English
Related papers

Related papers: A CLIP-Powered Framework for Robust and Generaliza…

200 papers

CLIP has become a cornerstone of multimodal representation learning, yet improving its performance typically requires a prohibitively costly process of training from scratch on billions of samples. We ask a different question: Can we…

Computer Vision and Pattern Recognition · Computer Science 2026-01-16 Anant Mehta , Xiyuan Wei , Xingyu Chen , Tianbao Yang

The growing scale of datasets in deep learning has introduced significant computational challenges. Dataset pruning addresses this challenge by constructing a compact but informative coreset from the full dataset with comparable…

Computer Vision and Pattern Recognition · Computer Science 2025-11-19 Furui Xu , Shaobo Wang , Jiajun Zhang , Chenghao Sun , Haixiang Tang , Linfeng Zhang

Instruction tuning has optimized the specialized capabilities of large language models (LLMs), but it often requires extensive datasets and prolonged training times. The challenge lies in developing specific capabilities by identifying…

Computation and Language · Computer Science 2026-05-26 Run Zou , Jianhang Ding , Yifan Ding , Wen Wu , Hao Chen , Renshu Gu

In this dissertation, we propose a systemic framework that prioritizes informative features and examples to enhance each stage of the development process. Specifically, we prioritize informative features and examples and improve the…

Machine Learning · Computer Science 2024-08-13 Dongmin Park

Recent advancements in pre-trained vision-language models like CLIP have shown promise in person re-identification (ReID) applications. However, their performance in generalizable person re-identification tasks remains suboptimal. The…

Computer Vision and Pattern Recognition · Computer Science 2024-10-16 Huazhong Zhao , Lei Qi , Xin Geng

Effectively leveraging multimodal data such as various images, laboratory tests and clinical information is gaining traction in a variety of AI-based medical diagnosis and prognosis tasks. Most existing multi-modal techniques only focus on…

Image and Video Processing · Electrical Eng. & Systems 2023-11-28 Yingying Fang , Shuang Wu , Sheng Zhang , Chaoyan Huang , Tieyong Zeng , Xiaodan Xing , Simon Walsh , Guang Yang

Machine learning interatomic potentials (MLIPs) provide an effective approach for accurately and efficiently modeling atomic interactions, expanding the capabilities of atomistic simulations to complex systems. However, a priori feature…

Computational Physics · Physics 2026-04-22 Tina Torabi , Matthias Militzer , Michael P. Friedlander , Christoph Ortner

Vision-Language Pre-training (VLP) has advanced the performance for many vision-language tasks. However, most existing pre-trained models only excel in either understanding-based tasks or generation-based tasks. Furthermore, performance…

Computer Vision and Pattern Recognition · Computer Science 2022-02-16 Junnan Li , Dongxu Li , Caiming Xiong , Steven Hoi

Selecting high-quality training data from a larger pool is a crucial step when instruction-tuning language models, as carefully curated datasets often produce models that outperform those trained on much larger, noisier datasets. Automated…

Computation and Language · Computer Science 2025-06-23 Hamish Ivison , Muru Zhang , Faeze Brahman , Pang Wei Koh , Pradeep Dasigi

A fine-grained data recipe is crucial for pre-training large language models, as it can significantly enhance training efficiency and model performance. One important ingredient in the recipe is to select samples based on scores produced by…

Computation and Language · Computer Science 2026-01-01 Ziqing Fan , Yuqiao Xian , Yan Sun , Li Shen

Training high-quality CLIP models typically requires enormous datasets, which limits the development of domain-specific models -- especially in areas that even the largest CLIP models do not cover well -- and drives up training costs. This…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Simon Ging , Sebastian Walter , Jelena Bratulić , Johannes Dienert , Hannah Bast , Thomas Brox

Noisy labels threaten the robustness of few-shot learning (FSL) due to the inexact features in a new domain. CLIP, a large-scale vision-language model, performs well in FSL on image-text embedding similarities, but it is susceptible to…

Computer Vision and Pattern Recognition · Computer Science 2024-12-18 Shizhuo Deng , Bowen Han , Jiaqi Chen , Hao Wang , Dongyue Chen , Tong Jia

We present Distill CLIP (DCLIP), a fine-tuned variant of the CLIP model that enhances multimodal image-text retrieval while preserving the original model's strong zero-shot classification capabilities. CLIP models are typically constrained…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Daniel Csizmadia , Andrei Codreanu , Victor Sim , Vighnesh Prabhu , Michael Lu , Kevin Zhu , Sean O'Brien , Vasu Sharma

Multimodal learning often grapples with the challenge of low-quality data, which predominantly manifests as two facets: modality imbalance and noisy corruption. While these issues are often studied in isolation, we argue that they share a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-06 Xun Jiang , Yufan Gu , Disen Hu , Yuqing Hou , Yazhou Yao , Fumin Shen , Heng Tao Shen , Xing Xu

Injecting world knowledge into pretrained multimodal large language models (MLLMs) is essential for domain-specific applications. Task-specific fine-tuning achieves this by tailoring MLLMs to high-quality in-domain data but encounters…

Multimedia · Computer Science 2026-03-31 Xiao An , Jiaxing Sun , Ting Hu , Wei He

Large-scale cross-modal pre-training paradigms have recently shown ubiquitous success on a wide range of downstream tasks, e.g., zero-shot classification, retrieval and image captioning. However, their successes highly rely on the scale and…

Computer Vision and Pattern Recognition · Computer Science 2023-01-05 Runhui Huang , Yanxin Long , Jianhua Han , Hang Xu , Xiwen Liang , Chunjing Xu , Xiaodan Liang

Falsely annotated samples, also known as noisy labels, can significantly harm the performance of deep learning models. Two main approaches for learning with noisy labels are global noise estimation and data filtering. Global noise…

Machine Learning · Computer Science 2025-07-31 Yuval Grinberg , Nimrod Harel , Jacob Goldberger , Ofir Lindenbaum

This paper investigates the performance of the Contrastive Language-Image Pre-training (CLIP) when scaled down to limited computation budgets. We explore CLIP along three dimensions: data, architecture, and training strategies. With regards…

Computer Vision and Pattern Recognition · Computer Science 2024-04-17 Zichao Li , Cihang Xie , Ekin Dogus Cubuk

We explore the potential of large-scale noisily labeled data to enhance feature learning by pretraining semantic segmentation models within a multi-modal framework for geospatial applications. We propose a novel Cross-modal Sample Selection…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Chenying Liu , Conrad Albrecht , Yi Wang , Xiao Xiang Zhu

Visual language models like Contrastive Language-Image Pretraining (CLIP) have shown impressive performance in analyzing natural images with language information. However, these models often encounter challenges when applied to specialized…

Computer Vision and Pattern Recognition · Computer Science 2024-12-11 Jiaqing Zhang , Mingxiang Cao , Xue Yang , Kai Jiang , Yunsong Li