913 citations · 3.2k across the 60 of their papers we have counts for
11 papers · 1 filter
UFO: A Unified Framework towards Omni-supervised Object Detection
Zhongzheng Ren, Zhiding Yu, Xiaodong Yang +3
Existing work on object detection often relies on a single form of annotation: the model is trained using either accurate yet costly bounding boxes or cheaper but less expressive i…
Learning Calibrated Uncertainties for Domain Shift: A Distributionally Robust Learning Approach
Haoxuan Wang, Zhiding Yu, Yisong Yue +3
We propose a framework for learning calibrated uncertainties under domain shifts, where the source (training) distribution differs from the target (test) distribution. We detect su…
Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning
Weili Nie, Zhiding Yu, Lei Mao +3
Humans have an inherent ability to learn novel concepts from only a few samples and generalize these concepts to different situations. Even though today's machine learning models e…
Delving Deeper into Anti-aliasing in ConvNets
Xueyan Zou, Fanyi Xiao, Zhiding Yu +1
Aliasing refers to the phenomenon that high frequency signals degenerate into completely different ones after sampling. It arises as a problem in the context of deep learning as do…
Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification
Yang Zou, Xiaodong Yang, Zhiding Yu +2
Although a significant progress has been witnessed in supervised person re-identification (re-id), it remains challenging to generalize re-id models to new domains due to the huge…
Transposer: Universal Texture Synthesis Using Feature Maps as Transposed Convolution Filter
Guilin Liu, Rohan Taori, Ting-Chun Wang +6
Conventional CNNs for texture synthesis consist of a sequence of (de)-convolution and up/down-sampling layers, where each layer operates locally and lacks the ability to capture th…
Automated Synthetic-to-Real Generalization
Wuyang Chen, Zhiding Yu, Zhangyang Wang +1
Models trained on synthetic images often face degraded generalization to real data. As a convention, these models are often initialized with ImageNet pre-trained representation. Ye…
Unsupervised Controllable Generation with Self-Training
Grigorios G Chrysos, Jean Kossaifi, Zhiding Yu +1
Recent generative adversarial networks (GANs) are able to generate impressive photo-realistic images. However, controllable generation with GANs remains a challenging research prob…
Neural Networks with Recurrent Generative Feedback
Yujia Huang, James Gornet, Sihui Dai +4
Neural networks are vulnerable to input perturbations such as additive noise and adversarial attacks. In contrast, human perception is much more robust to such perturbations. The B…
Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation
Yingda Xia, Dong Yang, Zhiding Yu +7
Although having achieved great success in medical image segmentation, deep learning-based approaches usually require large amounts of well-annotated data, which can be extremely ex…
Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detection
Zhongzheng Ren, Zhiding Yu, Xiaodong Yang +4
Weakly supervised learning has emerged as a compelling tool for object detection by reducing the need for strong supervision during training. However, major challenges remain: (1)…