Search Results for author:
Found 9 papers, 5 papers with code
Forget Sharpness: Perturbed Forgetting of Model Biases Within SAM Dynamics
We propose that perturbations in SAM perform perturbed forgetting, where they discard undesirable model biases to exhibit learning signals that generalize better.
AdaFlood: Adaptive Flood Regularization
Although neural networks are conventionally optimized towards zero training loss, it has been recently learned that targeting a non-zero training loss threshold, referred to as a flood level, often enables better test time generalization.
Meta Temporal Point Processes
In this work, we propose to train TPPs in a meta learning framework, where each sequence is treated as a different task, via a novel framing of TPPs as neural processes (NPs).
DYNASHARE: DYNAMIC NEURAL NETWORKS FOR MULTI-TASK LEARNING
Parameter sharing approaches for deep multi-task learning share a common intuition: for a single network to perform multiple prediction tasks, the network needs to support multiple specialized execution paths.
Heterogeneous Multi-task Learning with Expert Diversity
In contrast to single-task learning, in which a separate model is trained for each target, multi-task learning (MTL) optimizes a single model to predict multiple related targets simultaneously.
Beyond Single Stage Encoder-Decoder Networks: Deep Decoders for Semantic Image Segmentation
In order to further improve the architecture we introduce a weight function which aims to re-balance classes to increase the attention of the networks to under-represented objects.
Topometric Localization with Deep Learning
Compared to LiDAR-based localization methods, which provide high accuracy but rely on expensive sensors, visual localization approaches only require a camera and thus are more cost-effective while their accuracy and reliability typically is inferior to LiDAR-based methods.
Deep Semantic Classification for 3D LiDAR Data
To learn the distinction between movable and non-movable points in the environment, we introduce an approach based on deep neural network and for detecting the dynamic points, we estimate pointwise motion.
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection
In this paper, we propose a network architecture that computes and integrates the most important visual cues for action recognition: pose, motion, and the raw images.
