UniMoCo: Unsupervised, Semi-Supervised and Full-Supervised Visual Representation Learning

1 code implementation • 19 Mar 2021 • Zhigang Dai, Bolun Cai, Yugeng Lin, Junying Chen

To fully utilize the label annotations, we propose Unified Momentum Contrast (UniMoCo), which extends MoCo to support arbitrary ratios of labeled data and unlabeled data training.

Representation Learning

UP-DETR: Unsupervised Pre-training for Object Detection with Transformers

2 code implementations • CVPR 2021 • Zhigang Dai, Bolun Cai, Yugeng Lin, Junying Chen

Inspired by the great success of pre-training transformers in natural language processing, we propose a pretext task named random query patch detection to Unsupervisedly Pre-train DETR (UP-DETR) for object detection.

Multi-Task Learning Natural Language Processing +4

Listwise View Ranking for Image Cropping

1 code implementation • 14 May 2019 • Weirui Lu, Xiaofen Xing, Bolun Cai, Xiangmin Xu

However, the performance of ranking-based methods is often poor and this is mainly due to two reasons: 1) image cropping is a listwise ranking task rather than pairwise comparison; 2) the rescaling caused by pooling layer and the deformation in view generation damage the performance of composition learning.

Image Cropping

BIT: Biologically Inspired Tracker

no code implementations • 23 Apr 2019 • Bolun Cai, Xiangmin Xu, Xiaofen Xing, Kui Jia, Jie Miao, DaCheng Tao

Visual tracking is challenging due to image variations caused by various factors, such as object deformation, scale change, illumination change and occlusion.

Visual Tracking

Deep Sampling Networks

no code implementations • 4 Dec 2017 • Bolun Cai, Xiangmin Xu, Kailing Guo, Kui Jia, DaCheng Tao

With the powerful down-sampling process, the co-training DSN set a new state-of-the-art performance for image super-resolution.

Image Compression Image Super-Resolution

A Joint Intrinsic-Extrinsic Prior Model for Retinex

no code implementations • ICCV 2017 • Bolun Cai, Xianming Xu, Kailing Guo, Kui Jia, Bin Hu, DaCheng Tao

We propose a joint intrinsic-extrinsic prior model to estimate both illumination and reflectance from an observed image.

FReLU: Flexible Rectified Linear Units for Improving Convolutional Neural Networks

2 code implementations • 25 Jun 2017 • Suo Qiu, Xiangmin Xu, Bolun Cai

Rectified linear unit (ReLU) is a widely used activation function for deep convolutional neural networks.

Image Classification

Single Image Super-Resolution Using Multi-Scale Convolutional Neural Network

no code implementations • 15 May 2017 • Xiaoyi Jia, Xiangmin Xu, Bolun Cai, Kailing Guo

However, the previous methods mainly restore images from one single area in the low resolution (LR) input, which limits the flexibility of models to infer various scales of details for high resolution (HR) output.

Image Super-Resolution Single Image Super Resolution

Multi-scale Convolutional Neural Networks for Crowd Counting

1 code implementation • 8 Feb 2017 • Lingke Zeng, Xiangmin Xu, Bolun Cai, Suo Qiu, Tong Zhang

Crowd counting on static images is a challenging problem due to scale variations.

Crowd Counting

DehazeNet: An End-to-End System for Single Image Haze Removal

3 code implementations • 28 Jan 2016 • Bolun Cai, Xiangmin Xu, Kui Jia, Chunmei Qing, DaCheng Tao

The key to achieve haze removal is to estimate a medium transmission map for an input hazy image.

Image Dehazing Single Image Haze Removal