English
Related papers

Related papers: Frame-wise Conditioning Adaptation for Fine-Tuning…

200 papers

Foundation models (FMs) are pre-trained on large-scale datasets and then fine-tuned for a specific downstream task. The most common fine-tuning method is to update pretrained weights via low-rank adaptation (LoRA). Existing initialization…

Machine Learning · Computer Science 2025-10-21 Fabian Paischer , Lukas Hauzenberger , Thomas Schmied , Benedikt Alkin , Marc Peter Deisenroth , Sepp Hochreiter

Existing pedestrian attribute recognition (PAR) algorithms are mainly developed based on a static image, however, the performance is unreliable in challenging scenarios, such as heavy occlusion, motion blur, etc. In this work, we propose to…

Computer Vision and Pattern Recognition · Computer Science 2024-04-30 Xiao Wang , Qian Zhu , Jiandong Jin , Jun Zhu , Futian Wang , Bo Jiang , Yaowei Wang , Yonghong Tian

Fine-tuning Video Diffusion Models (VDMs) at the user level to generate videos that reflect specific attributes of training data presents notable challenges, yet remains underexplored despite its practical importance. Meanwhile, recent work…

Computer Vision and Pattern Recognition · Computer Science 2025-06-26 Sungwon Hwang , Hyojin Jang , Kinam Kim , Minho Park , Jaegul Choo

Low-rank adaptation (LoRA) is widely used for parameter-efficient fine-tuning, but its standard all-token, all-head design ignores the heterogeneous structure of vision language model (VLM) inputs. We introduce \emph{Image-LoRA}, a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Tiange Luo , Lajanugen Logeswaran , Jaekyeom Kim , Justin Johnson , Honglak Lee

Text-to-image diffusion models are typically trained to optimize the log-likelihood objective, which presents challenges in meeting specific requirements for downstream tasks, such as image aesthetics and image-text alignment. Recent…

Computer Vision and Pattern Recognition · Computer Science 2024-07-18 Chaofeng Chen , Annan Wang , Haoning Wu , Liang Liao , Wenxiu Sun , Qiong Yan , Weisi Lin

Recent video reasoning models have shown strong results on temporal and multimodal understanding, yet they depend on large-scale supervised data and multi-stage training pipelines, making them costly to train and difficult to adapt to new…

Recent methods in flow-based diffusion editing have enabled direct transformations between source and target image distribution without explicit inversion. However, the latent trajectories in these methods often exhibit accumulated velocity…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Zixiang Li , Yue Song , Jianing Peng , Ting Liu , Jun Huang , Xiaochao Qu , Luoqi Liu , Wei Wang , Yao Zhao , Yunchao Wei

While Text-to-Image (T2I) diffusion models excel at generating visually appealing images of individual instances, they struggle to accurately position and control the features generation of multiple instances. The Layout-to-Image (L2I) task…

Computer Vision and Pattern Recognition · Computer Science 2024-11-07 Yinwei Wu , Xianpan Zhou , Bing Ma , Xuefeng Su , Kai Ma , Xinchao Wang

Recent advancements in text-to-image (T2I) generation using diffusion models have enabled cost-effective video-editing applications by leveraging pre-trained models, eliminating the need for resource-intensive training. However, the…

Computer Vision and Pattern Recognition · Computer Science 2025-06-12 Yangfan He , Sida Li , Jianhui Wang , Kun Li , Xinyuan Song , Xinhang Yuan , Keqin Li , Kuan Lu , Menghao Huo , Jingqun Tang , Yi Xin , Jiaqi Chen , Miao Zhang , Xueqian Wang

This paper introduces a novel framework for end-to-end learned video coding. Image compression is generalized through conditional coding to exploit information from reference frames, allowing to process intra and inter frames with the same…

Image and Video Processing · Electrical Eng. & Systems 2021-04-29 Théo Ladune , Pierrick Philippe , Wassim Hamidouche , Lu Zhang , Olivier Déforges

Previous models for video captioning often use the output from a specific layer of a Convolutional Neural Network (CNN) as video features. However, the variable context-dependent semantics in the video may make it more appropriate to…

Computer Vision and Pattern Recognition · Computer Science 2017-11-20 Yunchen Pu , Martin Renqiang Min , Zhe Gan , Lawrence Carin

In this work we propose a simple unsupervised approach for next frame prediction in video. Instead of directly predicting the pixels in a frame given past frames, we predict the transformations needed for generating the next frame in a…

Machine Learning · Computer Science 2023-02-07 Joost van Amersfoort , Anitha Kannan , Marc'Aurelio Ranzato , Arthur Szlam , Du Tran , Soumith Chintala

This paper proposes a novel approach to address the challenge that pretrained VLA models often fail to effectively improve performance and reduce adaptation costs during standard supervised finetuning (SFT). Some advanced finetuning methods…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Wenxuan Song , Han Zhao , Fuhao Li , Ziyang Zhou , Xi Wang , Jing Lyu , Pengxiang Ding , Yan Wang , Donglin Wang , Haoang Li

Contrastive Language-Image Pretraining (CLIP) excels at learning generalizable image representations but often falls short in zero-shot inference on certain downstream datasets. Test-time adaptation (TTA) mitigates this issue by adjusting…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Zixin Wang , Dong Gong , Sen Wang , Zi Huang , Yadan Luo

Segmenting images is critical for visual understanding but demands extensive pixel-level annotations. Foundational models have enabled new paradigms for predicting new classes guided by textual prompts, without annotations from the target…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Gabriele Rosi , Fabio Cermelli , Carlo Masone , Barbara Caputo

Vision Transformer (ViT) is becoming more popular in image processing. Specifically, we investigate the effectiveness of test-time adaptation (TTA) on ViT, a technique that has emerged to correct its prediction during test-time by itself.…

Computer Vision and Pattern Recognition · Computer Science 2022-06-29 Takeshi Kojima , Yutaka Matsuo , Yusuke Iwasawa

Text-to-Video (T2V) generation has benefited from recent advances in diffusion models, yet current systems still struggle under complex scenarios, which are generally exacerbated by the ambiguity and underspecification of text prompts. In…

Artificial Intelligence · Computer Science 2026-04-21 Chengyi Yang , Pengzhen Li , Jiayin Qi , Aimin Zhou , Ji Wu , Ji Liu

Recent advances in text-to-image generation have enabled the creation of high-quality images with diverse applications. However, accurately describing desired visual attributes can be challenging, especially for non-experts in art and…

Computer Vision and Pattern Recognition · Computer Science 2024-12-11 Tong Wu , Yinghao Xu , Ryan Po , Mengchen Zhang , Guandao Yang , Jiaqi Wang , Ziwei Liu , Dahua Lin , Gordon Wetzstein

Despite the fact that text-to-video (TTV) model has recently achieved remarkable success, there have been few approaches on TTV for its extension to video editing. Motivated by approaches on TTV models adapting from diffusion-based…

Computer Vision and Pattern Recognition · Computer Science 2023-11-20 Chaehun Shin , Heeseung Kim , Che Hyun Lee , Sang-gil Lee , Sungroh Yoon

Diffusion models are widely used for generative tasks across domains. Given a pre-trained diffusion model, it is often desirable to fine-tune it further either to correct for errors in learning or to align with downstream applications.…