CamoFormer: Masked Separable Attention for Camouflaged Object Detection
- URL: http://arxiv.org/abs/2212.06570v1
- Date: Sat, 10 Dec 2022 10:03:27 GMT
- Title: CamoFormer: Masked Separable Attention for Camouflaged Object Detection
- Authors: Bowen Yin and Xuying Zhang and Qibin Hou and Bo-Yuan Sun and Deng-Ping
Fan and Luc Van Gool
- Abstract summary: We present a simple masked separable attention (MSA) for camouflaged object detection.
We first separate the multi-head self-attention into three parts, which are responsible for distinguishing the camouflaged objects from the background using different mask strategies.
We propose to capture high-resolution semantic representations progressively based on a simple top-down decoder with the proposed MSA to attain precise segmentation results.
- Score: 94.2870722866853
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: How to identify and segment camouflaged objects from the background is
challenging. Inspired by the multi-head self-attention in Transformers, we
present a simple masked separable attention (MSA) for camouflaged object
detection. We first separate the multi-head self-attention into three parts,
which are responsible for distinguishing the camouflaged objects from the
background using different mask strategies. Furthermore, we propose to capture
high-resolution semantic representations progressively based on a simple
top-down decoder with the proposed MSA to attain precise segmentation results.
These structures plus a backbone encoder form a new model, dubbed CamoFormer.
Extensive experiments show that CamoFormer surpasses all existing
state-of-the-art methods on three widely-used camouflaged object detection
benchmarks. There are on average around 5% relative improvements over previous
methods in terms of S-measure and weighted F-measure.
Related papers
- Toward Realistic Camouflaged Object Detection: Benchmarks and Method [11.279532701331647]
Camouflaged object detection (COD) primarily relies on semantic or instance segmentation methods.
We propose a camouflage-aware feature refinement (CAFR) strategy to detect camouflaged objects.
CAFR fully utilizes a clear perception of the current object within the prior knowledge of large models to assist detectors in deeply understanding the distinctions between background and foreground.
arXiv Detail & Related papers (2025-01-13T13:04:00Z) - CGCOD: Class-Guided Camouflaged Object Detection [19.959268087062217]
We introduce class-guided camouflaged object detection (CGCOD), which extends traditional COD task by incorporating object-specific class knowledge.
We propose a multi-stage framework, CGNet, which incorporates a plug-and-play class prompt generator and a simple yet effective class-guided detector.
This establishes a new paradigm for COD, bridging the gap between contextual understanding and class-guided detection.
arXiv Detail & Related papers (2024-12-25T19:38:32Z) - Unconstrained Salient and Camouflaged Object Detection [4.698538612738126]
We introduce a benchmark called Unconstrained Salient and Camouflaged Object Detection (USCOD)
USCOD supports the simultaneous detection of salient and camouflaged objects in unconstrained scenes, regardless of their presence.
To address this challenge, we propose USCNet, a baseline model for USCOD that decouples the learning of attribute distinction from mask reconstruction.
arXiv Detail & Related papers (2024-12-14T19:37:17Z) - MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders [93.87585467898252]
We design MonoMAE, a monocular 3D detector inspired by Masked Autoencoders.
MonoMAE consists of two novel designs. The first is depth-aware masking that selectively masks certain parts of non-occluded object queries.
The second is lightweight query completion that works with the depth-aware masking to learn to reconstruct and complete the masked object queries.
arXiv Detail & Related papers (2024-05-13T12:32:45Z) - Camouflaged Image Synthesis Is All You Need to Boost Camouflaged
Detection [65.8867003376637]
We propose a framework for synthesizing camouflage data to enhance the detection of camouflaged objects in natural scenes.
Our approach employs a generative model to produce realistic camouflage images, which can be used to train existing object detection models.
Our framework outperforms the current state-of-the-art method on three datasets.
arXiv Detail & Related papers (2023-08-13T06:55:05Z) - Referring Camouflaged Object Detection [97.90911862979355]
Ref-COD aims to segment specified camouflaged objects based on a small set of referring images with salient target objects.
We first assemble a large-scale dataset, called R2C7K, which consists of 7K images covering 64 object categories in real-world scenarios.
arXiv Detail & Related papers (2023-06-13T04:15:37Z) - Towards Deeper Understanding of Camouflaged Object Detection [64.81987999832032]
We argue that the binary segmentation setting fails to fully understand the concept of camouflage.
We present the first triple-task learning framework to simultaneously localize, segment and rank camouflaged objects.
arXiv Detail & Related papers (2022-05-23T14:26:18Z) - Simultaneously Localize, Segment and Rank the Camouflaged Objects [55.46101599577343]
Camouflaged object detection aims to segment camouflaged objects hiding in their surroundings.
We argue that explicitly modeling the conspicuousness of camouflaged objects against their particular backgrounds can lead to a better understanding about camouflage and evolution of animals.
We present the first ranking based COD network (Rank-Net) to simultaneously localize, segment and rank camouflaged objects.
arXiv Detail & Related papers (2021-03-06T02:53:36Z)
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.