no code implementations • 11 Oct 2023 • Ziqi Wen, Tianqin Li, Zhi Jing, Tai Sing Lee
The current benchmark for evaluating a model's global shape bias is a set of style-transferred images with the assumption that resistance to the attack of style transfer is related to the development of global structure sensitivity in the model.
no code implementations • 3 Jul 2023 • Tianye Wang, Haoxuan Yao, Tai Sing Lee, Jiayi Hong, Yang Li, Hongfei Jiang, Ian Max Andolina, Shiming Tang
To gain deeper insights into visual processing of natural scenes, we utilized widefield calcium-imaging of primate V4 in response to many natural images, generating a large dataset of columnar-scale responses.
2 code implementations • 29 Oct 2022 • Nikolas McNeal, Jennifer Huang, Aniekan Umoren, Shuqi Dai, Roger Dannenberg, Richard Randall, Tai Sing Lee
Our findings suggest that predictability is correlated with human perception of musicality and that a predictive coding neural network trained on music can be used to characterize the features and motifs contributing to human perception of music.
1 code implementation • ICCV 2021 • Andrew Luo, Tianqin Li, Wen-Hao Zhang, Tai Sing Lee
Recent advances in deep generative models have led to immense progress in 3D shape synthesis.
no code implementations • 2 Oct 2021 • Yimeng Zhang, Harold Rockwell, Sicheng Dai, Ge Huang, Stephen Tsou, Yuanyuan Wei, Tai Sing Lee
Feedforward CNN models have proven themselves in recent years as state-of-the-art models for predicting single-neuron responses to natural images in early visual cortical neurons.
no code implementations • ICLR 2022 • Tianqin Li, Zijie Li, Andrew Luo, Harold Rockwell, Amir Barati Farimani, Tai Sing Lee
To test our proposal, we show in a few-shot image generation task, that having a prototype memory during attention can improve image synthesis quality, learn interpretable visual concept clusters, as well as improve the robustness of the model.
no code implementations • 22 Dec 2019 • Siming Yan, Xuyang Fang, Bowen Xiao, Harold Rockwell, Yimeng Zhang, Tai Sing Lee
The abundant recurrent horizontal and feedback connections in the primate visual cortex are thought to play an important role in bringing global and semantic contextual information to early visual areas during perceptual inference, helping to resolve local ambiguity and fill in missing details.
1 code implementation • NeurIPS 2019 • Wenhao Zhang, Si Wu, Brent Doiron, Tai Sing Lee
This study provides a normative theory for how Bayesian causal inference can be implemented in neural circuits.
no code implementations • NeurIPS 2019 • Jie-Lin Qiu, Ge Huang, Tai Sing Lee
The model is a hierarchical recurrent neural model that learns to predict video sequences using the incoming video signals as teaching signals.
no code implementations • 19 Nov 2019 • Ziniu Wu, Harold Rockwell, Yimeng Zhang, Shiming Tang, Tai Sing Lee
System identification techniques -- projection pursuit regression models (PPRs) and convolutional neural networks (CNNs) -- provide state-of-the-art performance in predicting visual cortical neurons' responses to arbitrary input stimuli.
no code implementations • ICLR 2019 • Siming Yan*, Bowen Xiao*, Yimeng Zhang, Tai Sing Lee
In this work, we designed a Contextual Recurrent Convolutional Network with this feature embedded in a standard CNN structure.
no code implementations • ICLR 2019 • Jie-Lin Qiu, Ge Huang, Tai Sing Lee
In this paper we developed a hierarchical network model, called Hierarchical Prediction Network (HPNet) to understand how spatiotemporal memories might be learned and encoded in a representational hierarchy for predicting future video frames.
no code implementations • 25 Jan 2019 • Jie-Lin Qiu, Ge Huang, Tai Sing Lee
Within each level, the feed-forward path and the feedback path intersect in a recurrent gated circuit, instantiated in a LSTM module, to generate a prediction or explanation of the incoming signals.
no code implementations • 22 May 2017 • Hao Wang, Xingyu Lin, Yimeng Zhang, Tai Sing Lee
Trained on imagined occluded scenarios under the object persistence constraint, our network discovered more subtle and localized image features that were neglected by the original network for object classification, obtaining better separability of different object classes in the feature space.
no code implementations • 22 May 2017 • Heqing Ya, Haonan Sun, Jeffrey Helt, Tai Sing Lee
In this particular problem, a user is presented with a deformed picture of a Chinese phrase and eight low-resolution images.
no code implementations • 31 Mar 2017 • Xingyu Lin, Hao Wang, Zhihao LI, Yimeng Zhang, Alan Yuille, Tai Sing Lee
We develop a model of perceptual similarity judgment based on re-training a deep convolution neural network (DCNN) that learns to associate different views of each 3D object to capture the notion of object persistence and continuity in our visual experience.
no code implementations • 14 Nov 2014 • Ming-Min Zhao, Chengxu Zhuang, Yizhou Wang, Tai Sing Lee
We propose a new neurally-inspired model that can learn to encode the global relationship context of visual events across time and space and to use the contextual information to modulate the analysis by synthesis process in a predictive coding framework.