Fast Neural Architecture Search for Lightweight Dense Prediction Networks
We present LDP, a lightweight dense prediction neural architecture search (NAS) framework. Starting from a pre-defined generic backbone, LDP applies the novel Assisted Tabu Search for efficient architecture exploration. LDP is fast and suitable for various dense estimation problems, unlike previous NAS methods that are either computational demanding or deployed only for a single subtask. The performance of LPD is evaluated on monocular depth estimation, semantic segmentation, and image super-resolution tasks on diverse datasets, including NYU-Depth-v2, KITTI, Cityscapes, COCO-stuff, DIV2K, Set5, Set14, BSD100, Urban100. Experiments show that the proposed framework yields consistent improvements on all tested dense prediction tasks, while being $5\%-315\%$ more compact in terms of the number of model parameters than prior arts.
Code (0)
등록된 구현이 없습니다.
Tasks
Depth EstimationImage Super-ResolutionMonocular Depth EstimationNeural Architecture SearchPredictionScene UnderstandingSemantic SegmentationSuper-ResolutionSimilar Papers 제목 키워드 기반
HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers
High-resolution representations (HR) are essential for dense prediction tasks such as segmentation, detection, and pose estimation. Learning HR representations is typically ignored in previous Neural Architecture Search …
image-classificationImage ClassificationNeural Architecture SearchPose Estimation+2SparseMask: Differentiable Connectivity Learning for Dense Image Prediction
In this paper, we aim at automatically searching an efficient network architecture for dense image prediction. Particularly, we follow the encoder-decoder style and focus on designing a connectivity structure for the dec…
DecoderPredictionFastFlowNet: A Lightweight Network for Fast Optical Flow Estimation
Dense optical flow estimation plays a key role in many robotic vision tasks. In the past few years, with the advent of deep learning, we have witnessed great progress in optical flow estimation. However, current networks…
DecoderGPUOptical Flow EstimationCARAFE: Content-Aware ReAssembly of FEatures
Feature upsampling is a key operation in a number of modern convolutional network architectures, e.g. feature pyramids. Its design is critical for dense prediction tasks such as object detection and semantic/instance seg…
Feature UpsamplingInstance Segmentationobject-detectionObject Detection+1Superkernel Neural Architecture Search for Image Denoising
Recent advancements in Neural Architecture Search(NAS) resulted in finding new state-of-the-art Artificial Neural Network (ANN) solutions for tasks like image classification, object detection, or semantic segmentation wi…
DenoisingGPUimage-classificationImage Classification+9