paper-with-me

홈 › Papers

Differencing based Self-supervised pretraining for Scene Change Detection

2022-08-11 · Vijaya Raghavan T. Ramkumar, Elahe Arani, Bahram Zonooz

Scene change detection (SCD), a crucial perception task, identifies changes by comparing scenes captured at different times. SCD is challenging due to noisy changes in illumination, seasonal variations, and perspective differences across a pair of views. Deep neural network based solutions require a large quantity of annotated data which is tedious and expensive to obtain. On the other hand, transfer learning from large datasets induces domain shift. To address these challenges, we propose a novel \textit{Differencing self-supervised pretraining (DSP)} method that uses feature differencing to learn discriminatory representations corresponding to the changed regions while simultaneously tackling the noisy changes by enforcing temporal invariance across views. Our experimental results on SCD datasets demonstrate the effectiveness of our method, specifically to differences in camera viewpoints and lighting conditions. Compared against the self-supervised Barlow Twins and the standard ImageNet pretraining that uses more than a million additional labeled images, DSP can surpass it without using any additional data. Our results also demonstrate the robustness of DSP to natural corruptions, distribution shift, and learning under limited labeled data.

📄 PDF Abstract BibTeX arXiv:2208.05838

Code (1)

neurai-lab/dsp 공식 구현 pytorch

Tasks

Change DetectionScene Change DetectionTransfer Learning

Methods 이 논문이 사용한 방법론

Barlow Twins Barlow Twins is a self-supervised learning method that applies redundancy-reduction — a principle first proposed in neuroscience — to self supervised learning. The objective…

Similar Papers 제목 키워드 기반

CASTing Your Model: Learning to Localize Improves Self-Supervised Representations

2020-12-08 · CVPR 2021 1 · Ramprasaath R. Selvaraju, Karan Desai, Justin Johnson, Nikhil Naik

Recent advances in self-supervised learning (SSL) have largely closed the gap with supervised ImageNet pretraining. Despite their success these methods have been primarily applied to unlabeled ImageNet images, and show m…

Self-Supervised LearningVisual Grounding

Supervising Remote Sensing Change Detection Models with 3D Surface Semantics

2022-02-26 · Isaac Corley, Peyman Najafirad

Remote sensing change detection, identifying changes between scenes of the same location, is an active area of research with a broad range of applications. Recent advances in multimodal self-supervised pretraining have r…

Change DetectionRepresentation Learning

How Useful is Self-Supervised Pretraining for Visual Tasks?

2020-03-31 · CVPR 2020 6 · Alejandro Newell, Jia Deng

Recent advances have spurred incredible progress in self-supervised pretraining for vision. We investigate what factors may play a role in the utility of these pretraining methods for practitioners. To do this, we evalua…

Linear evaluation

Stateful Visual Encoders for Vision-Language Models

2026-06-03 · Zirui Wang, Junwei Yu, Adam Yala, David M. Chan 외 arxiv

Vision-language models (VLMs) are increasingly used in multi-image, multi-turn agentic settings where decisions depend on visual changes. However, in existing open-weight VLMs, visual comparisons happen only inside the l…

Self-Supervised Pretraining Improves Self-Supervised Pretraining

2021-03-23 · Colorado J. Reed, Xiangyu Yue, Ani Nrusimha, Sayna Ebrahimi 외

While self-supervised pretraining has proven beneficial for many computer vision tasks, it requires expensive and lengthy computation, large amounts of data, and is sensitive to data augmentation. Prior work demonstrates…

Data AugmentationImage Augmentation