no code implementations • CVPR 2014 • Golnaz Ghiasi, Yi Yang, Deva Ramanan, Charless C. Fowlkes
Occlusion poses a significant difficulty for object recognition due to the combinatorial diversity of possible occlusion patterns.
no code implementations • CVPR 2014 • Golnaz Ghiasi, Charless C. Fowlkes
The presence of occluders significantly impacts performance of systems for object recognition.
2 code implementations • 28 Jun 2015 • Golnaz Ghiasi, Charless C. Fowlkes
The presence of occluders significantly impacts object recognition accuracy.
1 code implementation • 8 May 2016 • Golnaz Ghiasi, Charless C. Fowlkes
CNN architectures have terrific recognition performance but rely on spatial pooling which makes it difficult to adapt them to tasks that require dense, pixel-accurate labeling.
Ranked #69 on Semantic Segmentation on Cityscapes test
20 code implementations • 18 May 2017 • Golnaz Ghiasi, Honglak Lee, Manjunath Kudlur, Vincent Dumoulin, Jonathon Shlens
In this paper, we present a method which combines the flexibility of the neural algorithm of artistic style with the speed of fast style transfer networks to allow real-time stylization using any content/style image pair.
6 code implementations • NeurIPS 2018 • Golnaz Ghiasi, Tsung-Yi Lin, Quoc V. Le
This lack of success of dropout for convolutional layers is perhaps due to the fact that activation units in convolutional layers are spatially correlated so information can still flow through convolutional networks despite dropout.
Ranked #774 on Image Classification on ImageNet
1 code implementation • ICLR 2020 • Mohammad Babaeizadeh, Golnaz Ghiasi
Artistic style transfer is the problem of synthesizing an image with content similar to a given image and style similar to another.
8 code implementations • CVPR 2019 • Golnaz Ghiasi, Tsung-Yi Lin, Ruoming Pang, Quoc V. Le
Here we aim to learn a better architecture of feature pyramid network for object detection.
6 code implementations • ECCV 2020 • Barret Zoph, Ekin D. Cubuk, Golnaz Ghiasi, Tsung-Yi Lin, Jonathon Shlens, Quoc V. Le
Importantly, the best policy found on COCO may be transferred unchanged to other detection datasets and models to improve predictive accuracy.
Ranked #6 on Robust Object Detection on Cityscapes
2 code implementations • CVPR 2020 • Bo Chen, Golnaz Ghiasi, Hanxiao Liu, Tsung-Yi Lin, Dmitry Kalenichenko, Hartwig Adams, Quoc V. Le
We propose MnasFPN, a mobile-friendly search space for the detection head, and combine it with latency-aware architecture search to produce efficient object detection models.
Ranked #230 on Object Detection on COCO test-dev
13 code implementations • CVPR 2020 • Xianzhi Du, Tsung-Yi Lin, Pengchong Jin, Golnaz Ghiasi, Mingxing Tan, Yin Cui, Quoc V. Le, Xiaodan Song
We propose SpineNet, a backbone with scale-permuted intermediate features and cross-scale connections that is learned on an object detection task by Neural Architecture Search.
Ranked #9 on Image Classification on iNaturalist
2 code implementations • NeurIPS 2020 • Barret Zoph, Golnaz Ghiasi, Tsung-Yi Lin, Yin Cui, Hanxiao Liu, Ekin D. Cubuk, Quoc V. Le
For example, on the COCO object detection dataset, pre-training benefits when we use one fifth of the labeled data, and hurts accuracy when we use all labeled data.
Ranked #1 on Semantic Segmentation on PASCAL VOC 2012 val
5 code implementations • CVPR 2021 • Golnaz Ghiasi, Yin Cui, Aravind Srinivas, Rui Qian, Tsung-Yi Lin, Ekin D. Cubuk, Quoc V. Le, Barret Zoph
Our baseline model outperforms the LVIS 2020 Challenge winning entry by +3. 6 mask AP on rare categories.
Ranked #1 on Object Detection on PASCAL VOC 2007
1 code implementation • 10 Jun 2021 • Samira Abnar, Rianne van den Berg, Golnaz Ghiasi, Mostafa Dehghani, Nal Kalchbrenner, Hanie Sedghi
It has been shown that under the following two assumptions: (a) access to samples from intermediate distributions, and (b) samples being annotated with the amount of change from the source distribution, self-training can be successfully applied on gradually shifted samples to adapt the model toward the target distribution.
no code implementations • ICCV 2021 • Golnaz Ghiasi, Barret Zoph, Ekin D. Cubuk, Quoc V. Le, Tsung-Yi Lin
The results suggest self-training is a promising direction to aggregate labeled and unlabeled training data for learning general feature representations.
no code implementations • 29 Sep 2021 • Samira Abnar, Rianne van den Berg, Golnaz Ghiasi, Mostafa Dehghani, Nal Kalchbrenner, Hanie Sedghi
It is shown that under the following two assumptions: (a) access to samples from intermediate distributions, and (b) samples being annotated with the amount of change from the source distribution; self-training can be successfully applied on gradually shifted samples to adapt the model toward the target distribution.
no code implementations • 19 Nov 2021 • Hieu Pham, Zihang Dai, Golnaz Ghiasi, Kenji Kawaguchi, Hanxiao Liu, Adams Wei Yu, Jiahui Yu, Yi-Ting Chen, Minh-Thang Luong, Yonghui Wu, Mingxing Tan, Quoc V. Le
Second, while increasing the dataset size and the model size has been the defacto method to improve the performance of deep learning models like BASIC, the effect of a large contrastive batch size on such contrastive-trained image-text models is not well-understood.
1 code implementation • 22 Dec 2021 • Golnaz Ghiasi, Xiuye Gu, Yin Cui, Tsung-Yi Lin
We propose OpenSeg to address the above issue while still making use of scalable image-level supervision of captions.
no code implementations • 23 Mar 2022 • Tianjian Meng, Golnaz Ghiasi, Reza Mahjourian, Quoc V. Le, Mingxing Tan
It is commonly believed that high internal resolution combined with expensive operations (e. g. atrous convolutions) are necessary for accurate semantic segmentation, resulting in slow speed and large memory usage.