Camouflaged Object Segmentation
18 papers with code • 6 benchmarks • 7 datasets
Camouflaged object segmentation (COS) or Camouflaged object detection (COD), which was originally promoted by T.-N. Le et al. (2017), aims to identify objects that conceal their texture into the surrounding environment. The high intrinsic similarities between the target object and the background make COS/COD far more challenging than the traditional object segmentation task. Also, refer to the online benchmarks on CAMO dataset, COD dataset, and online demo.
( Image source: Anabranch Network for Camouflaged Object Segmentation )
Benchmarks
These leaderboards are used to track progress in Camouflaged Object Segmentation
Most implemented papers
Camouflaged Object Segmentation with Distraction Mining
In this paper, we strive to embrace challenges towards effective and efficient COS. To this end, we develop a bio-inspired framework, termed Positioning and Focus Network (PFNet), which mimics the process of predation in nature.
Implicit Motion Handling for Video Camouflaged Object Detection
We propose a new video camouflaged object detection (VCOD) framework that can exploit both short-term dynamics and long-term temporal consistency to detect camouflaged objects from video frames.
Explicit Visual Prompting for Low-Level Structure Segmentations
Different from the previous visual prompting which is typically a dataset-level implicit embedding, our key insight is to enforce the tunable parameters focusing on the explicit visual content from each individual image, i. e., the features from frozen patch embeddings and the input's high-frequency components.
Edge-Aware Mirror Network for Camouflaged Object Detection
Existing edge-aware camouflaged object detection (COD) methods normally output the edge prediction in the early stage.
Improving existing segmentators performance with zero-shot segmentators
We release with this paper the open-source implementation of our method.
Unsupervised Camouflaged Object Segmentation as Domain Adaptation
To this end, we formulate the UCOS as a source-free unsupervised domain adaptation task (UCOS-DA), where both source labels and target labels are absent during the whole model training process.
ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection
Apart from the high intrinsic similarity between camouflaged objects and their background, objects are usually diverse in scale, fuzzy in appearance, and even severely occluded.
Bilateral Reference for High-Resolution Dichotomous Image Segmentation
It comprises two essential components: the localization module (LM) and the reconstruction module (RM) with our proposed bilateral reference (BiRef).