An official website of the United States government
Two-branch network architecture has shown its efficiency and effectiveness in real-time semantic segmentation tasks. However, direct fusion of high-resolution details and low-frequency context has the drawback of detailed features being easily overwhelmed by surrounding contextual information. This overshoot phenomenon limits the improvement of the segmentation accuracy of existing two-branch mod- els. In this paper, we make a connection between Convolutional Neural Networks (CNN) and Proportional-Integral-Derivative (PID) controllers and reveal that a two-branch network is equivalent to a Proportional-Integral (PI) controller, which inherently suffers from similar overshoot issues. To alleviate this problem, we propose a novel three- branch network architecture: PIDNet, which contains three branches to parse detailed, context and boundary information, respectively, and employs boundary attention to guide the fusion of detailed and context branches. Our family of PIDNets achieve the best trade-off between inference speed and accuracy and their accuracy surpasses all the existing models with similar inference speed on the Cityscapes and CamVid datasets. Specifically, PIDNet-S achieves 78.6% mIOU with inference speed of 93.2 FPS on Cityscapes and 80.1% mIOU with speed of 153.7 FPS on CamVid.
more »
« less
Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Video
We present Accel, a novel semantic video segmentation system that achieves high accuracy at low inference cost by combining the predictions of two network branches: (1) a reference branch that extracts high-detail features on a reference keyframe, and warps these features forward using frame-to-frame optical flow estimates, and (2) an update branch that computes features of adjustable quality on the current frame, performing a temporal update at each video frame. The modularity of the update branch, where feature subnetworks of varying layer depth can be inserted (e.g. ResNet-18 to ResNet-101), enables operation over a new, state-of-the-art accuracy-throughput trade-off spectrum. Over this curve, Accel models achieve both higher accuracy and faster inference times than the closest comparable single-frame segmentation networks. In general, Accel significantly outperforms previous work on efficient semantic video segmentation, correcting warping-related error that compounds on datasets with complex dynamics. Accel is end-to-end trainable and highly modular: the reference network, the optical flow network, and the update network can each be selected independently, depending on application requirements, and then jointly fine-tuned. The result is a robust, general system for fast, high-accuracy semantic segmentation on video
more »
« less
- Award ID(s):
- 1846431
- PAR ID:
- 10166381
- Date Published:
- Journal Name:
- IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Page Range / eLocation ID:
- 8858 to 8867
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
We present an architecture for online, incremental scene modeling which combines a SLAM-based scene understanding framework with semantic segmentation and object pose estimation. The core of this approach comprises a probabilistic inference scheme that predicts semantic labels for object hypotheses at each new frame. From these hypotheses, recognized scene structures are incrementally constructed and tracked. Semantic labels are inferred using a multi-domain convolutional architecture which operates on the image time series and which enables efficient propagation of features as well as robust model registration. To evaluate this architecture, we introduce a large-scale RGB-D dataset JHUSEQ-25 as a new benchmark for the sequence-based scene understanding in complex and densely cluttered scenes. This dataset contains 25 RGB-D video sequences with 100,000 labeled frames in total. We validate our method on this dataset and demonstrate improved performance of semantic segmentation and 6-DoF object pose estimation compared with methods based on the single view.more » « less
-
There is considerable interest in AI systems that can assist a cardiologist to diagnose echocardiograms, and can also be used to train residents in classifying echocardiograms. Prior work has focused on the analysis of a single frame. Classifying echocardiograms at the video-level is challenging due to intra-frame and inter-frame noise. We propose a two-stream deep network which learns from the spatial context and optical flow for the classification of echocardiography videos. Each stream contains two parts: a Convolutional Neural Network (CNN) for spatial features and a bi-directional Long Short-Term Memory (LSTM) network with Attention for temporal. The features from these two streams are fused for classification. We verify our experimental results on a dataset of 170 (80 normal and 90 abnormal) videos that have been manually labeled by trained cardiologists. Our method provides an overall accuracy of 91:18%, with a sensitivity of 94:11% and a specificity of 88:24%.more » « less
-
Semantic segmentation for scene understanding is nowadays widely demanded, raising significant challenges for the algorithm efficiency, especially its applications on resource-limited platforms. Current segmentation models are trained and evaluated on massive high-resolution scene images (“data-level”) and suffer from the expensive computation arising from the required multi-scale aggregation (“network level”). In both folds, the computational and energy costs in training and inference are notable due to the often desired large input resolutions and heavy computational burden of segmentation models. To this end, we propose DANCE, general automated DA ta- N etwork C o-optimization for E fficient segmentation model training and inference . Distinct from existing efficient segmentation approaches that focus merely on light-weight network design, DANCE distinguishes itself as an automated simultaneous data-network co-optimization via both input data manipulation and network architecture slimming. Specifically, DANCE integrates automated data slimming which adaptively downsamples/drops input images and controls their corresponding contribution to the training loss guided by the images’ spatial complexity. Such a downsampling operation, in addition to slimming down the cost associated with the input size directly, also shrinks the dynamic range of input object and context scales, therefore motivating us to also adaptively slim the network to match the downsampled data. Extensive experiments and ablating studies (on four SOTA segmentation models with three popular segmentation datasets under two training settings) demonstrate that DANCE can achieve “all-win” towards efficient segmentation (reduced training cost, less expensive inference, and better mean Intersection-over-Union (mIoU)). Specifically, DANCE can reduce ↓25%–↓77% energy consumption in training, ↓31%–↓56% in inference, while boosting the mIoU by ↓0.71%–↑ 13.34%.more » « less
-
We propose Vision Token Turing Machines (ViTTM), an efficient, low-latency, memory-augmented Vision Transformer (ViT). Our approach builds on Neural Turing Machines and Token Turing Machines, which were applied to NLP and sequential visual understanding tasks. ViTTMs are designed for non-sequential computer vision tasks such as image classification and segmentation. Our model creates two sets of tokens: process tokens and memory tokens; process tokens pass through encoder blocks and read-write from memory tokens at each encoder block in the network, allowing them to store and retrieve information from memory. By ensuring that there are fewer process tokens than memory tokens, we are able to reduce the inference time of the network while maintaining its accuracy. On ImageNet-1K, the state-of-the-art ViT-B has median latency of 529.5ms and 81.0% accuracy, while our ViTTM-B is 56% faster (234.1ms), with 2.4 times fewer FLOPs, with an accuracy of 82.9%. On ADE20K semantic segmentation, ViT-B achieves 45.65mIoU at 13.8 frame-per-second (FPS) whereas our ViTTM-B model acheives a 45.17 mIoU with 26.8 FPS (+94%).more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/CVPR.2019.00907
