DeepAI AI Chat
Log In Sign Up

PosNeg-Balanced Anchors with Aligned Features for Single-Shot Object Detection

by   Qiankun Tang, et al.
Institute of Computing Technology, Chinese Academy of Sciences

We introduce a novel single-shot object detector to ease the imbalance of foreground-background class by suppressing the easy negatives while increasing the positives. To achieve this, we propose an Anchor Promotion Module (APM) which predicts the probability of each anchor as positive and adjusts their initial locations and shapes to promote both the quality and quantity of positive anchors. In addition, we design an efficient Feature Alignment Module (FAM) to extract aligned features for fitting the promoted anchors with the help of both the location and shape transformation information from the APM. We assemble the two proposed modules to the backbone of VGG-16 and ResNet-101 network with an encoder-decoder architecture. Extensive experiments on MS COCO well demonstrate our model performs competitively with alternative methods (40.0% mAP on test-dev set) and runs faster (28.6 fps).


page 4

page 6


Single-Shot Refinement Neural Network for Object Detection

For object detection, the two-stage approach (e.g., Faster R-CNN) has be...

Balance-Oriented Focal Loss with Linear Scheduling for Anchor Free Object Detection

Most existing object detectors suffer from class imbalance problems that...

Semi-Anchored Detector for One-Stage Object Detection

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

Single-Shot Object Detection with Enriched Semantics

We propose a novel single shot object detection network named Detection ...

Efficient Decoder-free Object Detection with Transformers

Vision transformers (ViTs) are changing the landscape of object detectio...

LapNet : Automatic Balanced Loss and Optimal Assignment for Real-Time Dense Object Detection

Several modern deep single-stage object detectors are really effective f...

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...