paper-with-me

홈 › Papers

Generative Modeling for Multi-task Visual Learning

2021-06-25 · Zhipeng Bao, Martial Hebert, Yu-Xiong Wang

Generative modeling has recently shown great promise in computer vision, but it has mostly focused on synthesizing visually realistic images. In this paper, motivated by multi-task learning of shareable feature representations, we consider a novel problem of learning a shared generative model that is useful across various visual perception tasks. Correspondingly, we propose a general multi-task oriented generative modeling (MGM) framework, by coupling a discriminative multi-task network with a generative network. While it is challenging to synthesize both RGB images and pixel-level annotations in multi-task scenarios, our framework enables us to use synthesized images paired with only weak annotations (i.e., image-level scene labels) to facilitate multiple visual tasks. Experimental evaluation on challenging multi-task benchmarks, including NYUv2 and Taskonomy, demonstrates that our MGM framework improves the performance of all the tasks by large margins, consistently outperforming state-of-the-art multi-task approaches.

📄 PDF Abstract BibTeX arXiv:2106.13409

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Task Learning

Similar Papers 제목 키워드 기반

Generative Modeling for Multitask Visual Learning

2021-09-29 · Zhipeng Bao, Yu-Xiong Wang, Martial Hebert

Generative modeling has recently shown great promise in computer vision, but it has mostly focused on synthesizing visually realistic images. In this paper, motivated by multi-task learning of shareable feature represent…

Multi-Task Learning

VL-BEiT: Generative Vision-Language Pretraining

2022-06-02 · Hangbo Bao, Wenhui Wang, Li Dong, Furu Wei

We introduce a vision-language foundation model called VL-BEiT, which is a bidirectional multimodal Transformer learned by generative pretraining. Our minimalist solution conducts masked prediction on both monomodal and …

image-classificationImage ClassificationImage-text RetrievalLanguage Modeling+9

V-Bridge: Bridging Video Generative Priors to Versatile Few-shot Image Restoration

2026-03-13 · Shenghe Zheng, Junpeng Jiang, Wenbo Li arxiv

Large-scale video generative models are trained on vast and diverse visual data, enabling them to internalize rich structural, semantic, and dynamic priors of the visual world. While these models have demonstrated impres…

Image Restoration

DepthART: Monocular Depth Estimation as Autoregressive Refinement Task

2024-09-23 · Bulat Gabdullin, Nina Konovalova, Nikolay Patakin, Dmitry Senushkin 외

Despite recent success in discriminative approaches in monocular depth estimation its quality remains limited by training datasets. Generative approaches mitigate this issue by leveraging strong priors derived from train…

Depth EstimationImage GenerationMonocular Depth Estimation

3D-Belief: Embodied Belief Inference via Generative 3D World Modeling

2026-05-12 · Yifan Yin, Zehao Wen, Suyu Ye, Jieneng Chen 외 arxiv

Recent advances in visual generative models have highlighted the promise of learning generative world models. However, most existing approaches frame world modeling as novel-view synthesis or future-frame prediction, emp…