Efficient Parameter Mining and Freezing for Continual Object Detection
- URL: http://arxiv.org/abs/2402.12624v1
- Date: Tue, 20 Feb 2024 01:07:32 GMT
- Title: Efficient Parameter Mining and Freezing for Continual Object Detection
- Authors: Angelo G. Menezes, Augusto J. Peterlevitz, Mateus A. Chinelatto and
Andr\'e C. P. L. F. de Carvalho
- Abstract summary: We propose efficient ways to identify which layers are the most important for a network to maintain the performance of a detector across sequential updates.
The presented findings highlight the substantial advantages of layer-level parameter isolation in facilitating incremental learning within object detection models.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Continual Object Detection is essential for enabling intelligent agents to
interact proactively with humans in real-world settings. While
parameter-isolation strategies have been extensively explored in the context of
continual learning for classification, they have yet to be fully harnessed for
incremental object detection scenarios. Drawing inspiration from prior research
that focused on mining individual neuron responses and integrating insights
from recent developments in neural pruning, we proposed efficient ways to
identify which layers are the most important for a network to maintain the
performance of a detector across sequential updates. The presented findings
highlight the substantial advantages of layer-level parameter isolation in
facilitating incremental learning within object detection models, offering
promising avenues for future research and application in real-world scenarios.
Related papers
- Zero-shot Degree of Ill-posedness Estimation for Active Small Object Change Detection [8.977792536037956]
In everyday indoor navigation, robots often needto detect non-distinctive small-change objects.
Existing techniques rely on high-quality class-specific object priors to regularize a change detector model.
In this study, we explore the concept of degree-of-ill-posedness (DoI) to improve both passive and activevision.
arXiv Detail & Related papers (2024-05-10T01:56:39Z) - A Target Detection Algorithm in Traffic Scenes Based on Deep
Reinforcement Learning [2.8554857235549753]
This research presents a novel active detection model utilizing deep reinforcement learning to accurately detect traffic objects in real-world scenarios.
The model employs a deep Q-network based on LSTM-CNN that identifies and aligns target zones with specific categories of traffic objects.
Tests conducted demonstrate the model's proficiency, exhibiting exceptional precision and performance in locating traffic signal lights and speed limit signs.
arXiv Detail & Related papers (2023-12-25T04:23:30Z) - Feature Interaction Aware Automated Data Representation Transformation [27.26916497306978]
We develop a hierarchical reinforcement learning structure with cascading Markov Decision Processes to automate feature and operation selection.
We reward agents based on the interaction strength between selected features, resulting in intelligent and efficient exploration of the feature space that emulates human decision-making.
arXiv Detail & Related papers (2023-09-29T06:48:16Z) - Deep networks for system identification: a Survey [56.34005280792013]
System identification learns mathematical descriptions of dynamic systems from input-output data.
Main aim of the identified model is to predict new data from previous observations.
We discuss architectures commonly adopted in the literature, like feedforward, convolutional, and recurrent networks.
arXiv Detail & Related papers (2023-01-30T12:38:31Z) - Self-supervised Sequential Information Bottleneck for Robust Exploration
in Deep Reinforcement Learning [28.75574762244266]
In this work, we introduce the sequential information bottleneck objective for learning compressed and temporally coherent representations.
For efficient exploration in noisy environments, we further construct intrinsic rewards that capture task-relevant state novelty.
arXiv Detail & Related papers (2022-09-12T15:41:10Z) - Learning Neural Causal Models with Active Interventions [83.44636110899742]
We introduce an active intervention-targeting mechanism which enables a quick identification of the underlying causal structure of the data-generating process.
Our method significantly reduces the required number of interactions compared with random intervention targeting.
We demonstrate superior performance on multiple benchmarks from simulated to real-world data.
arXiv Detail & Related papers (2021-09-06T13:10:37Z) - Progressive Self-Guided Loss for Salient Object Detection [102.35488902433896]
We present a progressive self-guided loss function to facilitate deep learning-based salient object detection in images.
Our framework takes advantage of adaptively aggregated multi-scale features to locate and detect salient objects effectively.
arXiv Detail & Related papers (2021-01-07T07:33:38Z) - SID: Incremental Learning for Anchor-Free Object Detection via Selective
and Inter-Related Distillation [16.281712605385316]
Incremental learning requires a model to continually learn new tasks from streaming data.
Traditional fine-tuning of a well-trained deep neural network on a new task will dramatically degrade performance on the old task.
We propose a novel incremental learning paradigm called Selective and Inter-related Distillation (SID)
arXiv Detail & Related papers (2020-12-31T04:12:06Z) - Learning Long-term Visual Dynamics with Region Proposal Interaction
Networks [75.06423516419862]
We build object representations that can capture inter-object and object-environment interactions over a long-range.
Thanks to the simple yet effective object representation, our approach outperforms prior methods by a significant margin.
arXiv Detail & Related papers (2020-08-05T17:48:00Z) - Incremental Object Detection via Meta-Learning [77.55310507917012]
We propose a meta-learning approach that learns to reshape model gradients, such that information across incremental tasks is optimally shared.
In comparison to existing meta-learning methods, our approach is task-agnostic, allows incremental addition of new-classes and scales to high-capacity models for object detection.
arXiv Detail & Related papers (2020-03-17T13:40:00Z) - Global Context-Aware Progressive Aggregation Network for Salient Object
Detection [117.943116761278]
We propose a novel network named GCPANet to integrate low-level appearance features, high-level semantic features, and global context features.
We show that the proposed approach outperforms the state-of-the-art methods both quantitatively and qualitatively.
arXiv Detail & Related papers (2020-03-02T04:26:10Z)
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.