Masked AutoDecoder is Effective Multi-Task Vision Generalist

• URL: http://arxiv.org/abs/2403.07692v2
• Date: Thu, 14 Mar 2024 18:54:46 GMT
• Title: Masked AutoDecoder is Effective Multi-Task Vision Generalist
• Authors: Han Qiu, Jiaxing Huang, Peng Gao, Lewei Lu, Xiaoqin Zhang, Shijian Lu,
• Abstract summary: Masked AutoDecoder(MAD) is an effective multi-task vision generalist. We develop a parallel decoding framework that introduces bi-directional attention to capture contextual dependencies. Second, we design a masked sequence modeling approach that learns rich task contexts by masking and reconstructing task sequences.
• Score: 64.43215311406195
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Inspired by the success of general-purpose models in NLP, recent studies attempt to unify different vision tasks in the same sequence format and employ autoregressive Transformers for sequence prediction. They apply uni-directional attention to capture sequential dependencies and generate task sequences recursively. However, such autoregressive Transformers may not fit vision tasks well, as vision task sequences usually lack the sequential dependencies typically observed in natural languages. In this work, we design Masked AutoDecoder~(MAD), an effective multi-task vision generalist. MAD consists of two core designs. First, we develop a parallel decoding framework that introduces bi-directional attention to capture contextual dependencies comprehensively and decode vision task sequences in parallel. Second, we design a masked sequence modeling approach that learns rich task contexts by masking and reconstructing task sequences. In this way, MAD handles all the tasks by a single network branch and a simple cross-entropy loss with minimal task-specific designs. Extensive experiments demonstrate the great potential of MAD as a new paradigm for unifying various vision tasks. MAD achieves superior performance and inference efficiency compared to autoregressive counterparts while obtaining competitive accuracy with task-specific models. Code will be released.

Related papers

• SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation [62.58480650443393]
  Segment Anything (SAM) is a vision-foundation model for generalizable scene understanding and sequence imitation. We develop a novel multi-channel heatmap that enables the prediction of the action sequence in a single pass.
  arXiv  Detail & Related papers  (2024-05-30T00:32:51Z)
• GLID: Pre-training a Generalist Encoder-Decoder Vision Model [36.242095346942556]
  We propose a GeneraLIst encoder-Decoder (GLID) pre-training method for better handling various downstream computer vision tasks. GLID allows the pre-trained generalist encoder-decoder to be fine-tuned on various vision tasks with minimal task-specific architecture modifications. GLID achieves competitive performance on various vision tasks, including object detection, image segmentation, pose estimation, and depth estimation.
  arXiv  Detail & Related papers  (2024-04-11T09:43:07Z)
• Task Indicating Transformer for Task-conditional Dense Predictions [16.92067246179703]
  We introduce a novel task-conditional framework called Task Indicating Transformer (TIT) to tackle this challenge. Our approach designs a Mix Task Adapter module within the transformer block, which incorporates a Task Indicating Matrix through matrix decomposition. We also propose a Task Gate Decoder module that harnesses a Task Indicating Vector and gating mechanism to facilitate adaptive multi-scale feature refinement.
  arXiv  Detail & Related papers  (2024-03-01T07:06:57Z)
• Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model [83.85856356798531]
  VistaLLM is a visual system that addresses coarse- and fine-grained vision-language tasks. It employs a gradient-aware adaptive sampling technique to represent binary segmentation masks as sequences. We also introduce a novel task, AttCoSeg, which boosts the model's reasoning and grounding capability over multiple input images.
  arXiv  Detail & Related papers  (2023-12-19T18:53:01Z)
• Video Task Decathlon: Unifying Image and Video Tasks in Autonomous Driving [85.62076860189116]
  Video Task Decathlon (VTD) includes ten representative image and video tasks spanning classification, segmentation, localization, and association of objects and pixels. We develop our unified network, VTDNet, that uses a single structure and a single set of weights for all ten tasks.
  arXiv  Detail & Related papers  (2023-09-08T16:33:27Z)
• A Unified Sequence Interface for Vision Tasks [87.328893553186]
  We show that a diverse set of "core" computer vision tasks can be unified if formulated in terms of a shared pixel-to-sequence interface. We focus on four tasks, namely, object detection, instance segmentation, keypoint detection, and image captioning, all with diverse types of outputs. We show that one can train a neural network with a single model architecture and loss function on all these tasks, with no task-specific customization.
  arXiv  Detail & Related papers  (2022-06-15T17:08:53Z)
• MulT: An End-to-End Multitask Learning Transformer [66.52419626048115]
  We propose an end-to-end Multitask Learning Transformer framework, named MulT, to simultaneously learn multiple high-level vision tasks. Our framework encodes the input image into a shared representation and makes predictions for each vision task using task-specific transformer-based decoder heads.
  arXiv  Detail & Related papers  (2022-05-17T13:03:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.