Search Results for author:
Found 17 papers, 7 papers with code
Post-Training Quantization for Re-parameterization via Coarse & Fine Weight Splitting
Although neural networks have made remarkable advancements in various applications, they require substantial computational and memory resources.
FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugin
We apply the FlashOCC to diverse occupancy prediction baselines on the challenging Occ3D-nuScenes benchmarks and conduct extensive experiments to validate the effectiveness.
Unpaired Optical Coherence Tomography Angiography Image Super-Resolution via Frequency-Aware Inverse-Consistency GAN
For optical coherence tomography angiography (OCTA) images, a limited scanning rate leads to a trade-off between field-of-view (FOV) and imaging resolution.
TryOnDiffusion: A Tale of Two UNets
Given two images depicting a person and a garment worn by another person, our goal is to generate a visualization of how the garment might look on the input person.
Reference-based OCT Angiogram Super-resolution with Learnable Texture Generation
The key difference between the proposed method and traditional RefSR models is that the textures used during inference are generated by the LTG instead of being searched from a single reference image.
Improving Post-Training Quantization on Object Detection with Task Loss-Guided Lp Metric
PTQ optimizes the quantization parameters by different metrics to minimize the perturbation of quantization.
Benchmarking the Reliability of Post-training Quantization: a Particular Focus on Worst-case Performance
Post-training quantization (PTQ) is a popular method for compressing deep neural networks (DNNs) without modifying their original architecture or training procedures.
Foreground-Background Distribution Modeling Transformer for Visual Object Tracking
To address the above limitations, we propose a novel foreground-background distribution modeling transformer for visual object tracking (F-BDMTrack), including a fore-background agent learning (FBAL) module and a distribution-aware attention (DA2) module in a unified transformer architecture.
PD-Quant: Post-Training Quantization based on Prediction Difference Metric
It determines the quantization parameters by using the information of differences between network prediction before and after quantization.
Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D
The 3D scenes in our dataset come in minimally contrastive pairs: two scenes in a pair are almost identical, but a spatial relation holds in one and fails in the other.
Ranked #1 on
Spatial Relation Recognition
on Rel3D
Learning to Generate 3D Training Data Through Hybrid Gradient
We parametrize the design decisions as a real vector, and combine the approximate gradient and the analytical gradient to obtain the hybrid gradient of the network performance with respect to this vector.
Adversarial Objects Against LiDAR-Based Autonomous Driving Systems
Deep neural networks (DNNs) are found to be vulnerable against adversarial examples, which are carefully crafted inputs with a small magnitude of perturbation aiming to induce arbitrarily incorrect predictions.
Learning to Generate Synthetic 3D Training Data through Hybrid Gradient
We parametrize the design decisions as a real vector, and combine the approximate gradient and the analytical gradient to obtain the hybrid gradient of the network performance with respect to this vector.
MeshAdv: Adversarial Meshes for Visual Recognition
Highly expressive models such as deep neural networks (DNNs) have been widely applied to various applications.
Decorrelated Batch Normalization
Batch Normalization (BN) is capable of accelerating the training of deep models by centering and scaling activations within mini-batches.
Shape from Shading through Shape Evolution
The evolution generates better shapes guided by the network training, while the training improves by using the evolved shapes.
Single-Image Depth Perception in the Wild
This paper studies single-image depth perception in the wild, i. e., recovering depth from a single image taken in unconstrained settings.
