Control Distance IoU and Control Distance IoU Loss Function for Better
Bounding Box Regression
- URL: http://arxiv.org/abs/2103.11696v1
- Date: Mon, 22 Mar 2021 09:57:25 GMT
- Title: Control Distance IoU and Control Distance IoU Loss Function for Better
Bounding Box Regression
- Authors: Dong Chen and Duoqian Miao
- Abstract summary: We first present an evaluation-feedback module, which is proposed to consist of evaluation system and feedback mechanism.
Finally, we focus on both the evaluation system and the feedback mechanism, and propose Control Distance IoU and Control Distance IoU loss function.
- Score: 11.916482804759479
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Numerous improvements for feedback mechanisms have contributed to the great
progress in object detection. In this paper, we first present an
evaluation-feedback module, which is proposed to consist of evaluation system
and feedback mechanism. Then we analyze and summarize the disadvantages and
improvements of traditional evaluation-feedback module. Finally, we focus on
both the evaluation system and the feedback mechanism, and propose Control
Distance IoU and Control Distance IoU loss function (or CDIoU and CDIoU loss
for short) without increasing parameters or FLOPs in models, which show
different significant enhancements on several classical and emerging models.
Some experiments and comparative tests show that coordinated
evaluation-feedback module can effectively improve model performance. CDIoU and
CDIoU loss have different excellent performances in several models such as
Faster R-CNN, YOLOv4, RetinaNet and ATSS. There is a maximum AP improvement of
1.9% and an average AP of 0.8% improvement on MS COCO dataset, compared to
traditional evaluation-feedback modules.
Related papers
- Beyond Thumbs Up/Down: Untangling Challenges of Fine-Grained Feedback for Text-to-Image Generation [67.88747330066049]
Fine-grained feedback captures nuanced distinctions in image quality and prompt-alignment.
We show that demonstrating its superiority to coarse-grained feedback is not automatic.
We identify key challenges in eliciting and utilizing fine-grained feedback.
arXiv Detail & Related papers (2024-06-24T17:19:34Z) - YOLOv10: Real-Time End-to-End Object Detection [68.28699631793967]
YOLOs have emerged as the predominant paradigm in the field of real-time object detection.
The reliance on the non-maximum suppression (NMS) for post-processing hampers the end-to-end deployment of YOLOs.
We introduce the holistic efficiency-accuracy driven model design strategy for YOLOs.
arXiv Detail & Related papers (2024-05-23T11:44:29Z) - Autonomous Evaluation and Refinement of Digital Agents [57.12281122337407]
We show that domain-general automatic evaluators can significantly improve the performance of agents for web navigation and device control.
We validate the performance of these models in several popular benchmarks for digital agents, finding between 74.4 and 92.9% agreement with oracle evaluation metrics.
arXiv Detail & Related papers (2024-04-09T17:25:47Z) - Reinforcement Learning from Delayed Observations via World Models [10.298219828693489]
In reinforcement learning settings, agents assume immediate feedback about the effects of their actions after taking them.
In practice, this assumption may not hold true due to physical constraints and can significantly impact the performance of learning algorithms.
We propose leveraging world models, which have shown success in integrating past observations and learning dynamics, to handle observation delays.
arXiv Detail & Related papers (2024-03-18T23:18:27Z) - Improvement and Enhancement of YOLOv5 Small Target Recognition Based on
Multi-module Optimization [9.125818713673366]
The performance of the model is successfully enhanced by introducing GhostNet-based convolutional module, RepGFPN-based Neck module optimization, CA and Transformer's attention mechanism, and loss function improvement using NWD.
The improved model shows significant superiority in dealing with complex backgrounds and tiny targets in real-world application tests.
arXiv Detail & Related papers (2023-10-03T05:39:36Z) - Systematic Architectural Design of Scale Transformed Attention Condenser
DNNs via Multi-Scale Class Representational Response Similarity Analysis [93.0013343535411]
We propose a novel type of analysis called Multi-Scale Class Representational Response Similarity Analysis (ClassRepSim)
We show that adding STAC modules to ResNet style architectures can result in up to a 1.6% increase in top-1 accuracy.
Results from ClassRepSim analysis can be used to select an effective parameterization of the STAC module resulting in competitive performance.
arXiv Detail & Related papers (2023-06-16T18:29:26Z) - Robustness and Generalization Performance of Deep Learning Models on
Cyber-Physical Systems: A Comparative Study [71.84852429039881]
Investigation focuses on the models' ability to handle a range of perturbations, such as sensor faults and noise.
We test the generalization and transfer learning capabilities of these models by exposing them to out-of-distribution (OOD) samples.
arXiv Detail & Related papers (2023-06-13T12:43:59Z) - Learning Target-aware Representation for Visual Tracking via Informative
Interactions [49.552877881662475]
We introduce a novel backbone architecture to improve target-perception ability of feature representation for tracking.
The proposed GIM module and InBN mechanism are general and applicable to different backbone types including CNN and Transformer.
arXiv Detail & Related papers (2022-01-07T16:22:27Z) - Quantum proportional-integral (PI) control [6.207388432844965]
We apply formalism to two canonical quantum feedback control problems.
For entanglement generation the best strategy can be a combined PI strategy when the measurement efficiency is less than one.
For harmonic state stabilization we find that P feedback shows the best performance when actuation of both position and momentum feedback is possible.
arXiv Detail & Related papers (2020-07-27T20:35:47Z) - MM-KTD: Multiple Model Kalman Temporal Differences for Reinforcement
Learning [36.14516028564416]
This paper proposes an innovative Multiple Model Kalman Temporal Difference (MM-KTD) framework to learn optimal control policies.
An active learning method is proposed to enhance the sampling efficiency of the system.
Experimental results show superiority of the MM-KTD framework in comparison to its state-of-the-art counterparts.
arXiv Detail & Related papers (2020-05-30T06:39:55Z)
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.