Search Results for author:
Found 4 papers, 2 papers with code
Class Incremental Learning with Pre-trained Vision-Language Models
We also propose a method for parameter retention in the adapter layers that uses a measure of parameter importance to better maintain stability and plasticity during incremental learning.
Make Explicit Calibration Implicit: Calibrate Denoiser Instead of the Noise Model
However, these methods are impeded by several critical limitations: a) the explicit calibration process is both labor- and time-intensive, b) challenge exists in transferring denoisers across different camera models, and c) the disparity between synthetic and real noise is exacerbated by digital gain.
Ranked #1 on
Image Denoising
on SID SonyA7S2 x300
Endpoints Weight Fusion for Class Incremental Semantic Segmentation
In our method, the model containing old knowledge is fused with the model retaining new knowledge in a dynamic fusion manner, strengthening the memory of old classes in ever-changing distributions.
Class-Incremental Semantic Segmentation
Incremental Learning
+1
Representation Compensation Networks for Continual Semantic Segmentation
In this work, we study the continual semantic segmentation problem, where the deep neural networks are required to incorporate new classes continually without catastrophic forgetting.
Ranked #1 on
Domain 1-1
on Cityscapes
Class Incremental Learning
Continual Semantic Segmentation
+16
