Chair Segments: A Compact Benchmark for the Study of Object Segmentation

12/02/2020
by   Leticia Pinto-Alva, et al.
0

Over the years, datasets and benchmarks have had an outsized influence on the design of novel algorithms. In this paper, we introduce ChairSegments, a novel and compact semi-synthetic dataset for object segmentation. We also show empirical findings in transfer learning that mirror recent findings for image classification. We particularly show that models that are fine-tuned from a pretrained set of weights lie in the same basin of the optimization landscape. ChairSegments consists of a diverse set of prototypical images of chairs with transparent backgrounds composited into a diverse array of backgrounds. We aim for ChairSegments to be the equivalent of the CIFAR-10 dataset but for quickly designing and iterating over novel model architectures for segmentation. On Chair Segments, a U-Net model can be trained to full convergence in only thirty minutes using a single GPU. Finally, while this dataset is semi-synthetic, it can be a useful proxy for real data, leading to state-of-the-art accuracy on the Object Discovery dataset when used as a source of pretraining.

READ FULL TEXT

page 1

page 2

page 3

page 6

page 7

research
03/28/2023

Large-scale pretraining on pathological images for fine-tuning of small pathological benchmarks

Pretraining a deep learning model on large image datasets is a standard ...
research
12/12/2022

Synthetic Image Data for Deep Learning

Realistic synthetic image data rendered from 3D models can be used to au...
research
09/11/2018

Unbiasing Semantic Segmentation For Robot Perception using Synthetic Data Feature Transfer

Robot perception systems need to perform reliable image segmentation in ...
research
10/29/2021

Learning Co-segmentation by Segment Swapping for Retrieval and Discovery

The goal of this work is to efficiently identify visually similar patter...
research
06/26/2018

Syn2Real: A New Benchmark forSynthetic-to-Real Visual Domain Adaptation

Unsupervised transfer of object recognition models from synthetic to rea...
research
02/12/2023

LiT Tuned Models for Efficient Species Detection

Recent advances in training vision-language models have demonstrated unp...

Please sign up or login with your details

Forgot password? Click here to reset