Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search

02/09/2021
by   Peidong Liu, et al.
0

Designing proper loss functions for vision tasks has been a long-standing research direction to advance the capability of existing models. For object detection, the well-established classification and regression loss functions have been carefully designed by considering diverse learning challenges. Inspired by the recent progress in network architecture search, it is interesting to explore the possibility of discovering new loss function formulations via directly searching the primitive operation combinations. So that the learned losses not only fit for diverse object detection challenges to alleviate huge human efforts, but also have better alignment with evaluation metric and good mathematical convergence property. Beyond the previous auto-loss works on face recognition and image classification, our work makes the first attempt to discover new loss functions for the challenging object detection from primitive operation levels. We propose an effective convergence-simulation driven evolutionary search algorithm, called CSE-Autoloss, for speeding up the search progress by regularizing the mathematical rationality of loss candidates via convergence property verification and model optimization simulation. CSE-Autoloss involves the search space that cover a wide range of the possible variants of existing losses and discovers best-searched loss function combination within a short time (around 1.5 wall-clock days). We conduct extensive evaluations of loss function search on popular detectors and validate the good generalization capability of searched losses across diverse architectures and datasets. Our experiments show that the best-discovered loss function combinations outperform default combinations by 1.1 one-stage detectors on COCO respectively. Our searched losses are available at https://github.com/PerdonLiu/CSE-Autoloss.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/23/2020

Representation Sharing for Fast Object Detector Search and Beyond

Region Proposal Network (RPN) provides strong support for handling the s...
research
12/09/2021

Searching Parameterized AP Loss for Object Detection

Loss functions play an important role in training deep-network-based obj...
research
01/31/2020

Evolving Loss Functions With Multivariate Taylor Polynomial Parameterizations

Loss function optimization for neural networks has recently emerged as a...
research
04/19/2019

Automated Focal Loss for Image based Object Detection

Current state-of-the-art object detection algorithms still suffer the pr...
research
03/25/2021

AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks

Significant progress has been achieved in automating the design of vario...
research
03/17/2021

Revisiting the Loss Weight Adjustment in Object Detection

By definition, object detection requires a multi-task loss in order to s...
research
08/24/2022

Discovering Transferable Forensic Features for CNN-generated Images Detection

Visual counterfeits are increasingly causing an existential conundrum in...

Please sign up or login with your details

Forgot password? Click here to reset