paper-with-me

홈 › Papers

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 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, especially in the low-data regimes, and our model consistently outperforms state-of-the-art multi-task approaches.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Task Learning

Similar Papers 제목 키워드 기반

Deep Cross Residual Learning for Multitask Visual Recognition

2016-04-05 · Brendan Jou, Shih-Fu Chang

Residual learning has recently surfaced as an effective means of constructing very deep neural networks for object recognition. However, current incarnations of residual networks do not allow for the modeling and integra…

Object Recognition

In-context Learning Distillation: Transferring Few-shot Learning Ability of Pre-trained Language Models

2022-12-20 · Yukun Huang, Yanda Chen, Zhou Yu, Kathleen McKeown

Given the success with in-context learning of large pre-trained language models, we introduce in-context learning distillation to transfer in-context few-shot learning ability from large models to smaller models. We prop…

Few-Shot LearningIn-Context LearningLanguage ModelingLanguage Modelling

Regression Transformer: Concurrent sequence regression and generation for molecular language modeling

2022-02-01 · Jannis Born, Matteo Manica

Despite significant progress of generative models in the natural sciences, their controllability remains challenging. One fundamentally missing aspect of molecular or protein generative models is an inductive bias that c…

Conditional Text GenerationInductive BiasLanguage ModelingLanguage Modelling+3

Generative multitask learning mitigates target-causing confounding

2022-02-08 · Taro Makino, Krzysztof J. Geras, Kyunghyun Cho

We propose generative multitask learning (GMTL), a simple and scalable approach to causal representation learning for multitask learning. Our approach makes a minor change to the conventional multitask inference objectiv…

Out-of-Distribution GeneralizationRepresentation Learning

Indo LEGO-ABSA: A Multitask Generative Aspect Based Sentiment Analysis for Indonesian Language

2023-11-03 · Randy Zakya Suchrady, Ayu Purwarianti

Aspect-based sentiment analysis is a method in natural language processing aimed at identifying and understanding sentiments related to specific aspects of an entity. Aspects are words or phrases that represent an aspect…

Aspect-Based Sentiment AnalysisAspect Sentiment Triplet ExtractionAttributeSentiment Analysis+2