DeepAI AI Chat
Log In Sign Up

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

by   Qian Li, et al.
Institute of Computing Technology, Chinese Academy of Sciences

We analyze that different methods based channel or position attention mechanism give rise to different performance on scale, and some of state-of-the-art detectors applying feature pyramid are integrated with various variants convolutions with many mechanisms to enhance information, resulting in increasing runtime. This work addresses the problem by constructing an anchor-free detector with shared module consisting of encoder and decoder with attention mechanism. First, we consider different level features from backbone (e.g., ResNet-50) as the base features. Second, we feed the feature into a simple block, rather than various complex operations.Then, location and classification tasks are obtained by the detector head and classifier, respectively. At the same time, we use the semantic information to revise geometry locations. Additionally, we show that the detector is a pixel-semantic revise of position, universal, effective and simple to detect, especially, large-scale objects. More importantly, this work compares different feature processing (e.g.,mean, maximum or minimum) performance across channel. Finally,we present that our method improves detection accuracy by 3.8 AP compared to state-of-the-art MNC based ResNet-101 on the standard MSCOCO baseline.


page 1

page 6


SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization

Convolutional neural networks typically encode an input image into a ser...

Semi-Anchored Detector for One-Stage Object Detection

A standard one-stage detector is comprised of two tasks: classification ...

Differentiating Features for Scene Segmentation Based on Dedicated Attention Mechanisms

Semantic segmentation is a challenge in scene parsing. It requires both ...

Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers

Most polyp segmentation methods use CNNs as their backbone, leading to t...

FQDet: Fast-converging Query-based Detector

Recently, two-stage Deformable DETR introduced the query-based two-stage...

LiDAR-Based 3D Object Detection via Hybrid 2D Semantic Scene Generation

Bird's-Eye View (BEV) features are popular intermediate scene representa...

Propose-and-Attend Single Shot Detector

We present a simple yet effective prediction module for a one-stage dete...