Interactive Image Segmentation with Cross-Modality Vision Transformers

• URL: http://arxiv.org/abs/2307.02280v1
• Date: Wed, 5 Jul 2023 13:29:05 GMT
• Title: Interactive Image Segmentation with Cross-Modality Vision Transformers
• Authors: Kun Li, George Vosselman, Michael Ying Yang
• Abstract summary: Cross-modality vision transformers exploits mutual information to better guide the learning process. The stability of our method in term of avoiding failure cases shows its potential to be a practical annotation tool.
• Score: 18.075338835513993
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Interactive image segmentation aims to segment the target from the background with the manual guidance, which takes as input multimodal data such as images, clicks, scribbles, and bounding boxes. Recently, vision transformers have achieved a great success in several downstream visual tasks, and a few efforts have been made to bring this powerful architecture to interactive segmentation task. However, the previous works neglect the relations between two modalities and directly mock the way of processing purely visual information with self-attentions. In this paper, we propose a simple yet effective network for click-based interactive segmentation with cross-modality vision transformers. Cross-modality transformers exploits mutual information to better guide the learning process. The experiments on several benchmarks show that the proposed method achieves superior performance in comparison to the previous state-of-the-art models. The stability of our method in term of avoiding failure cases shows its potential to be a practical annotation tool. The code and pretrained models will be released under https://github.com/lik1996/iCMFormer.

Related papers

• Framer: Interactive Frame Interpolation [73.06734414930227]
  Framer targets producing smoothly transitioning frames between two images as per user creativity. Our approach supports customizing the transition process by tailoring the trajectory of some selected keypoints. It is noteworthy that our system also offers an "autopilot" mode, where we introduce a module to estimate the keypoints and the trajectory automatically.
  arXiv  Detail & Related papers  (2024-10-24T17:59:51Z)
• Learning from Exemplars for Interactive Image Segmentation [15.37506525730218]
  We introduce novel interactive segmentation frameworks for both a single object and multiple objects in the same category. Our model reduces users' labor by around 15%, requiring two fewer clicks to achieve target IoUs 85% and 90%.
  arXiv  Detail & Related papers  (2024-06-17T12:38:01Z)
• LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training [13.985488693082981]
  We propose a self-supervised object discovery approach that leverages motion and appearance information to produce high-quality object segmentation masks. We demonstrate the effectiveness of our approach, named LOCATE, on multiple standard video object segmentation, image saliency detection, and object segmentation benchmarks.
  arXiv  Detail & Related papers  (2023-08-22T07:27:09Z)
• DynaMITe: Dynamic Query Bootstrapping for Multi-object Interactive Segmentation Transformer [58.95404214273222]
  Most state-of-the-art instance segmentation methods rely on large amounts of pixel-precise ground-truth for training. We introduce a more efficient approach, called DynaMITe, in which we represent user interactions as-temporal queries. Our architecture also alleviates any need to re-compute image features during refinement, and requires fewer interactions for segmenting multiple instances in a single image.
  arXiv  Detail & Related papers  (2023-04-13T16:57:02Z)
• DOAD: Decoupled One Stage Action Detection Network [77.14883592642782]
  Localizing people and recognizing their actions from videos is a challenging task towards high-level video understanding. Existing methods are mostly two-stage based, with one stage for person bounding box generation and the other stage for action recognition. We present a decoupled one-stage network dubbed DOAD, to improve the efficiency for-temporal action detection.
  arXiv  Detail & Related papers  (2023-04-01T08:06:43Z)
• Multi-dataset Training of Transformers for Robust Action Recognition [75.5695991766902]
  We study the task of robust feature representations, aiming to generalize well on multiple datasets for action recognition. Here, we propose a novel multi-dataset training paradigm, MultiTrain, with the design of two new loss terms, namely informative loss and projection loss. We verify the effectiveness of our method on five challenging datasets, Kinetics-400, Kinetics-700, Moments-in-Time, Activitynet and Something-something-v2.
  arXiv  Detail & Related papers  (2022-09-26T01:30:43Z)
• Multimodal Contrastive Training for Visual Representation Learning [45.94662252627284]
  We develop an approach to learning visual representations that embraces multimodal data. Our method exploits intrinsic data properties within each modality and semantic information from cross-modal correlation simultaneously. By including multimodal training in a unified framework, our method can learn more powerful and generic visual features.
  arXiv  Detail & Related papers  (2021-04-26T19:23:36Z)
• Reviving Iterative Training with Mask Guidance for Interactive Segmentation [8.271859911016719]
  Recent works on click-based interactive segmentation have demonstrated state-of-the-art results by using various inference-time optimization schemes. We propose a simple feedforward model for click-based interactive segmentation that employs the segmentation masks from previous steps. We find that the models trained on a combination of COCO and LVIS with diverse and high-quality annotations show performance superior to all existing models.
  arXiv  Detail & Related papers  (2021-02-12T15:44:31Z)
• Transformers in Vision: A Survey [101.07348618962111]
  Transformers enable modeling long dependencies between input sequence elements and support parallel processing of sequence. Transformers require minimal inductive biases for their design and are naturally suited as set-functions. This survey aims to provide a comprehensive overview of the Transformer models in the computer vision discipline.
  arXiv  Detail & Related papers  (2021-01-04T18:57:24Z)
• Parameter Efficient Multimodal Transformers for Video Representation Learning [108.8517364784009]
  This work focuses on reducing the parameters of multimodal Transformers in the context of audio-visual video representation learning. We show that our approach reduces parameters up to 80$%$, allowing us to train our model end-to-end from scratch. To demonstrate our approach, we pretrain our model on 30-second clips from Kinetics-700 and transfer it to audio-visual classification tasks.
  arXiv  Detail & Related papers  (2020-12-08T00:16:13Z)

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.