FakeMix Augmentation Improves Transparent Object Detection
- URL: http://arxiv.org/abs/2103.13279v1
- Date: Wed, 24 Mar 2021 15:51:37 GMT
- Title: FakeMix Augmentation Improves Transparent Object Detection
- Authors: Yang Cao, Zhengqiang Zhang, Enze Xie, Qibin Hou, Kai Zhao, Xiangui
Luo, Jian Tuo
- Abstract summary: We propose a novel content-dependent data augmentation method termed FakeMix to overcome the boundary-related imbalance problem.
We also present AdaptiveASPP, an enhanced version of ASPP, that can capture multi-scale and cross-modality features dynamically.
- Score: 24.540569928274984
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Detecting transparent objects in natural scenes is challenging due to the low
contrast in texture, brightness and colors. Recent deep-learning-based works
reveal that it is effective to leverage boundaries for transparent object
detection (TOD). However, these methods usually encounter boundary-related
imbalance problem, leading to limited generation capability. Detailly, a kind
of boundaries in the background, which share the same characteristics with
boundaries of transparent objects but have much smaller amounts, usually hurt
the performance. To conquer the boundary-related imbalance problem, we propose
a novel content-dependent data augmentation method termed FakeMix. Considering
collecting these trouble-maker boundaries in the background is hard without
corresponding annotations, we elaborately generate them by appending the
boundaries of transparent objects from other samples into the current image
during training, which adjusts the data space and improves the generalization
of the models. Further, we present AdaptiveASPP, an enhanced version of ASPP,
that can capture multi-scale and cross-modality features dynamically. Extensive
experiments demonstrate that our methods clearly outperform the
state-of-the-art methods. We also show that our approach can also transfer well
on related tasks, in which the model meets similar troubles, such as mirror
detection, glass detection, and camouflaged object detection. Code will be made
publicly available.
Related papers
- ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection [70.11264880907652]
Recent object (COD) attempts to segment objects visually blended into their surroundings, which is extremely complex and difficult in real-world scenarios.
We propose an effective unified collaborative pyramid network that mimics human behavior when observing vague images and camouflaged zooming in and out.
Our framework consistently outperforms existing state-of-the-art methods in image and video COD benchmarks.
arXiv Detail & Related papers (2023-10-31T06:11:23Z) - TransTouch: Learning Transparent Objects Depth Sensing Through Sparse
Touches [23.87056600709768]
We propose a method to finetune a stereo network with sparse depth labels automatically collected using a probing system with tactile feedback.
We show that our method can significantly improve real-world depth sensing accuracy, especially for transparent objects.
arXiv Detail & Related papers (2023-09-18T01:55:17Z) - Towards General Visual-Linguistic Face Forgery Detection [95.73987327101143]
Deepfakes are realistic face manipulations that can pose serious threats to security, privacy, and trust.
Existing methods mostly treat this task as binary classification, which uses digital labels or mask signals to train the detection model.
We propose a novel paradigm named Visual-Linguistic Face Forgery Detection(VLFFD), which uses fine-grained sentence-level prompts as the annotation.
arXiv Detail & Related papers (2023-07-31T10:22:33Z) - A bioinspired three-stage model for camouflaged object detection [8.11866601771984]
We propose a three-stage model that enables coarse-to-fine segmentation in a single iteration.
Our model employs three decoders to sequentially process subsampled features, cropped features, and high-resolution original features.
Our network surpasses state-of-the-art CNN-based counterparts without unnecessary complexities.
arXiv Detail & Related papers (2023-05-22T02:01:48Z) - CamDiff: Camouflage Image Augmentation via Diffusion Model [83.35960536063857]
CamDiff is a novel approach to synthesize salient objects in camouflaged scenes.
We leverage the latent diffusion model to synthesize salient objects in camouflaged scenes.
Our approach enables flexible editing and efficient large-scale dataset generation at a low cost.
arXiv Detail & Related papers (2023-04-11T19:37:47Z) - Multitask AET with Orthogonal Tangent Regularity for Dark Object
Detection [84.52197307286681]
We propose a novel multitask auto encoding transformation (MAET) model to enhance object detection in a dark environment.
In a self-supervision manner, the MAET learns the intrinsic visual structure by encoding and decoding the realistic illumination-degrading transformation.
We have achieved the state-of-the-art performance using synthetic and real-world datasets.
arXiv Detail & Related papers (2022-05-06T16:27:14Z) - High-resolution Iterative Feedback Network for Camouflaged Object
Detection [128.893782016078]
Spotting camouflaged objects that are visually assimilated into the background is tricky for object detection algorithms.
We aim to extract the high-resolution texture details to avoid the detail degradation that causes blurred vision in edges and boundaries.
We introduce a novel HitNet to refine the low-resolution representations by high-resolution features in an iterative feedback manner.
arXiv Detail & Related papers (2022-03-22T11:20:21Z) - Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object
Detection [0.0]
We propose a mixed-scale triplet network, bf ZoomNet, which mimics the behavior of humans when observing vague images.
Specifically, our ZoomNet employs the zoom strategy to learn the discriminative mixed-scale semantics by the designed scale integration unit and hierarchical mixed-scale unit.
Our proposed highly task-friendly model consistently surpasses the existing 23 state-of-the-art methods on four public datasets.
arXiv Detail & Related papers (2022-03-05T09:13:52Z) - Segmenting Transparent Objects in the Wild [98.80906604285163]
This work proposes a large-scale dataset for transparent object segmentation, named Trans10K, consisting of 10,428 images of real scenarios with carefully manual annotations.
To evaluate the effectiveness of Trans10K, we propose a novel boundary-aware segmentation method, termed TransLab, which exploits boundary as the clue to improve segmentation of transparent objects.
arXiv Detail & Related papers (2020-03-31T04:44:31Z)
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.