Search Results for author:
Found 24 papers, 11 papers with code
Get the Best of Both Worlds: Improving Accuracy and Transferability by Grassmann Class Representation
We generalize the class vectors found in neural networks to linear subspaces (i. e.~points in the Grassmann manifold) and show that the Grassmann Class Representation (GCR) enables the simultaneous improvement in accuracy and feature transferability.
Collaborative Anomaly Detection
In recommendation systems, items are likely to be exposed to various users and we would like to learn about the familiarity of a new user with an existing item.
Class-Incremental Learning with Strong Pre-trained Models
We hypothesize that a strong base model can provide a good representation for novel classes and incremental learning can be done with small adaptations.
ViM: Out-Of-Distribution with Virtual-logit Matching
Most of the existing Out-Of-Distribution (OOD) detection algorithms depend on single input source: the feature, the logit, or the softmax probability.
Representation Consolidation from Multiple Expert Teachers
Indeed, we observe experimentally that standard distillation of task-specific teachers, or using these teacher representations directly, **reduces** downstream transferability compared to a task-agnostic generalist model.
MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding
We present MMOCR-an open-source toolbox which provides a comprehensive pipeline for text detection and recognition, as well as their downstream tasks such as named entity recognition and key information extraction.
Representation Consolidation for Training Expert Students
Traditionally, distillation has been used to train a student model to emulate the input/output functionality of a teacher.
Learning Curves for Analysis of Deep Networks
Learning curves model a classifier's test error as a function of the number of training samples.
Regularizing Reasons for Outfit Evaluation with Gradient Penalty
In this paper, we build an outfit evaluation system which provides feedbacks consisting of a judgment with a convincing explanation.
Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion
We introduce DeepInversion, a new method for synthesizing images from the image distribution used to train a deep neural network.
Policy Continuation with Hindsight Inverse Dynamics
This approach learns from Hindsight Inverse Dynamics based on Hindsight Experience Replay, enabling the learning process in a self-imitated manner and thus can be trained with supervised learning.
Convolutional Sequence Generation for Skeleton-Based Action Synthesis
It captures the temporal structure at multiple scales through the GP prior and the temporal convolutions; and establishes the spatial connection between the latent vectors and the skeleton graphs via a novel graph refining scheme.
Ranked #2 on
Human action generation
on NTU RGB+D
Regulatory Focus: Promotion and Prevention Inclinations in Policy Search
The estimation of advantage is crucial for a number of reinforcement learning algorithms, as it directly influences the choices of future paths.
Biased Estimates of Advantages over Path Ensembles
The estimation of advantage is crucial for a number of reinforcement learning algorithms, as it directly influences the choices of future paths.
Task-Assisted Domain Adaptation with Anchor Tasks
Our key idea to improve domain adaptation is to introduce a separate anchor task (such as facial landmarks) whose annotations can be obtained at no cost or are already available on both synthetic and real datasets.
A Dual-level Model Predictive Control Scheme for Multi-timescale Dynamical Systems--Extended Version
So far, many control algorithms have been developed for singularly perturbed systems.
Reducing Overconfident Errors outside the Known Distribution
We compare a number of methods from related fields such as calibration and epistemic uncertainty modeling, as well as two proposed methods that reduce overconfident errors of samples from an unknown novel distribution without drastically increasing evaluation time: (1) G-distillation, training an ensemble of classifiers and then distill into a single model using both labeled and unlabeled examples, or (2) NCR, reducing prediction confidence based on its novelty detection score.
Improving Confidence Estimates for Unfamiliar Examples
In this paper, we compare and evaluate several methods to improve confidence estimates for unfamiliar and familiar samples.
Deep Nearest Class Mean Model for Incremental Odor Classification
That is, the odor datasets are dynamically growing while both training samples and number of classes are increasing over time.
Complete 3D Scene Parsing from an RGBD Image
In this paper, we aim to interpret indoor scenes from one RGBD image.
Integrating Specialized Classifiers Based on Continuous Time Markov Chain
Specialized classifiers, namely those dedicated to a subset of classes, are often adopted in real-world recognition systems.
PolyNet: A Pursuit of Structural Diversity in Very Deep Networks
A number of studies have shown that increasing the depth or width of convolutional networks is a rewarding approach to improve the performance of image recognition.
Learning without Forgetting
We propose our Learning without Forgetting method, which uses only new task data to train the network while preserving the original capabilities.
Ranked #4 on
Domain 11-5
on Cityscapes
A New Retraction for Accelerating the Riemannian Three-Factor Low-Rank Matrix Completion Algorithm
In the line search step, R3MC approximates the minimum point on the searching curve by minimizing on the line tangent to the curve.
