AdaDINO: Pair-Aware In-Backbone Adaptation of Frozen DINO for Efficient Remote Sensing Change Detection

• URL: http://arxiv.org/abs/2608.07982v1
• Date: Sat, 08 Aug 2026 07:36:51 GMT
• Title: AdaDINO: Pair-Aware In-Backbone Adaptation of Frozen DINO for Efficient Remote Sensing Change Detection
• Abstract summary: AdaDINO is a pair-aware inbone adaptation framework that equips a frozen DINO encoder with bi-temporal interaction for efficient change detection.<n>Its core component, Change-aware Gated Local Adaptation (CGLA), couples the two streams after selected frozen blocks and injects a shared temporal residual into them with opposite signs.<n>AdaDINO achieves competitive or superior performance against VFM-based baselines, with the largest gain on the category-agnostic SYSU-CD dataset.
• Score: 12.041097740336333
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Vision foundation models (VFMs) such as DINO are pretrained for single-image representation, whereas remote sensing change detection requires reasoning over a bi-temporal pair. Existing VFM-based methods usually encode the two images independently and compare them only afterward, leaving the VFM backbone unaware of cross-temporal relations. To bridge this mismatch, we present AdaDINO, a pair-aware in-backbone adaptation framework that equips a frozen DINO encoder with bi-temporal interaction for efficient change detection. Its core component, Change-aware Gated Local Adaptation (CGLA), couples the two streams after selected frozen blocks and injects a shared temporal residual into them with opposite signs, enhancing genuine change responses while preserving the pair midpoint. Batch-Shared Chunk Selection (BSCS) further reduces feed-forward network (FFN) computation by retaining a batch-shared subset of channel chunks that can be executed as a compact dense FFN. A CGLA-Prior-Guided Refinement (CPGR) decoder reuses encoder-side change responses for coarse-to-fine prediction. Experiments on four remote sensing change detection benchmarks show that AdaDINO achieves competitive or superior performance against VFM-based baselines, with the largest gain on the category-agnostic SYSU-CD dataset. With 62.5% of the FFN hidden width removed, AdaDINO still achieves an F1 score of 85.29% on SYSU-CD while delivering a 1.41$\times$ throughput speedup. The code will be released.

Related papers

• S$^3$AM: A Single-Stream SAM with Reliability-Calibrated Frequency Adapter for Multi-modal Salient Object Detection [74.15663758681849]
  Single-stream framework integrates reliability-calibrated frequency adaptation into the adopted SAM backbone for MSOD.<n>Experiments on RGB-D, RGB-T, and RGB-NIR salient object detection benchmarks validate that the proposed framework achieves competitive performance.
  arXiv  Detail & Related papers  (2026-08-18T08:05:00Z)
• Resolving Multi-Target Association in OFDM-based ISAC via Vision-aided Multi-Modal Learning [10.44632158114449]
  We propose a vision-assisted OFDM-ISAC framework to overcome the data-association and resolution limits of single-modality ISAC.<n>The proposed framework achieves a 16 cm localization root mean square error (RMSE) and a 10.8 ns delay RMSE on a Blender-rendered vehicular testbed.
  arXiv  Detail & Related papers  (2026-06-20T19:07:22Z)
• CoSA: Correlation-Guided Change Attention with Learnable Residual Gating for Remote Sensing Change Detection [1.9364098361060789]
  We propose Context Sampling Attention (CoSA), a lightweight decoder-side refinement module.<n>CoSA explicitly leverages bi-temporal feature correlation as a control signal for adaptive change-aware feature enhancement.<n>Experiments on four benchmark datasets demonstrate consistent improvements over strong baselines.
  arXiv  Detail & Related papers  (2026-06-20T07:56:09Z)
• LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models [56.999481798138625]
  LimiX-2M is a 2M- parameter model that outperforms larger TabPFN-v2 and TabICL baselines on widely used benchmarks.<n>We present a unified tokenize-and-route framework for strong Tabular foundation models (TFMs)<n>Results highlight value-aware tokenization and readout-aligned routing as key levers for improving the accuracy--efficiency trade-off in TFMs.
  arXiv  Detail & Related papers  (2026-06-03T06:07:33Z)
• Prefix-Adaptive Block Diffusion for Efficient Document Recognition [52.15352911463151]
  Block Diffusion Models (BDMs) support parallel generation, flexible-length output, and KV caching, making them promising for efficient document parsing.<n>We propose the Prefix- Block Diffusion Model (PA-BDM) which replaces intra-block bidirectional denoising with causal denoising from prefix to suffix.<n> Experiments show that the 3B PA-BDM achieves higher recognition scores on several benchmarks and improves inference throughput by 71.6% over the 2.5B MinerU-Diffusion.
  arXiv  Detail & Related papers  (2026-05-16T07:50:13Z)
• Towards Remote Sensing Change Detection with Neural Memory [61.39582645714727]
  ChangeTitans is a Titans-based framework for remote sensing change detection.<n>First, we propose VTitans, which integrates neural memory with segmented local attention.<n>Second, we present a hierarchical VTitans-Adapter to refine multi-scale features across different network layers.<n>Third, we introduce TS-CBAM, a two-stream fusion module, to suppress pseudo-changes and enhance detection accuracy.
  arXiv  Detail & Related papers  (2026-02-11T03:50:51Z)
• HA2F: Dual-module Collaboration-Guided Hierarchical Adaptive Aggregation Framework for Remote Sensing Change Detection [17.445747802237836]
  We propose HA2F, which consists of dynamic hierarchical feature calibration module (DHFCM) and noise-adaptive feature alignment module (NAFRM)<n>Experiments verify the effectiveness of the proposed HA2F, which achieves state-of-the-art performance on LEVI-CD, WHU-CD, and SYSU-CD datasets.
  arXiv  Detail & Related papers  (2026-01-23T09:21:11Z)
• Morphing Through Time: Diffusion-Based Bridging of Temporal Gaps for Robust Alignment in Change Detection [51.56484100374058]
  We introduce a modular pipeline that improves spatial and temporal robustness without altering existing change detection networks.<n>A diffusion module synthesizes intermediate morphing frames that bridge large appearance gaps, enabling RoMa to estimate stepwise correspondences.<n>Experiments on LEVIR-CD, WHU-CD, and DSIFN-CD show consistent gains in both registration accuracy and downstream change detection.
  arXiv  Detail & Related papers  (2025-11-11T08:40:28Z)
• RatioWaveNet: A Learnable RDWT Front-End for Robust and Interpretable EEG Motor-Imagery Classification [1.4069478981641936]
  We present RatioWaveNet, which augments a strong temporal CNN-Transformer backbone with a trainable, Rationally-Dilated Wavelet Transform front end.<n>Our goal is to test whether this principled wavelet front end improves robustness precisely where BCIs typically fail.
  arXiv  Detail & Related papers  (2025-10-22T14:04:03Z)
• Deep Metric Learning for Unsupervised Remote Sensing Change Detection [60.89777029184023]
  Remote Sensing Change Detection (RS-CD) aims to detect relevant changes from Multi-Temporal Remote Sensing Images (MT-RSIs) The performance of existing RS-CD methods is attributed to training on large annotated datasets. This paper proposes an unsupervised CD method based on deep metric learning that can deal with both of these issues.
  arXiv  Detail & Related papers  (2023-03-16T17:52:45Z)
• Efficient Decoder-free Object Detection with Transformers [75.00499377197475]
  Vision transformers (ViTs) are changing the landscape of object detection approaches. We propose a decoder-free fully transformer-based (DFFT) object detector. DFFT_SMALL achieves high efficiency in both training and inference stages.
  arXiv  Detail & Related papers  (2022-06-14T13:22:19Z)

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.