SCNet: Training Inference Sample Consistency for Instance Segmentation

• URL: http://arxiv.org/abs/2012.10150v1
• Date: Fri, 18 Dec 2020 10:26:54 GMT
• Title: SCNet: Training Inference Sample Consistency for Instance Segmentation
• Authors: Thang Vu, Haeyong Kang, Chang D. Yoo
• Abstract summary: This paper proposes an architecture referred to as Sample Consistency Network (SCNet) to ensure that the IoU distribution of the samples at training time is close to that at inference time. Experiments on the standard dataset reveal the effectiveness of the proposed method over multiple evaluation metrics, including box AP, mask AP, and inference speed.
• Score: 15.963615360741356
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Cascaded architectures have brought significant performance improvement in object detection and instance segmentation. However, there are lingering issues regarding the disparity in the Intersection-over-Union (IoU) distribution of the samples between training and inference. This disparity can potentially exacerbate detection accuracy. This paper proposes an architecture referred to as Sample Consistency Network (SCNet) to ensure that the IoU distribution of the samples at training time is close to that at inference time. Furthermore, SCNet incorporates feature relay and utilizes global contextual information to further reinforce the reciprocal relationships among classifying, detecting, and segmenting sub-tasks. Extensive experiments on the standard COCO dataset reveal the effectiveness of the proposed method over multiple evaluation metrics, including box AP, mask AP, and inference speed. In particular, while running 38\% faster, the proposed SCNet improves the AP of the box and mask predictions by respectively 1.3 and 2.3 points compared to the strong Cascade Mask R-CNN baseline. Code is available at \url{https://github.com/thangvubk/SCNet}.

Related papers

• Efficiently Expanding Receptive Fields: Local Split Attention and Parallel Aggregation for Enhanced Large-scale Point Cloud Semantic Segmentation [7.199090922071512]
  We propose the Local Split Attention Pooling (LSAP) mechanism to effectively expand the receptive field through a series of local split operations. We put forth a novel framework, designated as LSNet, for large-scale point cloud semantic segmentation. LSNet demonstrated superior performance compared to state-of-the-art semantic segmentation networks on three benchmark datasets.
  arXiv  Detail & Related papers  (2024-09-03T07:10:20Z)
• DiTMoS: Delving into Diverse Tiny-Model Selection on Microcontrollers [34.282971510732736]
  We introduce DiTMoS, a novel DNN training and inference framework with a selector-classifiers architecture. A composition of weak models can exhibit high diversity and the union of them can significantly boost the accuracy upper bound. We deploy DiTMoS on the Neucleo STM32F767ZI board and evaluate it based on three time-series datasets for human activity recognition, keywords spotting, and emotion recognition.
  arXiv  Detail & Related papers  (2024-03-14T02:11:38Z)
• Multi-Base Station Cooperative Sensing with AI-Aided Tracking [10.400855135405251]
  We investigate a joint sensing and communication network consisting of multiple base stations (BSs) that cooperate through a fusion center (FC) We show that our framework could provide remarkable sensing performance, achieving an optimal sub-pattern assignment (OSPA) less than 60 cm.
  arXiv  Detail & Related papers  (2023-10-31T12:27:48Z)
• SVNet: Where SO(3) Equivariance Meets Binarization on Point Cloud Representation [65.4396959244269]
  The paper tackles the challenge by designing a general framework to construct 3D learning architectures. The proposed approach can be applied to general backbones like PointNet and DGCNN. Experiments on ModelNet40, ShapeNet, and the real-world dataset ScanObjectNN, demonstrated that the method achieves a great trade-off between efficiency, rotation, and accuracy.
  arXiv  Detail & Related papers  (2022-09-13T12:12:19Z)
• Receptive Field-based Segmentation for Distributed CNN Inference Acceleration in Collaborative Edge Computing [93.67044879636093]
  We study inference acceleration using distributed convolutional neural networks (CNNs) in collaborative edge computing network. We propose a novel collaborative edge computing using fused-layer parallelization to partition a CNN model into multiple blocks of convolutional layers.
  arXiv  Detail & Related papers  (2022-07-22T18:38:11Z)
• A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection [59.21990697929617]
  Humans tend to mine objects by learning from a group of images or several frames of video since we live in a dynamic world. Previous approaches design different networks on similar tasks separately, and they are difficult to apply to each other. We introduce a unified framework to tackle these issues, term as UFO (UnifiedObject Framework for Co-Object Framework)
  arXiv  Detail & Related papers  (2022-03-09T13:35:19Z)
• Semi-supervised Domain Adaptive Structure Learning [72.01544419893628]
  Semi-supervised domain adaptation (SSDA) is a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains. We introduce an adaptive structure learning method to regularize the cooperation of SSL and DA.
  arXiv  Detail & Related papers  (2021-12-12T06:11:16Z)
• HS3: Learning with Proper Task Complexity in Hierarchically Supervised Semantic Segmentation [81.87943324048756]
  We propose Hierarchically Supervised Semantic (HS3), a training scheme that supervises intermediate layers in a segmentation network to learn meaningful representations by varying task complexity. Our proposed HS3-Fuse framework further improves segmentation predictions and achieves state-of-the-art results on two large segmentation benchmarks: NYUD-v2 and Cityscapes.
  arXiv  Detail & Related papers  (2021-11-03T16:33:29Z)
• Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentation [76.2621758731288]
  We tackle the detection of out-of-distribution (OOD) objects in semantic segmentation. Our main contribution is a new OOD detection architecture called ObsNet associated with a dedicated training scheme based on Local Adversarial Attacks (LAA) We show it obtains top performances both in speed and accuracy when compared to ten recent methods of the literature on three different datasets.
  arXiv  Detail & Related papers  (2021-08-03T17:09:56Z)
• supervised adptive threshold network for instance segmentation [4.347876036795798]
  Mask R-CNN method based on adaptive threshold. layered adaptive network structure. adaptive feature pool. Experiments on benchmark data sets indicate that the effectiveness of the proposed model.
  arXiv  Detail & Related papers  (2021-06-07T09:25:44Z)
• Weakly Supervised Instance Segmentation by Deep Community Learning [39.18749732409763]
  We present a weakly supervised instance segmentation algorithm based on deep community learning with multiple tasks. We address this problem by designing a unified deep neural network architecture. The proposed algorithm achieves state-of-the-art performance in the weakly supervised setting.
  arXiv  Detail & Related papers  (2020-01-30T08:35:42Z)

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.