iNAS: Integral NAS for Device-Aware Salient Object Detection
Existing salient object detection (SOD) models usually focus on either backbone feature extractors or saliency heads, ignoring their relations. A powerful backbone could still achieve sub-optimal performance with a weak saliency head and vice versa. Moreover, the balance between model performance and inference latency poses a great challenge to model design, especially when considering different deployment scenarios. Considering all components in an integral neural architecture search (iNAS) space, we propose a flexible device-aware search scheme that only trains the SOD model once and quickly finds high-performance but low-latency models on multiple devices. An evolution search with latency-group sampling (LGS) is proposed to explore the entire latency area of our enlarged search space. Models searched by iNAS achieve similar performance with SOTA methods but reduce the 3.8x, 3.3x, 2.6x, 1.9x latency on Huawei Nova6 SE, Intel Core CPU, the Jetson Nano, and Nvidia Titan Xp. The code is released at https://mmcheng.net/inas/.
Code (0)
등록된 구현이 없습니다.
Tasks
CPUNeural Architecture SearchObjectobject-detectionObject DetectionSalient Object DetectionSimilar Papers 제목 키워드 기반
Synthesize Boundaries: A Boundary-aware Self-consistent Framework for Weakly Supervised Salient Object Detection
Fully supervised salient object detection (SOD) has made considerable progress based on expensive and time-consuming data with pixel-wise annotations. Recently, to relieve the labeling burden while maintaining performanc…
object-detectionObject DetectionSalient Object DetectionPositional information readout in $Ca^{2+}$ signaling
Living cells respond to spatial signals. Signal transmission to the cell interior often involves the release of second messengers like $Ca^{2+}$ . They will eventually trigger a physiological response by activating kinas…
Salient Object Detection via Integrity Learning
Although current salient object detection (SOD) works have achieved significant progress, they are limited when it comes to the integrity of the predicted salient regions. We define the concept of integrity at both a mic…
DiversityObjectobject-detectionObject Detection+1Accelerate Intermittent Deep Inference
Emerging research in edge devices and micro-controller units (MCU) enables on-device computation of Deep Learning Training and Inferencing tasks. More recently, contemporary trends focus on making the Deep Neural Net (DN…
Neural Architecture SearchSearching for Winograd-aware Quantized Networks
Lightweight architectural designs of Convolutional Neural Networks (CNNs) together with quantization have paved the way for the deployment of demanding computer vision applications on mobile devices. Parallel to this, al…
Neural Architecture SearchQuantization