348 citations · 1.9k across the 91 of their papers we have counts for
17 papers · 1 filter
Auto-X3D: Ultra-Efficient Video Understanding via Finer-Grained Neural Architecture Search
Yifan Jiang, Xinyu Gong, Junru Wu +3
Efficient video architecture is the key to deploying video recognition systems on devices with limited computing resources. Unfortunately, existing video architectures are often co…
AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition
Yulin Wang, Yang Yue, Yuanze Lin +6
Recent works have shown that the computational efficiency of video recognition can be significantly improved by reducing the spatial redundancy. As a representative work, the adapt…
SeMask: Semantically Masked Transformers for Semantic Segmentation
Jitesh Jain, Anukriti Singh, Nikita Orlov +4
Finetuning a pretrained backbone in the encoder part of an image transformer network has been the traditional approach for the semantic segmentation task. However, such an approach…
More Control for Free! Image Synthesis with Semantic Diffusion Guidance
Xihui Liu, Dong Huk Park, Samaneh Azadi +6
Controllable image synthesis models allow creation of diverse images based on text instructions or guidance from a reference image. Recently, denoising diffusion probabilistic mode…
Global and Local Alignment Networks for Unpaired Image-to-Image Translation
Guanglei Yang, Hao Tang, Humphrey Shi +5
The goal of unpaired image-to-image translation is to produce an output image reflecting the target domain's style while keeping unrelated contents of the input source image unchan…
Feudal Reinforcement Learning by Reading Manuals
Kai Wang, Zhonghao Wang, Mo Yu +1
Reading to act is a prevalent but challenging task which requires the ability to reason from a concise instruction. However, previous works face the semantic mismatch between the l…
ConvMLP: Hierarchical Convolutional MLPs for Vision
Jiachen Li, Ali Hassani, Steven Walton +1
MLP-based architectures, which consist of a sequence of consecutive multi-layer perceptron blocks, have recently been found to reach comparable results to convolutional and transfo…
Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics
Wuyang Chen, Xinyu Gong, Junru Wu +5
This work targets designing a principled and unified training-free framework for Neural Architecture Search (NAS), with high performance, low cost, and in-depth interpretation. NAS…
MSN: Efficient Online Mask Selection Network for Video Instance Segmentation
Vidit Goel, Jiachen Li, Shubhika Garg +2
In this work we present a novel solution for Video Instance Segmentation(VIS), that is automatically generating instance level segmentation masks along with object class and tracki…
RSCA: Real-time Segmentation-based Context-Aware Scene Text Detection
Jiachen Li, Yuan Lin, Rongrong Liu +2
Segmentation-based scene text detection methods have been widely adopted for arbitrary-shaped text detection recently, since they make accurate pixel-level predictions on curved te…
Is In-Domain Data Really Needed? A Pilot Study on Cross-Domain Calibration for Network Quantization
Haichao Yu, Linjie Yang, Humphrey Shi
Post-training quantization methods use a set of calibration data to compute quantization ranges for network parameters and activations. The calibration data usually comes from the…
Pseudo-IoU: Improving Label Assignment in Anchor-Free Object Detection
Jiachen Li, Bowen Cheng, Rogerio Feris +4
Current anchor-free object detectors are quite simple and effective yet lack accurate label assignment methods, which limits their potential in competing with classic anchor-based…
Escaping the Big Data Paradigm with Compact Transformers
Ali Hassani, Steven Walton, Nikhil Shah +3
With the rise of Transformers as the standard for language processing, and their advancements in computer vision, there has been a corresponding growth in parameter size and amount…
Learning to Track Instances without Video Annotations
Yang Fu, Sifei Liu, Umar Iqbal +3
Tracking segmentation masks of multiple instances has been intensively studied, but still faces two fundamental challenges: 1) the requirement of large-scale, frame-wise annotation…
Study Group Learning: Improving Retinal Vessel Segmentation Trained with Noisy Labels
Yuqian Zhou, Hanchao Yu, Humphrey Shi
Retinal vessel segmentation from retinal images is an essential task for developing the computer-aided diagnosis system for retinal diseases. Efforts have been made on high-perform…
UltraSR: Spatial Encoding is a Missing Key for Implicit Image Function-based Arbitrary-Scale Super-Resolution
Xingqian Xu, Zhangyang Wang, Humphrey Shi
The recent success of NeRF and other related implicit neural representation methods has opened a new path for continuous image representation, where pixel values no longer need to…
Adaptive Consistency Regularization for Semi-Supervised Transfer Learning
Abulikemu Abuduweili, Xingjian Li, Humphrey Shi +2
While recent studies on semi-supervised learning have shown remarkable progress in leveraging both labeled and unlabeled data, most of them presume a basic setting of the model is…