Small object detection is the task of detecting small objects.
( Image credit: Feature-Fused SSD )
As DenseNet conserves intermediate features with diverse receptive fields by aggregating them with dense connection, it shows good performance on the object detection task.
Ranked #13 on
Instance Segmentation
on COCO test-dev
REAL-TIME OBJECT DETECTION SEMANTIC SEGMENTATION SMALL OBJECT DETECTION
Boundary discontinuity and its inconsistency to the final detection metric have been the bottleneck for rotating detection regression loss design.
In this paper, we propose a new labeling strategy aimed to reduce the label noise in anchor-free detectors.
Ranked #38 on
Object Detection
on COCO test-dev
Inspired by the success of edge enhanced GAN (EEGAN) and ESRGAN, we apply a new edge-enhanced super-resolution GAN (EESRGAN) to improve the image quality of remote sensing images and use different detector networks in an end-to-end manner where detector loss is backpropagated into the EESRGAN to improve the detection performance.
IMAGE ENHANCEMENT REMOTE SENSING IMAGE CLASSIFICATION SATELLITE IMAGE SUPER-RESOLUTION SMALL OBJECT DETECTION SUPER-RESOLUTION
We evaluate different pasting augmentation strategies, and ultimately, we achieve 9. 7\% relative improvement on the instance segmentation and 7. 1\% on the object detection of small objects, compared to the current state of the art method on
INSTANCE SEGMENTATION SEMANTIC SEGMENTATION SMALL OBJECT DETECTION
Our new measure simultaneously evaluates region-aware and object-aware structural similarity between a SM and a GT map.
SALIENT OBJECT DETECTION SEMANTIC SEGMENTATION SMALL OBJECT DETECTION VIDEO OBJECT DETECTION VIDEO SALIENT OBJECT DETECTION
Moreover, inspired by the human education process that drives the learning from easy to hard concepts, we here propose the CMA training paradigm that first trains a clean detector which is free from the influence of noisy data.
In addition, we propose a novel sample-weighted loss function which can model sample weights for SWIPENet, which uses a novel sample re-weighting algorithm, namely Invert Multi-Class Adaboost (IMA), to reduce the influence of noise on the proposed SWIPENet.
We propose a multi-level feature fusion method for introducing contextual information in SSD, in order to improve the accuracy for small objects.
The performance of small object detection, however, is still less than satisfactory because of the deficiency of semantic information on shallow feature maps.