116 citations · 257 across the 26 of their papers we have counts for
26 papers
Unified Open-Vocabulary Dense Visual Prediction
Hengcan Shi, Munawar Hayat, Jianfei Cai
In recent years, open-vocabulary (OV) dense visual prediction (such as OV object detection, semantic, instance and panoptic segmentations) has attracted increasing research attenti…
ObjectSDF++: Improved Object-Compositional Neural Implicit Surfaces
Qianyi Wu, Kaisiyuan Wang, Kejie Li +2
In recent years, neural implicit surface reconstruction has emerged as a popular paradigm for multi-view 3D reconstruction. Unlike traditional multi-view stereo approaches, the neu…
Open-Vocabulary Object Detection via Scene Graph Discovery
Hengcan Shi, Munawar Hayat, Jianfei Cai
In recent years, open-vocabulary (OV) object detection has attracted increasing research attention. Unlike traditional detection, which only recognizes fixed-category objects, OV d…
Stitched ViTs are Flexible Vision Backbones
Zizheng Pan, Jing Liu, Haoyu He +2
Large pretrained plain vision Transformers (ViTs) have been the workhorse for many downstream tasks. However, existing works utilizing off-the-shelf ViTs are inefficient in terms o…
Explicit Correspondence Matching for Generalizable Neural Radiance Fields
Yuedong Chen, Haofei Xu, Qianyi Wu +3
We present a new generalizable NeRF method that is able to directly generalize to new unseen scenarios and perform novel view synthesis with as few as two source views. The key to…
Stitchable Neural Networks
Zizheng Pan, Jianfei Cai, Bohan Zhuang
The public model zoo containing enormous powerful pretrained model families (e.g., ResNet/DeiT) has reached an unprecedented scope than ever, which significantly contributes to the…
Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning
Haoyu He, Jianfei Cai, Jing Zhang +2
Visual Parameter-Efficient Fine-Tuning (PEFT) has become a powerful alternative for full fine-tuning so as to adapt pre-trained vision models to downstream tasks, which only tunes…
Vector Quantized Wasserstein Auto-Encoder
Tung-Long Vuong, Trung Le, He Zhao +4
Learning deep discrete latent presentations offers a promise of better symbolic and summarized abstractions that are more useful to subsequent downstream tasks. Inspired by the sem…
Class Enhancement Losses with Pseudo Labels for Zero-shot Semantic Segmentation
Son Duy Dao, Hengcan Shi, Dinh Phung +1
Recent mask proposal models have significantly improved the performance of zero-shot semantic segmentation. However, the use of a `background' embedding during training in these me…
Learning Object-Language Alignments for Open-Vocabulary Object Detection
Chuang Lin, Peize Sun, Yi Jiang +5
Existing object detection methods are bounded in a fixed-set vocabulary by costly labeled data. When dealing with novel categories, the model has to be retrained with more bounding…
MARLIN: Masked Autoencoder for facial video Representation LearnINg
Zhixi Cai, Shreya Ghosh, Kalin Stefanov +5
This paper proposes a self-supervised approach to learn universal facial representations from videos, that can transfer across a variety of facial analysis tasks such as Facial Att…
Unifying Flow, Stereo and Depth Estimation
Haofei Xu, Jing Zhang, Jianfei Cai +4
We present a unified formulation and model for three motion and 3D perception tasks: optical flow, rectified stereo matching and unrectified stereo depth estimation from posed imag…
Learning to Collocate Visual-Linguistic Neural Modules for Image Captioning
Xu Yang, Hanwang Zhang, Chongyang Gao +1
Humans tend to decompose a sentence into different parts like \textsc{sth do sth at someplace} and then fill each part with certain content. Inspired by this, we follow the \textit…
ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsing
Daxuan Ren, Jianmin Zheng, Jianfei Cai +2
Sketch-and-extrude is a common and intuitive modeling process in computer aided design. This paper studies the problem of learning the shape given in the form of point clouds by in…
MoVQ: Modulating Quantized Vectors for High-Fidelity Image Generation
Chuanxia Zheng, Long Tung Vuong, Jianfei Cai +1
Although two-stage Vector Quantized (VQ) generative models allow for synthesizing high-fidelity and high-resolution images, their quantization operator encodes similar patches with…
EcoFormer: Energy-Saving Attention with Linear Complexity
Jing Liu, Zizheng Pan, Haoyu He +2
Transformer is a transformative framework that models sequential data and has achieved remarkable performance on a wide range of tasks, but with high computational and energy cost.…
FocusFormer: Focusing on What We Need via Architecture Sampler
Jing Liu, Jianfei Cai, Bohan Zhuang
Vision Transformers (ViTs) have underpinned the recent breakthroughs in computer vision. However, designing the architectures of ViTs is laborious and heavily relies on expert know…
Object-Compositional Neural Implicit Surfaces
Qianyi Wu, Xian Liu, Yuedong Chen +4
The neural implicit representation has shown its effectiveness in novel view synthesis and high-quality 3D reconstruction from multi-view images. However, most approaches focus on…
Transformer Scale Gate for Semantic Segmentation
Hengcan Shi, Munawar Hayat, Jianfei Cai
Effectively encoding multi-scale contextual information is crucial for accurate semantic segmentation. Existing transformer-based segmentation models combine features across scales…
Fast Vision Transformers with HiLo Attention
Zizheng Pan, Jianfei Cai, Bohan Zhuang
Vision Transformers (ViTs) have triggered the most recent and significant breakthroughs in computer vision. Their efficient designs are mostly guided by the indirect metric of comp…
High-Quality Pluralistic Image Completion via Code Shared VQGAN
Chuanxia Zheng, Guoxian Song, Tat-Jen Cham +3
PICNet pioneered the generation of multiple and diverse results for image completion task, but it required a careful balance between loss (diversity) and reconstruct…
Dynamic Focus-aware Positional Queries for Semantic Segmentation
Haoyu He, Jianfei Cai, Zizheng Pan +4
The DETR-like segmentors have underpinned the most recent breakthroughs in semantic segmentation, which end-to-end train a set of queries representing the class prototypes or targe…
Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar Network
Duy-Tho Le, Hengcan Shi, Hamid Rezatofighi +1
Efficiently and accurately detecting people from 3D point cloud data is of great importance in many robotic and autonomous driving applications. This fundamental perception task is…
Rapid Elastic Architecture Search under Specialized Classes and Resource Constraints
Jing Liu, Bohan Zhuang, Mingkui Tan +4
In many real-world applications, we often need to handle various deployment scenarios, where the resource constraint and the superclass of interest corresponding to a group of clas…