PROJECT TITLE :

Object Detection from Scratch with Deep Supervision

ABSTRACT:

We propose Deeply Supervised Object Detectors (DSOD) as an object detection framework that can be taught from the ground up in this research. Off-the-shelf models pre-trained on large-scale classification datasets like ImageNet and OpenImage are heavily used in recent improvements in object detection. However, because of the varied goal function and diverse distributions of object categories, transferring pre-trained models from classification to detection may result in learning bias. Techniques such as fine-tuning on detection tasks could help to some extent, but they aren't fundamental. It will also be more challenging to transfer these pre-trained models across disparate domains (e.g., from RGB to depth images). As a result, training object detectors from scratch is a better answer to these crucial difficulties, which justifies our proposed strategy. Previous attempts in this manner have largely failed because to a lack of training data and unsophisticated object detection backbone network architectures. We propose a set of design principles for building object detectors from the ground up in DSOD. Deep supervision, which is facilitated by layer-wise dense connections in both backbone networks and prediction layers, is one of the main ideas in learning excellent detectors from scratch. We build our DSOD based on the single-shot detection architecture after including various other principles (SSD). The PASCAL VOC 2007, 2012, and COCO datasets are used to test our technique. DSOD routinely outperforms state-of-the-art approaches that employ significantly more compact models. In particular, DSOD surpasses SSD on all three test while only requiring 1/2 of the parameters. We also found that with only 1/3 of the parameters, DSOD can get comparable/slightly better results than Mask RCNN [1] + FPN [2] (under similar input size) with no extra data or pre-trained models (under similar input size).


Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here


PROJECT TITLE : Alzheimers Diseases Detection by Using Deep Learning Algorithms ABSTRACT: Accurate Alzheimer's disease (AD) diagnosis is critical for patient treatment, especially in the early stages of the disease, because
PROJECT TITLE : Deep Learning for Plant Species Classification Using Leaf Vein Morphometric ABSTRACT: Botanists and laypeople alike could benefit from a system that automatically identifies plant species. Deep learning is effective
PROJECT TITLE : Deep Learning for Smartphone-Based Malaria Parasite Detection in Thick Blood Smears ABSTRACT: This study looks into the possibilities of using smartphones to detect malaria parasites in thick blood smears. We've
PROJECT TITLE : Robust Lane Detection from Continuous Driving ScenesUsing Deep Neural Networks ABSTRACT: For autonomous vehicles and sophisticated driver assistance systems, lane recognition in driving scenes is a critical element.
PROJECT TITLE : Use of a Tracer-Specific Deep Artificial Neural Net to Denoise Dynamic PET Images ABSTRACT: The use of kinetic modeling (KM) on a voxel level in dynamic PET pictures frequently results in large amounts of noise,

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry