577 citations · 2.7k across the 94 of their papers we have counts for
22 papers · 1 filter
Towards Unified INT8 Training for Convolutional Neural Network
Feng Zhu, Ruihao Gong, Fengwei Yu +5
Recently low-bit (e.g., 8-bit) network quantization has been extensively studied to accelerate the inference. Besides inference, low-bit training with quantized gradients can furth…
Computation Reallocation for Object Detection
Feng Liang, Chen Lin, Ronghao Guo +4
The allocation of computation resources in the backbone is a crucial issue in object detection. However, classification allocation pattern is usually adopted directly to object det…
Equalization Loss for Large Vocabulary Instance Segmentation
Jingru Tan, Changbao Wang, Quanquan Li +1
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…
Improving One-shot NAS by Suppressing the Posterior Fading
Xiang Li, Chen Lin, Chuming Li +4
There is a growing interest in automated neural architecture search (NAS). To improve the efficiency of NAS, previous approaches adopt weight sharing method to force all models sha…
CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval
Zihao Wang, Xihui Liu, Hongsheng Li +4
Text-image cross-modal retrieval is a challenging task in the field of language and vision. Most previous approaches independently embed images and sentences into a joint embedding…
Efficient Neural Architecture Transformation Searchin Channel-Level for Object Detection
Junran Peng, Ming Sun, Zhaoxiang Zhang +2
Recently, Neural Architecture Search has achieved great success in large-scale image classification. In contrast, there have been limited works focusing on architecture search for…
POD: Practical Object Detection with Scale-Sensitive Network
Junran Peng, Ming Sun, Zhaoxiang Zhang +2
Scale-sensitive object detection remains a challenging task, where most of the existing methods could not learn it explicitly and are not robust to scale variance. In addition, the…
Towards Flops-constrained Face Recognition
Yu Liu, Guanglu Song, Manyuan Zhang +3
Large scale face recognition is challenging especially when the computational budget is limited. Given a \textit{flops} upper bound, the key is to find the optimal neural network a…
STM: SpatioTemporal and Motion Encoding for Action Recognition
Boyuan Jiang, Mengmeng Wang, Weihao Gan +2
Spatiotemporal and motion features are two complementary and crucial information for video action recognition. Recent state-of-the-art methods adopt a 3D CNN stream to learn spatio…
Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks
Ruihao Gong, Xianglong Liu, Shenghu Jiang +5
Hardware-friendly network quantization (e.g., binary/uniform quantization) can efficiently accelerate the inference and meanwhile reduce memory consumption of the deep neural netwo…
Grid R-CNN Plus: Faster and Better
Xin Lu, Buyu Li, Yuxin Yue +2
Grid R-CNN is a well-performed objection detection framework. It transforms the traditional box offset regression problem into a grid point estimation problem. With the guidance of…
P2SGrad: Refined Gradients for Optimizing Deep Face Models
Xiao Zhang, Rui Zhao, Junjie Yan +4
Cosine-based softmax losses significantly improve the performance of deep face recognition networks. However, these losses always include sensitive hyper-parameters which can make…
Learning to Cluster Faces on an Affinity Graph
Lei Yang, Xiaohang Zhan, Dapeng Chen +3
Face recognition sees remarkable progress in recent years, and its performance has reached a very high level. Taking it to a next level requires substantially larger data, which wo…
Learning to Auto Weight: Entirely Data-driven and Highly Efficient Weighting Framework
Zhenmao Li, Yichao Wu, Ken Chen +4
Example weighting algorithm is an effective solution to the training bias problem, however, most previous typical methods are usually limited to human knowledge and require laborio…
AM-LFS: AutoML for Loss Function Search
Chuming Li, Yuan Xin, Chen Lin +4
Designing an effective loss function plays an important role in visual analysis. Most existing loss function designs rely on hand-crafted heuristics that require domain experts to…
Online Hyper-parameter Learning for Auto-Augmentation Strategy
Chen Lin, Minghao Guo, Chuming Li +5
Data augmentation is critical to the success of modern deep learning techniques. In this paper, we propose Online Hyper-parameter Learning for Auto-Augmentation (OHL-Auto-Aug), an…
Knowledge Distillation via Route Constrained Optimization
Xiao Jin, Baoyun Peng, Yichao Wu +5
Distillation-based learning boosts the performance of the miniaturized neural network based on the hypothesis that the representation of a teacher model can be used as structured a…
Video Generation from Single Semantic Label Map
Junting Pan, Chengyu Wang, Xu Jia +4
This paper proposes the novel task of video generation conditioned on a SINGLE semantic label map, which provides a good balance between flexibility and quality in the generation p…
WIDER Face and Pedestrian Challenge 2018: Methods and Results
Chen Change Loy, Dahua Lin, Wanli Ouyang +49
This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian. The challenge focuses on the problem of precise localization of human faces and bodies, and accurat…
Dynamic Multi-path Neural Network
Yingcheng Su, Shunfeng Zhou, Yichao Wu +7
Although deeper and larger neural networks have achieved better performance, the complex network structure and increasing computational cost cannot meet the demands of many resourc…
Multi-Object Tracking with Multiple Cues and Switcher-Aware Classification
Weitao Feng, Zhihao Hu, Wei Wu +2
In this paper, we propose a unified Multi-Object Tracking (MOT) framework learning to make full use of long term and short term cues for handling complex cases in MOT scenes. Besid…
Dynamic Curriculum Learning for Imbalanced Data Classification
Yiru Wang, Weihao Gan, Jie Yang +2
Human attribute analysis is a challenging task in the field of computer vision, since the data is largely imbalance-distributed. Common techniques such as re-sampling and cost-sens…