12 citations · 61 across the 16 of their papers we have counts for
16 papers
Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models
Songwei Ge, Seungjun Nah, Guilin Liu +7
Despite tremendous progress in generating high-quality images using diffusion models, synthesizing a sequence of animated frames that are both photorealistic and temporally coheren…
LASER: A Neuro-Symbolic Framework for Learning Spatial-Temporal Scene Graphs with Weak Supervision
Jiani Huang, Ziyang Li, Mayur Naik +1
Supervised approaches for learning spatio-temporal scene graphs (STSG) from video are greatly hindered due to their reliance on STSG-annotated videos, which are labor-intensive to…
Hyperbolic Contrastive Learning for Visual Representations beyond Objects
Songwei Ge, Shlok Mishra, Simon Kornblith +2
Although self-/un-supervised methods have led to rapid progress in visual representation learning, these methods generally treat objects and scenes using the same lens. In this pap…
A simple, efficient and scalable contrastive masked autoencoder for learning visual representations
Shlok Mishra, Joshua Robinson, Huiwen Chang +4
We introduce CAN, a simple, efficient and scalable method for self-supervised learning of visual representations. Our framework is a minimal and conceptually clean synthesis of (C)…
Autoregressive Perturbations for Data Poisoning
Pedro Sandoval-Segura, Vasu Singla, Jonas Geiping +3
The prevalence of data scraping from social media as a means to obtain datasets has led to growing concerns regarding unauthorized use of data. Data poisoning attacks have been pro…
Poisons that are learned faster are more effective
Pedro Sandoval-Segura, Vasu Singla, Liam Fowl +4
Imperceptible poisoning attacks on entire datasets have recently been touted as methods for protecting data privacy. However, among a number of defenses preventing the practical us…
Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer
Songwei Ge, Thomas Hayes, Harry Yang +5
Videos are created to express emotion, exchange information, and share experiences. Video synthesis has intrigued researchers for a long time. Despite the rapid progress driven by…
On the Spectral Bias of Convolutional Neural Tangent and Gaussian Process Kernels
Amnon Geifman, Meirav Galun, David Jacobs +1
We study the properties of various over-parametrized convolutional neural architectures through their respective Gaussian process and neural tangent kernels. We prove that, with no…
Object-Aware Cropping for Self-Supervised Learning
Shlok Mishra, Anshul Shah, Ankan Bansal +5
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-sup…
Robust Contrastive Learning Using Negative Samples with Diminished Semantics
Songwei Ge, Shlok Mishra, Haohan Wang +2
Unsupervised learning has recently made exceptional progress because of the development of more effective contrastive learning methods. However, CNNs are prone to depend on low-lev…
Maneuver Identification Challenge
Kaira Samuel, Vijay Gadepally, David Jacobs +8
AI algorithms that identify maneuvers from trajectory data could play an important role in improving flight safety and pilot training. AI challenges allow diverse teams to work tog…
Improved Detection of Face Presentation Attacks Using Image Decomposition
Shlok Kumar Mishra, Kuntal Sengupta, Max Horowitz-Gelb +3
Presentation attack detection (PAD) is a critical component in secure face authentication. We present a PAD algorithm to distinguish face spoofs generated by a photograph of a subj…
Shift Invariance Can Reduce Adversarial Robustness
Songwei Ge, Vasu Singla, Ronen Basri +1
Shift invariance is a critical property of CNNs that improves performance on classification. However, we show that invariance to circular shifts can also lead to greater sensitivit…
Low Curvature Activations Reduce Overfitting in Adversarial Training
Vasu Singla, Sahil Singla, David Jacobs +1
Adversarial training is one of the most effective defenses against adversarial attacks. Previous works suggest that overfitting is a dominant phenomenon in adversarial training lea…
Learning Visual Representations for Transfer Learning by Suppressing Texture
Shlok Mishra, Anshul Shah, Ankan Bansal +5
Recent literature has shown that features obtained from supervised training of CNNs may over-emphasize texture rather than encoding high-level information. In self-supervised learn…
Towards Automatic Generation of Questions from Long Answers
Shlok Kumar Mishra, Pranav Goel, Abhishek Sharma +3
Automatic question generation (AQG) has broad applicability in domains such as tutoring systems, conversational agents, healthcare literacy, and information retrieval. Existing eff…