efficient Distillation of Large-scale Language Models [129.73786264834894]
  We propose MixKD, a data-agnostic distillation framework, to endow the resulting model with stronger generalization ability. We prove from a theoretical perspective that under reasonable conditions MixKD gives rise to a smaller gap between the error and the empirical error. Experiments under a limited-data setting and ablation studies further demonstrate the advantages of the proposed approach.
  arXiv  Detail & Related papers  (2020-11-01T18:47:51Z)

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.