Search Results for author:
Found 23 papers, 8 papers with code
Generative Physical AI in Vision: A Survey
Therefore, the field of physics-aware generation in computer vision is rapidly growing, calling for a comprehensive survey to provide a structured analysis of current efforts.
Enhancing Privacy-Utility Trade-offs to Mitigate Memorization in Diffusion Models
Text-to-image diffusion models have demonstrated remarkable capabilities in creating images highly aligned with user prompts, yet their proclivity for memorizing training set images has sparked concerns about the originality of the generated images and privacy issues, potentially leading to legal complications for both model owners and users, particularly when the memorized images contain proprietary content.
Investigating Memorization in Video Diffusion Models
Diffusion models, widely used for image and video generation, face a significant limitation: the risk of memorizing and reproducing training data during inference, potentially generating unauthorized copyrighted content.
Exploring Local Memorization in Diffusion Models via Bright Ending Attention
Furthermore, driven by our observation that local memorization significantly underperforms in existing tasks of measuring, detecting, and mitigating memorization in diffusion models compared to global memorization, we propose a simple yet effective method to integrate BE and the results of the new localization task into these existing frameworks.
Compress Guidance in Conditional Diffusion Sampling
We found that enforcing guidance throughout the sampling process is often counterproductive due to the model-fitting issue, where samples are 'tuned' to match the classifier's parameters rather than generalizing the expected condition.
Surgical Triplet Recognition via Diffusion Model
In this paper, we propose DiffTriplet, a new generative framework for surgical triplet recognition employing the diffusion model, which predicts surgical triplets via iterative denoising.
Ranked #1 on
Action Triplet Recognition
on CholecT45 (cross-val)
Towards Memorization-Free Diffusion Models
Pretrained diffusion models and their outputs are widely accessible due to their exceptional capacity for synthesizing high-quality images and their open-source nature.
Collage Prompting: Budget-Friendly Visual Recognition with GPT-4V
Based on the observation that the accuracy of GPT-4V's image recognition varies significantly with the order of images within the collage prompt, our method further learns to optimize the arrangement of images for maximum recognition accuracy.
Residual Learning in Diffusion Models
This gap results in a residual in the generated images adversely impacting the image quality.
Boosting Diffusion Models with an Adaptive Momentum Sampler
Our proposed sampler can be readily applied to a pre-trained diffusion model, utilizing momentum mechanisms and adaptive updating to smooth the reverse sampling process and ensure stable generation, resulting in outputs of enhanced quality.
Diffusion Action Segmentation
Temporal action segmentation is crucial for understanding long-form videos.
Ranked #3 on
Action Segmentation
on GTEA
Two-in-one Knowledge Distillation for Efficient Facial Forgery Detection
More specifically, knowledge distillation on both the spatial and frequency branches has degraded performance than distillation only on the spatial branch.
Calibrating a Deep Neural Network with Its Predecessors
However, early stopping, as a well-known technique to mitigate overfitting, fails to calibrate networks.
Beyond Pretrained Features: Noisy Image Modeling Provides Adversarial Defense
Experimental results demonstrate that, in terms of adversarial robustness, NIM is superior to MIM thanks to its effective denoising capability.
Private Image Generation With Dual-Purpose Auxiliary Classifier
However, apart from this standard utility, we identify the "reversed utility" as another crucial aspect, which computes the accuracy on generated data of a classifier trained using real data, dubbed as real2gen accuracy (r2g%).
Personalized Image Generation for Color Vision Deficiency Population
Approximately, 350 million people, a proportion of 8%, suffer from color vision deficiency (CVD).
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution
Video Super-Resolution (VSR) aims to restore high-resolution (HR) videos from low-resolution (LR) videos.
Towards Unified Surgical Skill Assessment
In this paper, a unified multi-path framework for automatic surgical skill assessment is proposed, which takes care of multiple composing aspects of surgical skills, including surgical tool usage, intraoperative event pattern, and other skill proxies.
Unsupervised Surgical Instrument Segmentation via Anchor Generation and Semantic Diffusion
In the experiments on the binary instrument segmentation task of the 2017 MICCAI EndoVis Robotic Instrument Segmentation Challenge dataset, the proposed method achieves 0. 71 IoU and 0. 81 Dice score without using a single manual annotation, which is promising to show the potential of unsupervised learning for surgical tool segmentation.
Surgical Skill Assessment on In-Vivo Clinical Data via the Clearness of Operating Field
Then an objective and automated framework based on neural network is proposed to predict surgical skills through the proxy of COF.
Completeness Modeling and Context Separation for Weakly Supervised Temporal Action Localization
In this work, we first identify two underexplored problems posed by the weak supervision for temporal action localization, namely action completeness modeling and action-context separation.
Ranked #14 on
Weakly Supervised Action Localization
on ActivityNet-1.3
Deep Reinforcement Learning for Surgical Gesture Segmentation and Classification
Recognition of surgical gesture is crucial for surgical skill assessment and efficient surgery training.
Ranked #3 on
Action Segmentation
on JIGSAWS
