Search Results for author:
Found 17 papers, 11 papers with code
BiFormer: Vision Transformer with Bi-Level Routing Attention
As the core building block of vision transformers, attention is a powerful tool to capture long-range dependency.
Ranked #3 on
Object Detection
on COCO 2017
(mAP metric)
FeatureBooster: Boosting Feature Descriptors with a Lightweight Neural Network
We introduce a lightweight network to improve descriptors of keypoints within the same image.
Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection
In this study, we dive deep into the inconsistency of pseudo targets in semi-supervised object detection (SSOD).
What Are Expected Queries in End-to-End Object Detection?
As both sparse and dense queries are imperfect, then \emph{what are expected queries in end-to-end object detection}?
Group R-CNN for Weakly Semi-supervised Object Detection with Points
The core of this task is to train a point-to-box regressor on well-labeled images that can be used to predict credible bounding boxes for each point annotation.
Temporal RoI Align for Video Object Recognition
In this work, considering the features of the same object instance are highly similar among frames in a video, a novel Temporal RoI Align operator is proposed to extract features from other frames feature maps for current frame proposals by utilizing feature similarity.
Ranked #1 on
Video Instance Segmentation
on YouTube-VIS
Group Fisher Pruning for Practical Network Compression
Our method can be used to prune any structures including those with coupled channels.
WSSOD: A New Pipeline for Weakly- and Semi-Supervised Object Detection
The performance of object detection, to a great extent, depends on the availability of large annotated datasets.
Rethinking the Pruning Criteria for Convolutional Neural Network
Channel pruning is a popular technique for compressing convolutional neural networks (CNNs), and various pruning criteria have been proposed to remove the redundant filters of CNNs.
Understanding the wiring evolution in differentiable neural architecture search
To this end, we pose questions that future differentiable methods for neural wiring discovery need to confront, hoping to evoke a discussion and rethinking on how much bias has been enforced implicitly in existing NAS methods.
Scale-Equalizing Pyramid Convolution for Object Detection
Inspired by this, a convolution across the pyramid level is proposed in this study, which is termed pyramid convolution and is a modified 3-D convolution.
Ranked #88 on
Object Detection
on COCO test-dev
Convolution-Weight-Distribution Assumption: Rethinking the Criteria of Channel Pruning
Channel pruning is a popular technique for compressing convolutional neural networks (CNNs), where various pruning criteria have been proposed to remove the redundant filters.
AdaX: Adaptive Gradient Descent with Exponential Long Term Memory
Although adaptive optimization algorithms such as Adam show fast convergence in many machine learning tasks, this paper identifies a problem of Adam by analyzing its performance in a simple non-convex synthetic problem, showing that Adam's fast convergence would possibly lead the algorithm to local minimums.
How Does BN Increase Collapsed Neural Network Filters?
This phenomenon is caused by the normalization effect of BN, which induces a non-trainable region in the parameter space and reduces the network capacity as a result.
Kalman Normalization: Normalizing Internal Representations Across Network Layers
In this paper, we present a novel normalization method, called Kalman Normalization (KN), for improving and accelerating the training of DNNs, particularly under the context of micro-batches.
Towards Understanding Regularization in Batch Normalization
Batch Normalization (BN) improves both convergence and generalization in training neural networks.
Batch Kalman Normalization: Towards Training Deep Neural Networks with Micro-Batches
As an indispensable component, Batch Normalization (BN) has successfully improved the training of deep neural networks (DNNs) with mini-batches, by normalizing the distribution of the internal representation for each hidden layer.
