GrowTAS: Progressive Expansion from Small to Large Subnets for Efficient ViT Architecture Search

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lee, Hyunju, Oh, Youngmin, Jeon, Jeimin, Baek, Donghyeon, Ham, Bumsub
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Subnet-Aware Dynamic Supernet Training for Neural Architecture Search
by: Jeon, Jeimin, et al.
Published: (2025)

TAS-LoRA: Transformer Architecture Search with Mixture-of-LoRA Experts
by: Jeon, Jeimin, et al.
Published: (2026)

Efficient Few-Shot Neural Architecture Search by Counting the Number of Nonlinear Functions
by: Oh, Youngmin, et al.
Published: (2024)

FYI: Flip Your Images for Dataset Distillation
by: Son, Byunggwan, et al.
Published: (2024)

Scheduling Weight Transitions for Quantization-Aware Training
by: Lee, Junghyup, et al.
Published: (2024)

Relational Feature Caching for Accelerating Diffusion Transformers
by: Son, Byunggwan, et al.
Published: (2026)

Toward INT4 Fixed-Point Training via Exploring Quantization Error for Gradients
by: Kim, Dohyung, et al.
Published: (2024)

AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Search
by: Lee, Junghyup, et al.
Published: (2024)

AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Models
by: Lee, Seunghoon, et al.
Published: (2025)

Improving Visual Token Reduction via Rectifying Distortions for Efficient Multimodal LLM Inference
by: Cho, Hyeonwoo, et al.
Published: (2026)

ConcatPlexer: Additional Dim1 Batching for Faster ViTs
by: Han, Donghoon, et al.
Published: (2023)

Maximizing the Position Embedding for Vision Transformers with Global Average Pooling
by: Lee, Wonjun, et al.
Published: (2025)

Exploring Hierarchical Consistency and Unbiased Objectness for Open-Vocabulary Object Detection
by: Lee, Sanghoon, et al.
Published: (2026)

3DPillars: Pillar-based two-stage 3D object detection
by: Noh, Jongyoun, et al.
Published: (2025)

Disentangled Representations for Short-Term and Long-Term Person Re-Identification
by: Eom, Chanho, et al.
Published: (2024)

Quasar-ViT: Hardware-Oriented Quantization-Aware Architecture Search for Vision Transformers
by: Li, Zhengang, et al.
Published: (2024)

EA-ViT: Efficient Adaptation for Elastic Vision Transformer
by: Zhu, Chen, et al.
Published: (2025)

Deeper Inside Deep ViT
by: Hong, Sungrae
Published: (2025)

I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantization
by: Zhong, Yunshan, et al.
Published: (2023)

Jailbreaking on Text-to-Video Models via Scene Splitting Strategy
by: Lee, Wonjun, et al.
Published: (2025)

RepViT: Revisiting Mobile CNN From ViT Perspective
by: Wang, Ao, et al.
Published: (2023)

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

ToaSt: Token Channel Selection and Structured Pruning for Efficient ViT
by: Moon, Hyunchan, et al.
Published: (2026)

STRAP-ViT: Segregated Tokens with Randomized -- Transformations for Defense against Adversarial Patches in ViTs
by: Chattopadhyay, Nandish, et al.
Published: (2026)

Frequency-Adaptive Discrete Cosine-ViT-ResNet Architecture for Sparse-Data Vision
by: Kang, Ziyue, et al.
Published: (2025)

ViTCAE: ViT-based Class-conditioned Autoencoder
by: Jebraeeli, Vahid, et al.
Published: (2025)

HyTAS: A Hyperspectral Image Transformer Architecture Search Benchmark and Analysis
by: Zhou, Fangqin, et al.
Published: (2024)

Cerberus: Attribute-based person re-identification using semantic IDs
by: Eom, Chanho, et al.
Published: (2024)

Partial Large Kernel CNNs for Efficient Super-Resolution
by: Lee, Dongheon, et al.
Published: (2024)

Rethinking Random Masking in Self-Distillation on ViT
by: Seong, Jihyeon, et al.
Published: (2025)

YOLO-Former: YOLO Shakes Hand With ViT
by: Khoramdel, Javad, et al.
Published: (2024)

Your ViT is Secretly an Image Segmentation Model
by: Kerssies, Tommie, et al.
Published: (2025)

ViT-5: Vision Transformers for The Mid-2020s
by: Wang, Feng, et al.
Published: (2026)

Learning CNN on ViT: A Hybrid Model to Explicitly Class-specific Boundaries for Domain Adaptation
by: Ngo, Ba Hung, et al.
Published: (2024)

Purrturbed but Stable: Human-Cat Invariant Representations Across CNNs, ViTs and Self-Supervised ViTs
by: Shah, Arya, et al.
Published: (2025)

Mobile U-ViT: Revisiting large kernel and U-shaped ViT for efficient medical image segmentation
by: Tang, Fenghe, et al.
Published: (2025)

Exploiting Lightweight Hierarchical ViT and Dynamic Framework for Efficient Visual Tracking
by: Kang, Ben, et al.
Published: (2025)

HydraViT: Stacking Heads for a Scalable ViT
by: Haberer, Janek, et al.
Published: (2024)

Exploring the Synergies of Hybrid CNNs and ViTs Architectures for Computer Vision: A survey
by: Yunusa, Haruna, et al.
Published: (2024)

MSCViT: A Small-size ViT architecture with Multi-Scale Self-Attention Mechanism for Tiny Datasets
by: Zhang, Bowei, et al.
Published: (2025)