Cover Image

Scaling (Down) CLIP: A Comprehensive Analysis of Data, Architecture, and Training Strategies

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Zichao, Xie, Cihang, Cubuk, Ekin Dogus
Format:	Preprint
Published:	2024
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

Revisiting Adversarial Training at Scale
by: Wang, Zeyu, et al.
Published: (2024)

On the Adversarial Robustness of Camera-based 3D Object Detection
by: Xie, Shaoyuan, et al.
Published: (2023)

CLIPS: An Enhanced CLIP Framework for Learning with Synthetic Captions
by: Liu, Yanqing, et al.
Published: (2024)

Scaling White-Box Transformers for Vision
by: Yang, Jinrui, et al.
Published: (2024)

From Pixels to Objects: A Hierarchical Approach for Part and Object Segmentation Using Local and Global Aggregation
by: Xie, Yunfei, et al.
Published: (2024)

NeuCLIP: Efficient Large-Scale CLIP Training with Neural Normalizer Optimization
by: Wei, Xiyuan, et al.
Published: (2025)

Demystifying CLIP Data
by: Xu, Hu, et al.
Published: (2023)

M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image Generation
by: Ren, Sucheng, et al.
Published: (2024)

Meta CLIP 2: A Worldwide Scaling Recipe
by: Chuang, Yung-Sung, et al.
Published: (2025)

OmniCLIP: Adapting CLIP for Video Recognition with Spatial-Temporal Omni-Scale Feature Learning
by: Liu, Mushui, et al.
Published: (2024)

TNG-CLIP:Training-Time Negation Data Generation for Negation Awareness of CLIP
by: Cai, Yuliang, et al.
Published: (2025)

GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset
by: Wang, Yuhan, et al.
Published: (2025)

OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning
by: Li, Xianhang, et al.
Published: (2025)

Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More
by: Wang, Feng, et al.
Published: (2025)

EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters
by: Sun, Quan, et al.
Published: (2024)

Filter & Align: Leveraging Human Knowledge to Curate Image-Text Data
by: Zhang, Lei, et al.
Published: (2023)

Story-Iter: A Training-free Iterative Paradigm for Long Story Visualization
by: Mao, Jiawei, et al.
Published: (2024)

NeuroCLIP: Neuromorphic Data Understanding by CLIP and SNN
by: Guo, Yufei, et al.
Published: (2023)

ClipTTT: CLIP-Guided Test-Time Training Helps LVLMs See Better
by: Nath, Mriganka, et al.
Published: (2026)

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness
by: Wang, Zeyu, et al.
Published: (2025)

Selective, Controlled and Domain-Agnostic Unlearning in Pretrained CLIP: A Training- and Data-Free Approach
by: Mishra, Ashish, et al.
Published: (2025)

Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency
by: Wang, Feng, et al.
Published: (2024)

Localization vs. Semantics: Visual Representations in Unimodal and Multimodal Models
by: Li, Zhuowan, et al.
Published: (2022)

CLIP-VIS: Adapting CLIP for Open-Vocabulary Video Instance Segmentation
by: Zhu, Wenqi, et al.
Published: (2024)

SPFormer: Enhancing Vision Transformer with Superpixel Representation
by: Mei, Jieru, et al.
Published: (2024)

Probing CLIP's Comprehension of 360-Degree Textual and Visual Semantics
by: Wang, Hai, et al.
Published: (2026)

CLIP Architecture for Abdominal CT Image-Text Alignment and Zero-Shot Learning: Investigating Batch Composition and Data Scaling
by: Shivika, et al.
Published: (2026)

AnimalMotionCLIP: Embedding motion in CLIP for Animal Behavior Analysis
by: Zhong, Enmin, et al.
Published: (2025)

Benchmarking PathCLIP for Pathology Image Analysis
by: Zheng, Sunyi, et al.
Published: (2024)

A Comprehensive Survey on Deep Learning-Based LiDAR Super-Resolution for Autonomous Driving
by: Goo, June Moh, et al.
Published: (2026)

PowerCLIP: Powerset Alignment for Contrastive Pre-Training
by: Kawamura, Masaki, et al.
Published: (2025)

The Unreasonable Effectiveness of Text Embedding Interpolation for Continuous Image Steering
by: Ekin, Yigit, et al.
Published: (2026)

ResCLIP: Residual Attention for Training-free Dense Vision-language Inference
by: Yang, Yuhang, et al.
Published: (2024)

LowCLIP: Adapting the CLIP Model Architecture for Low-Resource Languages in Multimodal Image Retrieval Task
by: Asgarov, Ali, et al.
Published: (2024)

CLIP-VQDiffusion : Langauge Free Training of Text To Image generation using CLIP and vector quantized diffusion model
by: Han, Seungdae, et al.
Published: (2024)

CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey
by: Li, Jindong, et al.
Published: (2025)

VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models
by: Wang, Yuxuan, et al.
Published: (2024)

Text and Image Are Mutually Beneficial: Enhancing Training-Free Few-Shot Classification with CLIP
by: Li, Yayuan, et al.
Published: (2024)

ComKD-CLIP: Comprehensive Knowledge Distillation for Contrastive Language-Image Pre-traning Model
by: Chen, Yifan, et al.
Published: (2024)

ARVideo: Autoregressive Pretraining for Self-Supervised Video Representation Learning
by: Ren, Sucheng, et al.
Published: (2024)