Efficient PEFT Methods with Adaptive Checkpointing for Vision Models and VLMs on Resource Constrained Consumer-GPUs

• URL: http://arxiv.org/abs/2607.02158v1
• Date: Thu, 02 Jul 2026 13:31:29 GMT
• Title: Efficient PEFT Methods with Adaptive Checkpointing for Vision Models and VLMs on Resource Constrained Consumer-GPUs
• Abstract summary: This paper compares five parameter-efficient fine-tuning methods (PEFT) on Transformers- (ViT-Small, TinyViT) and Mamba-based vision backbones (Vim-Small, MambaVision-T)<n>We evaluate three families of foundation-model baselines: zero-shot contrastive vision language models (OpenCLIP, SigLIP), self-supervised vision backbones with lightweight evaluation protocols (DINOv2), and autoregressive VLMs for prompt-based classification (PaliGemma, MobileVLM, SmolVLM)<n>Experiments on CIFAR-100 and DTD
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern pretrained vision models achieve strong accuracy but demand substantial GPU memory for fine-tuning, making edge deployment impractical. This paper compares five parameter-efficient fine-tuning (PEFT) methods (Full FT, LoRA, AdaLoRA, QLoRA, BitFit) on Transformers- (ViT-Small, TinyViT) and Mamba-based vision backbones (Vim-Small, MambaVision-T) under an on-device VRAM budget (e.g., 2 GB), together with three gradient-checkpointing strategies (none, static, and a proposed memory-budget-aware adaptive algorithm); and we evaluate three families of foundation-model baselines: zero-shot contrastive vision language models (OpenCLIP, SigLIP), self-supervised vision backbones with lightweight evaluation protocols (DINOv2), and autoregressive VLMs for prompt-based classification (PaliGemma, MobileVLM, SmolVLM). Experiments on CIFAR-100 and DTD report accuracy, training time, energy, and the NetScore family of multi-objective metrics, which we extend with two deployment-aware variants. QLoRA and BitFit cut energy 20-30% at a 1-2% accuracy cost; the adaptive algorithm reduces peak memory 43-79% with 9-30% energy overhead. DINOv2 surpasses fine-tuned models on CIFAR-100 (0.917 vs. 0.897) at a fraction of the energy, while small autoregressive VLMs remain uncompetitive.

Related papers

• HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents [71.09493646932046]
  We introduce HY-Embodied-0.5, a family of foundation models specifically designed for real-world embodied agents.<n>The HY-Embodied-0.5 suite comprises two primary variants: an efficient model with 2B activated parameters designed for edge deployment, and a powerful model with 32B activated parameters targeted for complex reasoning.<n>Our MoT-2B model outperforms similarly sized state-of-the-art models on 16 benchmarks, while the 32B variant achieves performance comparable to frontier models such as Gemini 3.0 Pro.
  arXiv  Detail & Related papers  (2026-04-08T17:59:48Z)
• DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding, Perception, Prediction and Planning [94.62097655403683]
  We propose DrivePI, a novel spatial-aware 4D MLLM that serves as a unified Vision-Language-Action framework.<n>Our method jointly performs spatial understanding, 3D perception, prediction (i.e., occupancy flow), and planning (i.e., action outputs) in parallel.<n>With only a 0.5B Qwen2.5 model as MLLM backbone, DrivePI as a single unified model matches or exceeds both existing VLA models and specialized VA models.
  arXiv  Detail & Related papers  (2025-12-14T18:45:54Z)
• LL-ViT: Edge Deployable Vision Transformers with Look Up Table Neurons [1.213604453116022]
  Vision Transformers have been tremendously successful in computer vision tasks.<n>Large computational, memory, and energy demands are a challenge for edge inference on FPGAs.<n>We propose LL-ViT, a novel edge optimized vision transformer design.
  arXiv  Detail & Related papers  (2025-11-02T05:51:48Z)
• AndesVL Technical Report: An Efficient Mobile-side Multimodal Large Language Model [40.488271586857884]
  AndesVL is a suite of mobile-side MLLMs with 0.6B to 4B parameters based on Qwen3's LLM and various visual encoders.<n>We introduce a 1+N LoRA architecture alongside a Quantization-Aware LoRA Fine-Tuning framework to facilitate efficient task adaptation and model compression.<n>We achieve a 6.7x peak decoding speedup ratio, up to 30.9% memory reduction, and 1.8 bits-per-weight when deploying AndesVL-4B on MediaTek Dimensity 9500 chips.
  arXiv  Detail & Related papers  (2025-10-13T15:04:38Z)
• MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe [68.04078852416248]
  MiniCPM-V 4.5 is an 8B parameter model designed for high efficiency and strong performance.<n>We introduce three core improvements in model architecture, data strategy and training method.<n>MiniCPM-V 4.5 achieves state-of-the-art performance among models under 30B size.
  arXiv  Detail & Related papers  (2025-09-16T19:41:48Z)
• EfficientLLM: Efficiency in Large Language Models [64.3537131208038]
  Large Language Models (LLMs) have driven significant progress, yet their growing counts and context windows incur prohibitive compute, energy, and monetary costs.<n>We introduce EfficientLLM, a novel benchmark and the first comprehensive empirical study evaluating efficiency techniques for LLMs at scale.
  arXiv  Detail & Related papers  (2025-05-20T02:27:08Z)
• A Light Perspective for 3D Object Detection [46.23578780480946]
  This paper introduces a novel approach that incorporates cutting-edge Deep Learning techniques into the feature extraction process.<n>Our model, NextBEV, surpasses established feature extractors like ResNet50 and MobileNetV3.<n>By fusing these lightweight proposals, we have enhanced the accuracy of the VoxelNet-based model by 2.93% and improved the F1-score of the PointPillar-based model by approximately 20%.
  arXiv  Detail & Related papers  (2025-03-10T10:03:23Z)
• EMOv2: Pushing 5M Vision Model Frontier [92.21687467702972]
  We set up the new frontier of the 5M magnitude lightweight model on various downstream tasks.<n>Our work rethinks the lightweight infrastructure of efficient IRB and practical components in Transformer.<n>Considering the imperceptible latency for mobile users when downloading models under 4G/5G bandwidth, we investigate the performance upper limit of lightweight models with a magnitude of 5M.
  arXiv  Detail & Related papers  (2024-12-09T17:12:22Z)
• Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts [60.1586169973792]
  M$3$ViT is the latest multi-task ViT model that introduces mixture-of-experts (MoE) MoE achieves better accuracy and over 80% reduction computation but leaves challenges for efficient deployment on FPGA. Our work, dubbed Edge-MoE, solves the challenges to introduce the first end-to-end FPGA accelerator for multi-task ViT with a collection of architectural innovations.
  arXiv  Detail & Related papers  (2023-05-30T02:24:03Z)
• EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning [19.354515754130592]
  We introduce a distilling then pruning framework to compress large vision-language models into smaller, faster, and more accurate ones. We apply our framework to train EfficientVLM, a fast and accurate vision-language model consisting of 6 vision layers, 3 text layers, and 3 cross-modal fusion layers. EfficientVLM retains 98.4% performance of the teacher model and accelerates its inference speed by 2.2x.
  arXiv  Detail & Related papers  (2022-10-14T13:26:41Z)

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.