English
Related papers

Related papers: Rethinking ImageNet Pre-training

200 papers

Adder neural networks (AdderNets) have shown impressive performance on image classification with only addition operations, which are more energy efficient than traditional convolutional neural networks built with multiplications. Compared…

Computer Vision and Pattern Recognition · Computer Science 2021-12-28 Xinghao Chen , Chang Xu , Minjing Dong , Chunjing Xu , Yunhe Wang

We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. The…

Computer Vision and Pattern Recognition · Computer Science 2018-01-25 Kaiming He , Georgia Gkioxari , Piotr Dollár , Ross Girshick

Initialization, normalization, and skip connections are believed to be three indispensable techniques for training very deep convolutional neural networks and obtaining state-of-the-art performance. This paper shows that deep vanilla…

Computer Vision and Pattern Recognition · Computer Science 2020-08-18 Haozhi Qi , Chong You , Xiaolong Wang , Yi Ma , Jitendra Malik

Semantic segmentation labels are expensive and time consuming to acquire. Hence, pretraining is commonly used to improve the label-efficiency of segmentation models. Typically, the encoder of a segmentation model is pretrained as a…

Computer Vision and Pattern Recognition · Computer Science 2022-05-24 Emmanuel Brempong Asiedu , Simon Kornblith , Ting Chen , Niki Parmar , Matthias Minderer , Mohammad Norouzi

This study proposes a semi-supervised co-training framework for object detection in densely packed retail environments, where limited labeled data and complex conditions pose major challenges. The framework combines Faster R-CNN (utilizing…

Computer Vision and Pattern Recognition · Computer Science 2025-09-15 Hossein Yazdanjouei , Arash Mansouri , Mohammad Shokouhifar

This paper explores a better prediction target for BERT pre-training of vision transformers. We observe that current prediction targets disagree with human perception judgment.This contradiction motivates us to learn a perceptual prediction…

Computer Vision and Pattern Recognition · Computer Science 2022-12-19 Xiaoyi Dong , Jianmin Bao , Ting Zhang , Dongdong Chen , Weiming Zhang , Lu Yuan , Dong Chen , Fang Wen , Nenghai Yu , Baining Guo

We propose an incremental training method that partitions the original network into sub-networks, which are then gradually incorporated in the running network during the training process. To allow for a smooth dynamic growth of the network,…

Machine Learning · Computer Science 2018-03-29 Roxana Istrate , Adelmo Cristiano Innocenza Malossi , Costas Bekas , Dimitrios Nikolopoulos

State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since additional labeled data is needed to specify any…

Computer Vision and Pattern Recognition · Computer Science 2021-03-02 Alec Radford , Jong Wook Kim , Chris Hallacy , Aditya Ramesh , Gabriel Goh , Sandhini Agarwal , Girish Sastry , Amanda Askell , Pamela Mishkin , Jack Clark , Gretchen Krueger , Ilya Sutskever

According to recent studies, commonly used computer vision datasets contain about 4% of label errors. For example, the COCO dataset is known for its high level of noise in data labels, which limits its use for training robust neural deep…

Computer Vision and Pattern Recognition · Computer Science 2021-09-08 Natalia Khanzhina , Alexey Lapenok , Andrey Filchenkov

Recently there has been a lot of work on pruning filters from deep convolutional neural networks (CNNs) with the intention of reducing computations. The key idea is to rank the filters based on a certain criterion (say, $l_1$-norm, average…

Computer Vision and Pattern Recognition · Computer Science 2018-02-01 Deepak Mittal , Shweta Bhardwaj , Mitesh M. Khapra , Balaraman Ravindran

The paradigm of large-scale pre-training followed by downstream fine-tuning has been widely employed in various object detection algorithms. In this paper, we reveal discrepancies in data, model, and task between the pre-training and…

Computer Vision and Pattern Recognition · Computer Science 2023-08-15 Ming Li , Jie Wu , Xionghui Wang , Chen Chen , Jie Qin , Xuefeng Xiao , Rui Wang , Min Zheng , Xin Pan

Cascaded architectures have brought significant performance improvement in object detection and instance segmentation. However, there are lingering issues regarding the disparity in the Intersection-over-Union (IoU) distribution of the…

Computer Vision and Pattern Recognition · Computer Science 2020-12-21 Thang Vu , Haeyong Kang , Chang D. Yoo

Contrastive self-supervised learning has largely narrowed the gap to supervised pre-training on ImageNet. However, its success highly relies on the object-centric priors of ImageNet, i.e., different augmented views of the same image…

Computer Vision and Pattern Recognition · Computer Science 2021-12-06 Jiahao Xie , Xiaohang Zhan , Ziwei Liu , Yew Soon Ong , Chen Change Loy

A core component of the recent success of self-supervised learning is cropping data augmentation, which selects sub-regions of an image to be used as positive views in the self-supervised loss. The underlying assumption is that randomly…

Computer Vision and Pattern Recognition · Computer Science 2023-04-10 Shlok Mishra , Anshul Shah , Ankan Bansal , Abhyuday Jagannatha , Janit Anjaria , Abhishek Sharma , David Jacobs , Dilip Krishnan

In the segmentation of remotely sensed images, deep learning models are typically pre-trained using large image databases like ImageNet before fine-tuned on domain-specific datasets. However, the performance of these fine-tuned models is…

Computer Vision and Pattern Recognition · Computer Science 2026-05-01 Yuan Fang , Yuanzhi Cai , Jagannath Aryal , Qinfeng Zhu , Hong Huang , Cheng Zhang , Lei Fan

Weakly supervised image segmentation trained with image-level labels usually suffers from inaccurate coverage of object areas during the generation of the pseudo groundtruth. This is because the object activation maps are trained with the…

Computer Vision and Pattern Recognition · Computer Science 2022-06-30 Weide Liu , Xiangfei Kong , Tzu-Yi Hung , Guosheng Lin

Learning generalizable policies that can adapt to unseen environments remains challenging in visual Reinforcement Learning (RL). Existing approaches try to acquire a robust representation via diversifying the appearances of in-domain…

Machine Learning · Computer Science 2022-12-20 Zhecheng Yuan , Zhengrong Xue , Bo Yuan , Xueqian Wang , Yi Wu , Yang Gao , Huazhe Xu

Batch normalization is a key component of most image classification models, but it has many undesirable properties stemming from its dependence on the batch size and interactions between examples. Although recent work has succeeded in…

Computer Vision and Pattern Recognition · Computer Science 2021-02-12 Andrew Brock , Soham De , Samuel L. Smith , Karen Simonyan

The approximation and convergence properties of implicit neural representations (INRs) are known to be highly sensitive to parameter initialization strategies. While several data-driven initialization methods demonstrate significant…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Kushal Vyas , Alper Kayabasi , Daniel Kim , Vishwanath Saragadam , Ashok Veeraraghavan , Guha Balakrishnan

Deep co-training has been introduced to semi-supervised segmentation and achieves impressive results, yet few studies have explored the working mechanism behind it. In this work, we revisit the core assumption that supports co-training:…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Yijiang Li , Xinjiang Wang , Lihe Yang , Litong Feng , Wayne Zhang , Ying Gao