Cover Image

Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Frumkin, Natalia, Gope, Dibakar, Marculescu, Diana
Format:	Preprint
Published:	2023
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling
by: Frumkin, Natalia, et al.
Published: (2025)

Data-Free Group-Wise Fully Quantized Winograd Convolution via Learnable Scales
by: Pan, Shuokai, et al.
Published: (2024)

Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes
by: Li, Aodi, et al.
Published: (2024)

SupMAE: Supervised Masked Autoencoders Are Efficient Vision Learners
by: Liang, Feng, et al.
Published: (2022)

Ada-VE: Training-Free Consistent Video Editing Using Adaptive Motion Prior
by: Mahmud, Tanvir, et al.
Published: (2024)

Synthesizing Artifact Dataset for Pixel-level Detection
by: Menn, Dennis, et al.
Published: (2025)

T-VSL: Text-Guided Visual Sound Source Localization in Mixtures
by: Mahmud, Tanvir, et al.
Published: (2024)

ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer Acceleration
by: Huang, Ning-Chi, et al.
Published: (2024)

Scaling Graph Convolutions for Mobile Vision
by: Avery, William, et al.
Published: (2024)

AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer
by: Wu, Zhuguanyu, et al.
Published: (2024)

PaPr: Training-Free One-Step Patch Pruning with Lightweight ConvNets for Faster Inference
by: Mahmud, Tanvir, et al.
Published: (2024)

Mix-QViT: Mixed-Precision Vision Transformer Quantization Driven by Layer Importance and Quantization Sensitivity
by: Ranjan, Navin, et al.
Published: (2025)

Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers
by: Zhong, Yunshan, et al.
Published: (2024)

AIQViT: Architecture-Informed Post-Training Quantization for Vision Transformers
by: Jiang, Runqing, et al.
Published: (2025)

Locality-Attending Vision Transformer
by: Hajimiri, Sina, et al.
Published: (2026)

LocalViT: Analyzing Locality in Vision Transformers
by: Li, Yawei, et al.
Published: (2021)

Video Compression Meets Video Generation: Latent Inter-Frame Pruning with Attention Recovery
by: Menn, Dennis, et al.
Published: (2026)

MA-AVT: Modality Alignment for Parameter-Efficient Audio-Visual Transformers
by: Mahmud, Tanvir, et al.
Published: (2024)

MGRQ: Post-Training Quantization For Vision Transformer With Mixed Granularity Reconstruction
by: Yang, Lianwei, et al.
Published: (2024)

MPTQ-ViT: Mixed-Precision Post-Training Quantization for Vision Transformer
by: Tai, Yu-Shan, et al.
Published: (2024)

MK-UNet: Multi-kernel Lightweight CNN for Medical Image Segmentation
by: Rahman, Md Mostafijur, et al.
Published: (2025)

LoMix: Learnable Weighted Multi-Scale Logits Mixing for Medical Image Segmentation
by: Rahman, Md Mostafijur, et al.
Published: (2025)

Mixed Non-linear Quantization for Vision Transformers
by: Kim, Gihwan, et al.
Published: (2024)

Instance-Aware Group Quantization for Vision Transformers
by: Moon, Jaehyeon, et al.
Published: (2024)

The Geometry of Robustness: Optimizing Loss Landscape Curvature and Feature Manifold Alignment for Robust Finetuning of Vision-Language Models
by: Chopra, Shivang, et al.
Published: (2026)

Towards Accurate Post-Training Quantization of Vision Transformers via Error Reduction
by: Zhong, Yunshan, et al.
Published: (2024)

ADFQ-ViT: Activation-Distribution-Friendly Post-Training Quantization for Vision Transformers
by: Jiang, Yanfeng, et al.
Published: (2024)

Inducing Spatial Locality in Vision Transformers through the Training Protocol
by: Toledo, Eduardo Santiago, et al.
Published: (2026)

Federated Vision Transformer with Adaptive Focal Loss for Medical Image Classification
by: Zhao, Xinyuan, et al.
Published: (2026)

Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning
by: Ma, Lianbo, et al.
Published: (2025)

LampQ: Towards Accurate Layer-wise Mixed Precision Quantization for Vision Transformers
by: Kim, Minjun, et al.
Published: (2025)

Joint Post-Training Quantization of Vision Transformers with Learned Prompt-Guided Data Generation
by: Li, Shile, et al.
Published: (2026)

Amortized-Precision Quantization for Early-Exit Vision Transformers
by: Fang, Rui, et al.
Published: (2026)

Multi-Scale High-Resolution Logarithmic Grapher Module for Efficient Vision GNNs
by: Munir, Mustafa, et al.
Published: (2025)

Analyzing Local Representations of Self-supervised Vision Transformers
by: Vanyan, Ani, et al.
Published: (2023)

Similarity Trajectories: Linking Sampling Process to Artifacts in Diffusion-Generated Images
by: Menn, Dennis, et al.
Published: (2024)

Reframing Long-Tailed Learning via Loss Landscape Geometry
by: Chen, Shenghan, et al.
Published: (2026)

LRP-QViT: Mixed-Precision Vision Transformer Quantization via Layer-wise Relevance Propagation
by: Ranjan, Navin, et al.
Published: (2024)

APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers
by: Wu, Zhuguanyu, et al.
Published: (2025)

Quantized Spike-driven Transformer
by: Qiu, Xuerui, et al.
Published: (2025)