paper-with-me

홈 › Papers

RRNet: Repetition-Reduction Network for Energy Efficient Decoder of Depth Estimation

2019-07-23 · Sang-Yun Oh, Hye-Jin S. Kim, Jongeun Lee, Junmo Kim

We introduce Repetition-Reduction network (RRNet) for resource-constrained depth estimation, offering significantly improved efficiency in terms of computation, memory and energy consumption. The proposed method is based on repetition-reduction (RR) blocks. The RR blocks consist of the set of repeated convolutions and the residual connection layer that take place of the pointwise reduction layer with linear connection to the decoder. The RRNet help reduce memory usage and power consumption in the residual connections to the decoder layers. RRNet consumes approximately 3.84 times less energy and 3.06 times less meory and is approaximately 2.21 times faster, without increasing the demand on hardware resource relative to the baseline network (Godard et al, CVPR'17), outperforming current state-of-the-art lightweight architectures such as SqueezeNet, ShuffleNet, MobileNet and PyDNet.

📄 PDF Abstract BibTeX arXiv:1907.09707

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderDepth Estimation

Methods 이 논문이 사용한 방법론

Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution …
Inverted Residual Block 설명 없음
Tether Customer Service Number +1-833-534-1729 설명 없음
Grouped Convolution A Grouped Convolution uses a group of convolutions - multiple kernels per layer - resulting in multiple channel outputs per layer. This leads to wider networks helping a…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Batch Normalization 설명 없음
Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…

Similar Papers 제목 키워드 기반

RRNet: Towards ReLU-Reduced Neural Network for Two-party Computation Based Private Inference

2023-02-05 · Hongwu Peng, Shanglin Zhou, Yukui Luo, Nuo Xu 외

The proliferation of deep learning (DL) has led to the emergence of privacy and security concerns. To address these issues, secure Two-party computation (2PC) has been proposed as a means of enabling privacy-preserving D…

Privacy Preserving

RRNet: Configurable Real-Time Video Enhancement with Arbitrary Local Lighting Variations

2026-01-05 · Wenlong Yang, Canran Jin, Weihang Yuan, Chao Wang 외 arxiv

With the growing demand for real-time video enhancement in live applications, existing methods often struggle to balance speed and effective exposure control, particularly under uneven lighting. We introduce RRNet (Rende…

Video Enhancement

DRRNet: Macro-Micro Feature Fusion and Dual Reverse Refinement for Camouflaged Object Detection

2025-05-14 · Jianlin Sun, Xiaolin Fang, Juwei Guan, Dongdong Gui 외

The core challenge in Camouflage Object Detection (COD) lies in the indistinguishable similarity between targets and backgrounds in terms of color, texture, and shape. This causes existing methods to either lose edge det…

object-detectionObject DetectionScene Understanding

Uncertainty-Guided Inference-Time Depth Adaptation for Transformer-Based Visual Tracking

2026-02-18 · Patrick Poggi, Divake Kumar, Theja Tulabandhula, Amit Ranjan Trivedi arxiv

Transformer-based single-object trackers achieve state-of-the-art accuracy but rely on fixed-depth inference, executing the full encoder--decoder stack for every frame regardless of visual complexity, thereby incurring u…

Knowledge DistillationVisual Tracking

Overcoming Decoder Inconsistencies in Whisper for Dravidian and Low-Resource Languages

2026-06-08 · Chowdam Venkata Kumar, Kumud Tripathi, Pankaj Wasnik arxiv

Multilingual ASR models such as Whisper perform well on high-resource languages but exhibit substantially higher Word Error Rates (WER) for Dravidian languages compared to Indo-Aryan ones. Through linguistic and dataset …