# Retrospective Memory for Camouflaged Object Detection

arXiv: https://arxiv.org/abs/2506.15244 · HTML: https://mlsanity.com/paper/2506.15244/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 62 references that are in the map.
- First posted on arXiv 18 Jun 2025.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [Vision Transformer Adapter for Dense Predictions](https://mlsanity.com/paper/2205.08534/) (2022)
- [Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1904.02639/) (2019)
- [Structure-measure: A New Way to Evaluate Foreground Maps](https://mlsanity.com/paper/1708.00786/) (2017)
- [Video Object Segmentation using Space-Time Memory Networks](https://mlsanity.com/paper/1904.00607/) (2019)
- [Anabranch Network for Camouflaged Object Segmentation](https://mlsanity.com/paper/2105.09451/) (2021)
- [FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation](https://mlsanity.com/paper/1902.09513/) (2019)
- [Camouflaged Object Segmentation with Distraction Mining](https://mlsanity.com/paper/2104.10475/) (2021)
- [Video Object Segmentation with Episodic Graph Memory Networks](https://mlsanity.com/paper/2007.07020/) (2020)
- [Feature Shrinkage Pyramid for Camouflaged Object Detection with Transformers](https://mlsanity.com/paper/2303.14816/) (2023)
- [High-resolution Iterative Feedback Network for Camouflaged Object Detection](https://mlsanity.com/paper/2203.11624/) (2022)
- [SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation](https://mlsanity.com/paper/2408.08870/) (2024)
- [SoftPatch: Unsupervised Anomaly Detection with Noisy Data](https://mlsanity.com/paper/2403.14233/) (2024)
- [Exploring Deeper! Segment Anything Model with Depth Perception for Camouflaged Object Detection](https://mlsanity.com/paper/2407.12339/) (2024)
- [Learning Camouflaged Object Detection from Noisy Pseudo Label](https://mlsanity.com/paper/2407.13157/) (2024)
- [TailedCore: Few-Shot Sampling for Unsupervised Long-Tail Noisy Anomaly Detection](https://mlsanity.com/paper/2504.02775/) (2025)

## Abstract (arXiv)

Camouflaged object detection (COD) primarily focuses on learning subtle yet discriminative representations from complex scenes. Existing methods predominantly follow the parametric feedforward architecture based on static visual representation modeling. However, they lack explicit mechanisms for acquiring historical context, limiting their adaptation and effectiveness in handling challenging camouflage scenes. In this paper, we propose a recall-augmented COD architecture, namely RetroMem, which dynamically modulates camouflage pattern perception and inference by integrating relevant historical knowledge into the process. Specifically, RetroMem employs a two-stage training paradigm consisting of a learning stage and a recall stage to construct, update, and utilize memory representations effectively. During the learning stage, we design a dense multi-scale adapter (DMA) to improve the pretrained encoder's capability to capture rich multi-scale visual information with very few trainable parameters, thereby providing foundational inferences. In the recall stage, we propose a dynamic memory mechanism (DMM) and an inference pattern reconstruction (IPR). These components fully leverage the latent relationships between learned knowledge and current sample context to reconstruct the inference of camouflage patterns, thereby significantly improving the model's understanding of camouflage scenes. Extensive experiments on several widely used datasets demonstrate that our RetroMem significantly outperforms existing state-of-the-art methods.