Changer: Feature Interaction is What You Need for Change Detection

• URL: http://arxiv.org/abs/2209.08290v1
• Date: Sat, 17 Sep 2022 09:13:02 GMT
• Title: Changer: Feature Interaction is What You Need for Change Detection
• Authors: Sheng Fang, Kaiyu Li, Zhe Li
• Abstract summary: Change detection is an important tool for long-term earth observation missions. We propose a novel general change detection architecture, MetaChanger, which includes a series of alternative interaction layers in the feature extractor. We observe Changer series models achieve competitive performance on different scale change detection datasets.
• Score: 6.385385687682811
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Change detection is an important tool for long-term earth observation missions. It takes bi-temporal images as input and predicts "where" the change has occurred. Different from other dense prediction tasks, a meaningful consideration for change detection is the interaction between bi-temporal features. With this motivation, in this paper we propose a novel general change detection architecture, MetaChanger, which includes a series of alternative interaction layers in the feature extractor. To verify the effectiveness of MetaChanger, we propose two derived models, ChangerAD and ChangerEx with simple interaction strategies: Aggregation-Distribution (AD) and "exchange". AD is abstracted from some complex interaction methods, and "exchange" is a completely parameter\&computation-free operation by exchanging bi-temporal features. In addition, for better alignment of bi-temporal features, we propose a flow dual-alignment fusion (FDAF) module which allows interactive alignment and feature fusion. Crucially, we observe Changer series models achieve competitive performance on different scale change detection datasets. Further, our proposed ChangerAD and ChangerEx could serve as a starting baseline for future MetaChanger design.

Related papers

• ChangeChat: An Interactive Model for Remote Sensing Change Analysis via Multimodal Instruction Tuning [0.846600473226587]
  We introduce ChangeChat, the first bitemporal vision-language model (VLM) designed specifically for RS change analysis. ChangeChat utilizes multimodal instruction tuning, allowing it to handle complex queries such as change captioning, category-specific quantification, and change localization. Experiments show that ChangeChat offers a comprehensive, interactive solution for RS change analysis, achieving performance comparable to or even better than state-of-the-art (SOTA) methods on specific tasks.
  arXiv  Detail & Related papers  (2024-09-13T07:00:44Z)
• A Late-Stage Bitemporal Feature Fusion Network for Semantic Change Detection [32.112311027857636]
  We propose a novel late-stage bitemporal feature fusion network to address the issue of semantic change detection. Specifically, we propose local global attentional aggregation module to strengthen feature fusion, and propose local global context enhancement module to highlight pivotal semantics. Our proposed model achieves new state-of-the-art performance on both datasets.
  arXiv  Detail & Related papers  (2024-06-15T16:02:10Z)
• Change-Agent: Towards Interactive Comprehensive Remote Sensing Change Interpretation and Analysis [28.3763053922823]
  Current RSICI technology encompasses change detection and change captioning, each with its limitations in providing comprehensive interpretation. We propose an interactive Change-Agent, which can follow user instructions to achieve comprehensive change interpretation. The Change-Agent integrates a multi-level change interpretation (MCI) model as the eyes and a large language model (LLM) as the brain.
  arXiv  Detail & Related papers  (2024-03-28T17:55:42Z)
• Segment Any Change [64.23961453159454]
  We propose a new type of change detection model that supports zero-shot prediction and generalization on unseen change types and data distributions. AnyChange is built on the segment anything model (SAM) via our training-free adaptation method, bitemporal latent matching. We also propose a point query mechanism to enable AnyChange's zero-shot object-centric change detection capability.
  arXiv  Detail & Related papers  (2024-02-02T07:17:39Z)
• Disentangled Interaction Representation for One-Stage Human-Object Interaction Detection [70.96299509159981]
  Human-Object Interaction (HOI) detection is a core task for human-centric image understanding. Recent one-stage methods adopt a transformer decoder to collect image-wide cues that are useful for interaction prediction. Traditional two-stage methods benefit significantly from their ability to compose interaction features in a disentangled and explainable manner.
  arXiv  Detail & Related papers  (2023-12-04T08:02:59Z)
• MS-Former: Memory-Supported Transformer for Weakly Supervised Change Detection with Patch-Level Annotations [50.79913333804232]
  We propose a memory-supported transformer (MS-Former) for weakly supervised change detection. MS-Former consists of a bi-directional attention block (BAB) and a patch-level supervision scheme (PSS) Experimental results on three benchmark datasets demonstrate the effectiveness of our proposed method in the change detection task.
  arXiv  Detail & Related papers  (2023-11-16T09:57:29Z)
• EMS-Net: Efficient Multi-Temporal Self-Attention For Hyperspectral Change Detection [32.23764287942984]
  We have proposed an original Efficient Multi-temporal Self-attention Network (EMS-Net) for hyperspectral change detection. EMS-Net cuts redundancy of those similar and containing-no-changes feature maps, computing efficient multi-temporal change information for precise binary change map. Experiments implemented on two hyperspectral change detection datasets manifests the out-standing performance and validity of proposed method.
  arXiv  Detail & Related papers  (2023-03-24T02:11:22Z)
• EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning [83.11657818251447]
  We propose EqMotion, an efficient equivariant motion prediction model with invariant interaction reasoning. We conduct experiments for the proposed model on four distinct scenarios: particle dynamics, molecule dynamics, human skeleton motion prediction and pedestrian trajectory prediction. Our method achieves state-of-the-art prediction performances on all the four tasks, improving by 24.0/30.1/8.6/9.2%.
  arXiv  Detail & Related papers  (2023-03-20T05:23:46Z)
• Part-guided Relational Transformers for Fine-grained Visual Recognition [59.20531172172135]
  We propose a framework to learn the discriminative part features and explore correlations with a feature transformation module. Our proposed approach does not rely on additional part branches and reaches state-the-of-art performance on 3-of-the-level object recognition.
  arXiv  Detail & Related papers  (2022-12-28T03:45:56Z)
• Multi-Behavior Sequential Recommendation with Temporal Graph Transformer [66.10169268762014]
  We tackle the dynamic user-item relation learning with the awareness of multi-behavior interactive patterns. We propose a new Temporal Graph Transformer (TGT) recommendation framework to jointly capture dynamic short-term and long-range user-item interactive patterns.
  arXiv  Detail & Related papers  (2022-06-06T15:42:54Z)
• Reformulating HOI Detection as Adaptive Set Prediction [25.44630995307787]
  We reformulate HOI detection as an adaptive set prediction problem. We propose an Adaptive Set-based one-stage framework (AS-Net) with parallel instance and interaction branches. Our method outperforms previous state-of-the-art methods without any extra human pose and language features.
  arXiv  Detail & Related papers  (2021-03-10T10:40:33Z)

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.