Search Results for author:
Found 23 papers, 7 papers with code
RADACS: Towards Higher-Order Reasoning using Action Recognition in Autonomous Vehicles
When applied to autonomous vehicle settings, action recognition can help enrich an environment model's understanding of the world and improve plans for future action.
RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features
In this work, we propose a new method called RefineMask for high-quality instance segmentation of objects and scenes, which incorporates fine-grained features during the instance-wise segmenting process in a multi-stage manner.
Fixing the Teacher-Student Knowledge Discrepancy in Distillation
To solve this problem, in this paper, we propose a novel student-dependent distillation method, knowledge consistent distillation, which makes teacher's knowledge more consistent with the student and provides the best suitable knowledge to different student networks for distillation.
Differentiable Network Adaption with Elastic Search Space
In this paper we propose a novel network adaption method called Differentiable Network Adaption (DNA), which can adapt an existing network to a specific computation budget by adjusting the width and depth in a differentiable manner.
Differentiable Dynamic Wirings for Neural Networks
A standard practice of deploying deep neural networks is to apply the same architecture to all the input instances.
Multi-scale Network Architecture Search for Object Detection
Many commonly-used detection frameworks aim to handle the multi-scale object detection problem.
Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection
To address the problem of imbalanced gradients, we introduce a new version of equalization loss, called equalization loss v2 (EQL v2), a novel gradient guided reweighing mechanism that re-balances the training process for each category independently and equally.
Ranked #9 on
Instance Segmentation
on LVIS v1.0 val
Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks
To facilitate the training, we represent the network connectivity of each sample in an adjacency matrix.
MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object Detection
In this paper, we propose MimicDet, a novel and efficient framework to train a one-stage detector by directly mimic the two-stage features, aiming to bridge the accuracy gap between one-stage and two-stage detectors.
1st Place Solution of LVIS Challenge 2020: A Good Box is not a Guarantee of a Good Mask
This article introduces the solutions of the team lvisTraveler for LVIS Challenge 2020.
Ranked #1 on
Instance Segmentation
on LVIS v1.0 test-dev
Learning Connectivity of Neural Networks from a Topological Perspective
In this paper, we attempt to optimize the connectivity in neural networks.
DMCP: Differentiable Markov Channel Pruning for Neural Networks
In DMCP, we model the channel pruning as a Markov process, in which each state represents for retaining the corresponding channel during pruning, and transitions between states denote the pruning process.
Equalization Loss for Long-Tailed Object Recognition
Based on it, we propose a simple but effective loss, named equalization loss, to tackle the problem of long-tailed rare categories by simply ignoring those gradients for rare categories.
Ranked #15 on
Long-tail Learning
on CIFAR-10-LT (ρ=10)
Residual Knowledge Distillation
Knowledge distillation (KD) is one of the most potent ways for model compression.
Equalization Loss for Large Vocabulary Instance Segmentation
Recent object detection and instance segmentation tasks mainly focus on datasets with a relatively small set of categories, e. g. Pascal VOC with 20 classes and COCO with 80 classes.
Diving into Optimization of Topology in Neural Networks
Seeking effective networks has become one of the most crucial and practical areas in deep learning.
PRUNING WITH HINTS: AN EFFICIENT FRAMEWORK FOR MODEL ACCELERATION
Hints can improve the performance of student model by transferring knowledge from teacher model.
WIDER Face and Pedestrian Challenge 2018: Methods and Results
This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian.
An Embarrassingly Simple Approach for Knowledge Distillation
Knowledge Distillation (KD) aims at improving the performance of a low-capacity student model by inheriting knowledge from a high-capacity teacher model.
Grid R-CNN
This paper proposes a novel object detection framework named Grid R-CNN, which adopts a grid guided localization mechanism for accurate object detection.
Ranked #150 on
Object Detection
on COCO minival
Mimicking Very Efficient Network for Object Detection
More specifically, we conduct a mimic method for the features sampled from the entire feature map and use a transform layer to map features from the small network onto the same dimension of the large network.
POI: Multiple Object Tracking with High Performance Detection and Appearance Feature
In this paper, we explore the high-performance detection and deep learning based appearance feature, and show that they lead to significantly better MOT results in both online and offline setting.
