3 citations · 9 across the 10 of their papers we have counts for
11 papers
Position: Unlabeled IS NOT Equal to No Human Supervision in Visual Learning
Dong Lao
This position paper argues that the absence of labels does not imply the absence of human supervision in visual learning, and urges the research community to identify sources of su…
Triangular Consistency as a Universal Constraint for Learning Optical Flow
Yi Xiao, Carlos Rodriguez Coronel, Jing Zhan +3
We propose triangular consistency as a first-principled constraint for optical flow, which is agnostic to network architecture, supervision type, and dataset, and applies to both i…
Naïve PAINE: Lightweight Text-to-Image Generation Improvement with Prompt Evaluation
Joong Ho Kim, Nicholas Thai, Souhardya Saha Dip +2
Text-to-Image (T2I) generation is primarily driven by Diffusion Models (DM) which rely on random Gaussian noise. Thus, like playing the slots at a casino, a DM will produce differe…
Test-Time Defense Against Adversarial Attacks via Stochastic Resonance of Latent Ensembles
Dong Lao, Yuxiang Zhang, Haniyeh Ehsani Oskouie +3
We propose a test-time defense mechanism against adversarial attacks: imperceptible image perturbations that significantly alter the predictions of a model. Unlike existing methods…
RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions
Ziyao Zeng, Yangchao Wu, Hyoungseob Park +6
We propose a method for metric-scale monocular depth estimation. Inferring depth from a single image is an ill-posed problem due to the loss of scale from perspective projection du…
Diffeomorphic Template Registration for Atmospheric Turbulence Mitigation
Dong Lao, Congli Wang, Alex Wong +1
We describe a method for recovering the irradiance underlying a collection of images corrupted by atmospheric turbulence. Since supervised data is often technically impossible to o…
WorDepth: Variational Language Prior for Monocular Depth Estimation
Ziyao Zeng, Daniel Wang, Fengyu Yang +6
Three-dimensional (3D) reconstruction from a single image is an ill-posed problem with inherent ambiguities, i.e. scale. Predicting a 3D scene from text description(s) is similarly…
AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimation
Yangchao Wu, Tian Yu Liu, Hyoungseob Park +3
Unsupervised depth completion and estimation methods are trained by minimizing reconstruction error. Block artifacts from resampling, intensity saturation, and occlusions are among…
Sub-token ViT Embedding via Stochastic Resonance Transformers
Dong Lao, Yangchao Wu, Tian Yu Liu +2
Vision Transformer (ViT) architectures represent images as collections of high-dimensional vectorized tokens, each corresponding to a rectangular non-overlapping patch. This repres…
Divided Attention: Unsupervised Multi-Object Discovery with Contextually Separated Slots
Dong Lao, Zhengyang Hu, Francesco Locatello +2
We investigate the emergence of objects in visual perception in the absence of any semantic annotation. The resulting model has received no supervision, does not use any pre-traine…
On the Viability of Monocular Depth Pre-training for Semantic Segmentation
Dong Lao, Fengyu Yang, Daniel Wang +4
The question of whether pre-training on geometric tasks is viable for downstream transfer to semantic tasks is important for two reasons, one practical and the other scientific. If…