Propose-and-Attend Single Shot Detector

07/30/2019
by   Ho-Deok Jang, et al.
0

We present a simple yet effective prediction module for a one-stage detector. The main process is conducted in a coarse-to-fine manner. First, the module roughly adjusts the default boxes to well capture the extent of target objects in an image. Second, given the adjusted boxes, the module aligns the receptive field of the convolution filters accordingly, not requiring any embedding layers. Both steps build a propose-and-attend mechanism, mimicking two-stage detectors in a highly efficient manner. To verify its effectiveness, we apply the proposed module to a basic one-stage detector SSD. Our final model achieves an accuracy comparable to that of state-of-the-art detectors while using a fraction of their model parameters and computational overheads. Moreover, we found that the proposed module has two strong applications. 1) The module can be successfully integrated into a lightweight backbone, further pushing the efficiency of the one-stage detector. 2) The module also allows train-from-scratch without relying on any sophisticated base networks as previous methods do.

READ FULL TEXT
research
03/28/2023

STMixer: A One-Stage Sparse Action Detector

Traditional video action detectors typically adopt the two-stage pipelin...
research
09/18/2017

StairNet: Top-Down Semantic Aggregation for Accurate One Shot Detection

One-stage object detectors such as SSD or YOLO already have shown promis...
research
11/21/2017

Receptive Field Block Net for Accurate and Fast Object Detection

Current top-performing object detectors depend on deep CNN backbones, su...
research
08/03/2022

YOLO-FaceV2: A Scale and Occlusion Aware Face Detector

In recent years, face detection algorithms based on deep learning have m...
research
07/10/2021

CSL-YOLO: A New Lightweight Object Detection System for Edge Computing

The development of lightweight object detectors is essential due to the ...
research
10/05/2018

Decoupled Classification Refinement: Hard False Positive Suppression for Object Detection

In this paper, we analyze failure cases of state-of-the-art detectors an...
research
01/04/2020

Pixel-Semantic Revise of Position Learning A One-Stage Object Detector with A Shared Encoder-Decoder

We analyze that different methods based channel or position attention me...

Please sign up or login with your details

Forgot password? Click here to reset