Instance Localization for Self-supervised Detection Pretraining
- URL: http://arxiv.org/abs/2102.08318v1
- Date: Tue, 16 Feb 2021 17:58:57 GMT
- Title: Instance Localization for Self-supervised Detection Pretraining
- Authors: Ceyuan Yang, Zhirong Wu, Bolei Zhou, Stephen Lin
- Abstract summary: We propose a new self-supervised pretext task, called instance localization.
We show that integration of bounding boxes into pretraining promotes better task alignment and architecture alignment for transfer learning.
Experimental results demonstrate that our approach yields state-of-the-art transfer learning results for object detection.
- Score: 68.24102560821623
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Prior research on self-supervised learning has led to considerable progress
on image classification, but often with degraded transfer performance on object
detection. The objective of this paper is to advance self-supervised pretrained
models specifically for object detection. Based on the inherent difference
between classification and detection, we propose a new self-supervised pretext
task, called instance localization. Image instances are pasted at various
locations and scales onto background images. The pretext task is to predict the
instance category given the composited images as well as the foreground
bounding boxes. We show that integration of bounding boxes into pretraining
promotes better task alignment and architecture alignment for transfer
learning. In addition, we propose an augmentation method on the bounding boxes
to further enhance the feature alignment. As a result, our model becomes weaker
at Imagenet semantic classification but stronger at image patch localization,
with an overall stronger pretrained model for object detection. Experimental
results demonstrate that our approach yields state-of-the-art transfer learning
results for object detection on PASCAL VOC and MSCOCO.
Related papers
- Few-Shot Object Detection with Sparse Context Transformers [37.106378859592965]
Few-shot detection is a major task in pattern recognition which seeks to localize objects using models trained with few labeled data.
We propose a novel sparse context transformer (SCT) that effectively leverages object knowledge in the source domain, and automatically learns a sparse context from only few training images in the target domain.
We evaluate the proposed method on two challenging few-shot object detection benchmarks, and empirical results show that the proposed method obtains competitive performance compared to the related state-of-the-art.
arXiv Detail & Related papers (2024-02-14T17:10:01Z) - Location-Aware Self-Supervised Transformers [74.76585889813207]
We propose to pretrain networks for semantic segmentation by predicting the relative location of image parts.
We control the difficulty of the task by masking a subset of the reference patch features visible to those of the query.
Our experiments show that this location-aware pretraining leads to representations that transfer competitively to several challenging semantic segmentation benchmarks.
arXiv Detail & Related papers (2022-12-05T16:24:29Z) - CoDo: Contrastive Learning with Downstream Background Invariance for
Detection [10.608660802917214]
We propose a novel object-level self-supervised learning method, called Contrastive learning with Downstream background invariance (CoDo)
The pretext task is converted to focus on instance location modeling for various backgrounds, especially for downstream datasets.
Experiments on MSCOCO demonstrate that the proposed CoDo with common backbones, ResNet50-FPN, yields strong transfer learning results for object detection.
arXiv Detail & Related papers (2022-05-10T01:26:15Z) - LEAD: Self-Supervised Landmark Estimation by Aligning Distributions of
Feature Similarity [49.84167231111667]
Existing works in self-supervised landmark detection are based on learning dense (pixel-level) feature representations from an image.
We introduce an approach to enhance the learning of dense equivariant representations in a self-supervised fashion.
We show that having such a prior in the feature extractor helps in landmark detection, even under drastically limited number of annotations.
arXiv Detail & Related papers (2022-04-06T17:48:18Z) - Object-aware Contrastive Learning for Debiased Scene Representation [74.30741492814327]
We develop a novel object-aware contrastive learning framework that localizes objects in a self-supervised manner.
We also introduce two data augmentations based on ContraCAM, object-aware random crop and background mixup, which reduce contextual and background biases during contrastive self-supervised learning.
arXiv Detail & Related papers (2021-07-30T19:24:07Z) - Rectifying the Shortcut Learning of Background: Shared Object
Concentration for Few-Shot Image Recognition [101.59989523028264]
Few-Shot image classification aims to utilize pretrained knowledge learned from a large-scale dataset to tackle a series of downstream classification tasks.
We propose COSOC, a novel Few-Shot Learning framework, to automatically figure out foreground objects at both pretraining and evaluation stage.
arXiv Detail & Related papers (2021-07-16T07:46:41Z) - Aligning Pretraining for Detection via Object-Level Contrastive Learning [57.845286545603415]
Image-level contrastive representation learning has proven to be highly effective as a generic model for transfer learning.
We argue that this could be sub-optimal and thus advocate a design principle which encourages alignment between the self-supervised pretext task and the downstream task.
Our method, called Selective Object COntrastive learning (SoCo), achieves state-of-the-art results for transfer performance on COCO detection.
arXiv Detail & Related papers (2021-06-04T17:59:52Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.