Two-Stream Interactive Joint Learning of Scene Parsing and Geometric Vision Tasks

• URL: http://arxiv.org/abs/2602.13588v1
• Date: Sat, 14 Feb 2026 04:11:19 GMT
• Title: Two-Stream Interactive Joint Learning of Scene Parsing and Geometric Vision Tasks
• Authors: Guanfeng Tang, Hongbo Zhao, Ziwei Long, Jiayao Li, Bohong Xiao, Wei Ye, Hanli Wang, Rui Fan,
• Abstract summary: Two Interactive Streams (TwInS) is a novel bio-inspired joint learning framework capable of simultaneously performing scene parsing and geometric vision tasks.<n>To eliminate the dependence on costly human-annotated correspondence ground truth, TwInS is equipped with a tailored semi-supervised training strategy.
• Score: 24.19752468668527
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Inspired by the human visual system, which operates on two parallel yet interactive streams for contextual and spatial understanding, this article presents Two Interactive Streams (TwInS), a novel bio-inspired joint learning framework capable of simultaneously performing scene parsing and geometric vision tasks. TwInS adopts a unified, general-purpose architecture in which multi-level contextual features from the scene parsing stream are infused into the geometric vision stream to guide its iterative refinement. In the reverse direction, decoded geometric features are projected into the contextual feature space for selective heterogeneous feature fusion via a novel cross-task adapter, which leverages rich cross-view geometric cues to enhance scene parsing. To eliminate the dependence on costly human-annotated correspondence ground truth, TwInS is further equipped with a tailored semi-supervised training strategy, which unleashes the potential of large-scale multi-view data and enables continuous self-evolution without requiring ground-truth correspondences. Extensive experiments conducted on three public datasets validate the effectiveness of TwInS's core components and demonstrate its superior performance over existing state-of-the-art approaches. The source code will be made publicly available upon publication.

Related papers

• Revisiting Multi-Task Visual Representation Learning [52.93947931352643]
  We introduce MTV, a principled multi-task visual pretraining framework.<n>We leverage high-capacity "expert" models to synthesize dense, structured pseudo-labels at scale.<n>Our results demonstrate that MTV achieves "best-of-both-worlds" performance.
  arXiv  Detail & Related papers  (2026-01-20T11:59:19Z)
• EVLP:Learning Unified Embodied Vision-Language Planner with Reinforced Supervised Fine-Tuning [44.254412516852874]
  Current methods fail to adopt a unified generation framework for multimodal planning, lead to inconsistent in multimodal planning.<n>Our approach achieves multimodal planning for long-horizon tasks through a novel training pipeline incorporating dynamic pretraining and reinforced alignment.
  arXiv  Detail & Related papers  (2025-11-03T10:24:49Z)
• Exploring a Unified Vision-Centric Contrastive Alternatives on Multi-Modal Web Documents [99.62178668680578]
  We propose Vision-Centric Contrastive Learning (VC2L), a unified framework that models text, images, and their combinations using a single vision transformer.<n> VC2L operates entirely in pixel space by rendering all inputs, whether textual, visual, or combined, as images.<n>To capture complex cross-modal relationships in web documents, VC2L employs a snippet-level contrastive learning objective that aligns consecutive multimodal segments.
  arXiv  Detail & Related papers  (2025-10-21T14:59:29Z)
• Real-Time Intuitive AI Drawing System for Collaboration: Enhancing Human Creativity through Formal and Contextual Intent Integration [26.920087528015205]
  This paper presents a real-time generative drawing system that interprets and integrates both formal intent and contextual intent.<n>The system achieves low-latency, two-stage transformation while supporting multi-user collaboration on shared canvases.
  arXiv  Detail & Related papers  (2025-08-12T01:34:23Z)
• Geometric Visual Fusion Graph Neural Networks for Multi-Person Human-Object Interaction Recognition in Videos [14.198003271084799]
  Human-Object Interaction (HOI) recognition in videos requires understanding both visual patterns and geometric relationships as they evolve over time.<n>We propose the Geometric Visual Fusion Graph Neural Network (GeoVis-GNN), which uses dual-attention feature fusion combined with interdependent entity graph learning.<n>To advance HOI recognition to real-world scenarios, we introduce the Concurrent Partial Interaction dataset.
  arXiv  Detail & Related papers  (2025-06-03T22:51:44Z)
• SeMv-3D: Towards Concurrency of Semantic and Multi-view Consistency in General Text-to-3D Generation [122.47961178994456]
  SeMv-3D is a novel framework that jointly enhances semantic alignment and multi-view consistency in GT23D generation.<n>At its core, we introduce Triplane Prior Learning (TPL), which effectively learns triplane priors.<n>We also present Prior-based Semantic Aligning in Triplanes (SAT), which enables consistent any-view synthesis.
  arXiv  Detail & Related papers  (2024-10-10T07:02:06Z)
• Focus on Neighbors and Know the Whole: Towards Consistent Dense Multiview Text-to-Image Generator for 3D Creation [64.07560335451723]
  CoSER is a novel consistent dense Multiview Text-to-Image Generator for Text-to-3D. It achieves both efficiency and quality by meticulously learning neighbor-view coherence. It aggregates information along motion paths explicitly defined by physical principles to refine details.
  arXiv  Detail & Related papers  (2024-08-23T15:16:01Z)
• Towards Deeply Unified Depth-aware Panoptic Segmentation with Bi-directional Guidance Learning [63.63516124646916]
  We propose a deeply unified framework for depth-aware panoptic segmentation. We propose a bi-directional guidance learning approach to facilitate cross-task feature learning. Our method sets the new state of the art for depth-aware panoptic segmentation on both Cityscapes-DVPS and SemKITTI-DVPS datasets.
  arXiv  Detail & Related papers  (2023-07-27T11:28:33Z)
• Semantic Role Aware Correlation Transformer for Text to Video Retrieval [23.183653281610866]
  This paper proposes a novel transformer that explicitly disentangles the text and video into semantic roles of objects, spatial contexts and temporal contexts. Preliminary results on popular YouCook2 indicate that our approach surpasses a current state-of-the-art method, with a high margin in all metrics.
  arXiv  Detail & Related papers  (2022-06-26T11:28:03Z)
• COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval [59.15034487974549]
  We propose a novel COllaborative Two-Stream vision-language pretraining model termed COTS for image-text retrieval. Our COTS achieves the highest performance among all two-stream methods and comparable performance with 10,800X faster in inference. Importantly, our COTS is also applicable to text-to-video retrieval, yielding new state-ofthe-art on the widely-used MSR-VTT dataset.
  arXiv  Detail & Related papers  (2022-04-15T12:34:47Z)

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.