Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks116 from public data
- Deep Residual Learning for Image Recognition241,838
This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
- Identity Mappings in Deep Residual Networks11,460
The propagation formulations behind the residual building blocks suggest that the forward and backward signals can be directly propagated from one block to any other block, when using identity mappings as the skip connections and after-addition activation.
- ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices9,446
An extremely computation-efficient CNN architecture named ShuffleNet is introduced, which is designed specially for mobile devices with very limited computing power (e.g., 10-150 MFLOPs), to greatly reduce computation cost while maintaining accuracy.
- ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design6,868
This work proposes to evaluate the direct metric on the target platform, beyond only considering FLOPs, and derives several practical guidelines for efficient network design, called ShuffleNet V2.
- 2,946
- Unified Perceptual Parsing for Scene Understanding2,690
A multi-task framework called UPerNet and a training strategy are developed to learn from heterogeneous image annotations and it is shown that it is able to effectively segment a wide range of concepts from images.
- RepVGG: Making VGG-style ConvNets Great Again2,660
A simple but powerful architecture of convolutional neural network, which has a VGG-like inference-time body composed of nothing but a stack of 3 × 3 convolution and ReLU, while the training-time model has a multi-branch topology.
- 1,360
- 1,124
- Single Path One-Shot Neural Architecture Search with Uniform Sampling1,060
A Single Path One-Shot model is proposed to construct a simplified supernet, where all architectures are single paths so that weight co-adaption problem is alleviated.
- You Only Look One-level Feature788
This paper revisits feature pyramids networks (FPN) for one-stage detectors and points out that the success of FPN is due to its divide-and-conquer solution to the optimization problem in object detection rather than multi-scale feature fusion.
- DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation716
This paper introduces an extremely efficient CNN architecture named DFANet for semantic segmentation under resource constraints that substantially reduces the number of parameters, but still obtains sufficient receptive field and enhances the model learning ability, which strikes a balance between the speed and segmentation performance.
- MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning650
A novel meta learning approach for automatic channel pruning of very deep neural networks by training a PruningNet, a kind of meta network, which is able to generate weight parameters for any pruned structure given the target network.
- Anchor DETR: Query Design for Transformer-Based Detector631
The proposed detector, called Anchor DETR, can achieve better performance and run faster than the DETR with 10x fewer training epochs, and an attention variant, which can reduce the memory cost while achieving similar or better performance than the standard attention in DETR.
- Repulsion Loss: Detecting Pedestrians in a Crowd591
This paper first explores how a state-of-the-art pedestrian detector is harmed by crowd occlusion via experimentation, and proposes a novel bounding box regression loss specifically designed for crowd scenes, termed repulsion loss.
- ExFuse: Enhancing Feature Fusion for Semantic Segmentation572
It is found that introducing semantic information into low-level features and high-resolution details into high-level features is more effective for the later fusion, and a new framework, named ExFuse, is proposed to bridge the gap between low-level and high-level features.
- OTA: Optimal Transport Assignment for Object Detection550
This paper innovatively revisit the label assignment from a global perspective and proposes to formulate the assigning procedure as an Optimal Transport (OT) problem – a well-studied topic in Optimization Theory.
- Meta-SR: A Magnification-Arbitrary Network for Super-Resolution539
This work proposes a novel method called Meta-SR to firstly solvesuper-resolution of arbitrary scale factor (including non-integer scale factors) with a single model and shows the superi-ority of the Meta-Upscale.
- Deep Learning with Low Precision by Half-Wave Gaussian Quantization537
An half-wave Gaussian quantizer (HWGQ) is proposed for forward approximation and shown to have efficient implementation, by exploiting the statistics of of network activations and batch normalization operations, and to achieve much closer performance to full precision networks than previously available low-precision networks.
- High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification512
This paper proposes a novel framework by learning high-order relation and topology information for discriminative features and robust alignment for occluded person re-identification and significantly outperforms state-of-the-art mAP scores on Occluded-Duke dataset.
- 462
- 454
- Perceive Where to Focus: Learning Visibility-Aware Part-Level Features for Partial Person Re-Identification388
A Visibility-aware Part Model (VPM) is proposed for partial re-ID, which learns to perceive the visibility of regions through self-supervision, which significantly improves the learned feature representation and the achieved accuracy is on par with the state of the art.
- FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation376
This work proposes FFB6D, a Full Flow Bidirectional fusion network designed for 6D pose estimation from a single RGBD image, which learns to combine appearance and geometry information for representation learning as well as output representation selection.
- Distribution Alignment: A Unified Framework for Long-tail Visual Recognition376
This work develops an adaptive calibration function that enables us to adjust the classification scores for each data point in the two-stage learning to balance the class prior, which provides a flexible and unified solution to diverse scenarios in visual recognition tasks.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.