Search Results for author:
Found 24 papers, 7 papers with code
Similarity-Preserving Knowledge Distillation
Knowledge distillation is a widely applicable technique for training a student neural network under the guidance of a trained teacher network.
RankSim: Ranking Similarity Regularization for Deep Imbalanced Regression
Data imbalance, in which a plurality of the data samples come from a small proportion of labels, poses a challenge in training deep neural networks.
Learning Discriminative Prototypes with Dynamic Time Warping
We propose Discriminative Prototype DTW (DP-DTW), a novel method to learn class-specific discriminative prototypes for temporal recognition tasks.
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.
Backtracking Regression Forests for Accurate Camera Relocalization
Camera relocalization plays a vital role in many robotics and computer vision tasks, such as global localization, recovery from tracking failure, and loop closure detection.
Tree Cross Attention
In this work, we propose Tree Cross Attention (TCA) - a module based on Cross Attention that only retrieves information from a logarithmic $\mathcal{O}(\log(N))$ number of tokens for performing inference.
Multi-level Residual Networks from Dynamical Systems View
Deep residual networks (ResNets) and their variants are widely used in many computer vision applications and natural language processing tasks.
Exploiting Points and Lines in Regression Forests for RGB-D Camera Relocalization
Camera relocalization plays a vital role in many robotics and computer vision tasks, such as global localization, recovery from tracking failure and loop closure detection.
Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional Network with Bayesian Optimization
When approaching a novel visual recognition problem in a specialized image domain, a common strategy is to start with a pre-trained deep neural network and fine-tune it to the specialized domain.
Learning Person Trajectory Representations for Team Activity Analysis
Activity analysis in which multiple people interact across a large space is challenging due to the interplay of individual actions and collective group dynamics.
CLIP-Q: Deep Network Compression Learning by In-Parallel Pruning-Quantization
This allows us to take advantage of the complementary nature of pruning and quantization and to recover from premature pruning errors, which is not possible with current two-stage approaches.
Constraint-Aware Deep Neural Network Compression
Deep neural network compression has the potential to bring modern resource-hungry deep networks to resource-limited devices.
Where and when to look? Spatial-temporal attention for action recognition in videos
Our model is efficient, as it proposes a separable spatio-temporal mechanism for video attention, while being able to identify important parts of the video both spatially and temporally.
Action Recognition In Videos
Temporal Action Localization
+1
Piggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation
In contrast, we propose a parameter efficient framework, Piggyback GAN, which learns the current task by building a set of convolutional and deconvolutional filters that are factorized into filters of the models trained on previous tasks.
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.
Gumbel-Softmax Selective Networks
This commonly encountered operational context calls for principled techniques for training ML models with the option to abstain from predicting when uncertain.
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).
Ranking Regularization for Critical Rare Classes: Minimizing False Positives at a High True Positive Rate
In this paper, we present a novel approach to address the challenge of minimizing false positives for systems that need to operate at a high true positive rate.
Memory Efficient Neural Processes via Constant Memory Attention Block
Neural Processes (NPs) are popular meta-learning methods for efficiently modelling predictive uncertainty.
DynaShare: Task and Instance Conditioned Parameter Sharing for Multi-Task Learning
Multi-task networks rely on effective parameter sharing to achieve robust generalization across tasks.
Constant Memory Attention Block
Modern foundation model architectures rely on attention mechanisms to effectively capture context.
Prompting-based Temporal Domain Generalization
Machine learning traditionally assumes that the training and testing data are distributed independently and identically.
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.
Pretext Training Algorithms for Event Sequence Data
Pretext training followed by task-specific fine-tuning has been a successful approach in vision and language domains.
