Pith. sign in

REVIEW 5 cited by

Semantic Change Detection with Asymmetric Siamese Networks

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2010.05687 v2 pith:BPRUVMRD submitted 2020-10-12 cs.CV

Kunping Yang , Gui-Song Xia , Zicheng Liu , Bo Du , Wen Yang , Marcello Pelillo , Liangpei Zhang This is my paper · ORCID
classification cs.CV
keywords differentchangesemanticdetectionidentifyland-covermodelalgorithms
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Given two multi-temporal aerial images, semantic change detection aims to locate the land-cover variations and identify their change types with pixel-wise boundaries. This problem is vital in many earth vision related tasks, such as precise urban planning and natural resource management. Existing state-of-the-art algorithms mainly identify the changed pixels by applying homogeneous operations on each input image and comparing the extracted features. However, in changed regions, totally different land-cover distributions often require heterogeneous features extraction procedures w.r.t each input. In this paper, we present an asymmetric siamese network (ASN) to locate and identify semantic changes through feature pairs obtained from modules of widely different structures, which involve areas of various sizes and apply different quantities of parameters to factor in the discrepancy across different land-cover distributions. To better train and evaluate our model, we create a large-scale well-annotated SEmantic Change detectiON Dataset (SECOND), while an Adaptive Threshold Learning (ATL) module and a Separated Kappa (SeK) coefficient are proposed to alleviate the influences of label imbalance in model training and evaluation. The experimental results demonstrate that the proposed model can stably outperform the state-of-the-art algorithms with different encoder backbones.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. CogVis: Must Open-Vocabulary Change Detection Perceive the Scene Anew for Every Query?

    cs.AI 2026-08 conditional novelty 7.0 of 10

    CogVis achieves state-of-the-art open-vocabulary change detection on seven remote-sensing benchmarks by computing a reusable category-agnostic change prior once per image pair and calibrating per-query decision thresh...

  2. Robust Change Captioning in Remote Sensing: SECOND-CC Dataset and MModalCC Framework

    cs.CV 2025-01 conditional novelty 6.0 of 10

    A new dataset and a multimodal attention model improve remote sensing change captioning, but only when ground-truth semantic maps are supplied as input.

  3. Semantic-CD: Remote Sensing Image Semantic Change Detection towards Open-vocabulary Setting

    cs.CV 2025-01 conditional novelty 5.0 of 10

    Semantic-CD couples binary and semantic change detection in remote sensing imagery via CLIP text-guided cost volumes, reporting state-of-the-art scores on the SECOND dataset.

  4. DynamicEarth: How Far are We from Open-Vocabulary Change Detection?

    cs.CV 2025-01 reject novelty 4.0 of 10

    The paper shows that composing mask proposal, feature comparison, and open-vocabulary classification models can detect arbitrary-category changes in satellite images without training.

  5. Detect Changes like Humans: Incorporating Semantic Priors for Improved Change Detection

    cs.CV 2024-12 conditional novelty 4.0 of 10

    A change detection network with a frozen FastSAM encoder, a dual-stream semantic/difference decoder, and pseudo-change pretraining from segmentation maps raises F1 on five remote sensing benchmarks.

Pith tools