Search Results for author:
Found 33 papers, 19 papers with code
Few-Shot Semantic Segmentation with Democratic Attention Networks
The crux of few-shot segmentation is to extract object information from the support image and then propagate it to guide the segmentation of query images.
The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer
This paper introduces SAIL, a single transformer unified multimodal large language model (MLLM) that integrates raw pixel encoding and language decoding within a singular architecture.
Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness
The latter aims to aggregate information from all available views to recover Bird's-Eye-View images, contributing to a comprehensive overview of the entire scene.
DocVideoQA: Towards Comprehensive Understanding of Document-Centric Videos through Question Answering
Through fine-tuning, the LLM is equipped with audio-visual capabilities, leading to significant improvements in document-centric video understanding.
OpenSatMap: A Fine-grained High-resolution Satellite Dataset for Large-scale Map Construction
By publishing and maintaining the dataset, we provide a high-quality benchmark for satellite-based map construction and downstream tasks like autonomous driving.
Reconstructive Visual Instruction Tuning
This paper introduces reconstructive visual instruction tuning (ROSS), a family of Large Multimodal Models (LMMs) that exploit vision-centric supervision signals.
CJEval: A Benchmark for Assessing Large Language Models Using Chinese Junior High School Exam Data
Online education platforms have significantly transformed the dissemination of educational resources by providing a dynamic and digital infrastructure.
DocTabQA: Answering Questions from Long Documents Using Tables
To the best of our knowledge, this problem has not been previously explored.
VISA: Reasoning Video Object Segmentation via Large Language Models
In this paper, we introduce a new task, Reasoning Video Object Segmentation (ReasonVOS).
Ranked #3 on
Referring Video Object Segmentation
on ReVOS
JeDi: Joint-Image Diffusion Models for Finetuning-Free Personalized Text-to-Image Generation
Personalized text-to-image generation models enable users to create images that depict their individual possessions in diverse scenes, finding applications in various domains.
Mining Open Semantics from CLIP: A Relation Transition Perspective for Few-Shot Learning
Specifically, we adopt a transformer module which takes the visual feature as "Query", the text features of the anchors as "Key" and the similarity matrix between the text features of anchor and target classes as "Value".
Alpha Invariance: On Inverse Scaling Between Distance and Volume Density in Neural Radiance Fields
Scale-ambiguity in 3D scene dimensions leads to magnitude-ambiguity of volumetric densities in neural radiance fields, i. e., the densities double when scene size is halved, and vice versa.
Continual Forgetting for Pre-trained Vision Models
(i) For unwanted knowledge, efficient and effective deleting is crucial.
Dynamic Prototype Adaptation with Distillation for Few-shot Point Cloud Segmentation
Existing prototype-based methods rely on support prototypes to guide the segmentation of query point clouds, but they encounter challenges when significant object variations exist between the support prototypes and query features.
Bootstrap Masked Visual Modeling via Hard Patches Mining
To empower the model as a teacher, we propose Hard Patches Mining (HPM), predicting patch-wise losses and subsequently determining where to mask.
DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions
As it is empirically observed that Vision Transformers (ViTs) are quite insensitive to the order of input tokens, the need for an appropriate self-supervised pretext task that enhances the location awareness of ViTs is becoming evident.
Using Unreliable Pseudo-Labels for Label-Efficient Semantic Segmentation
A common practice is to select the highly confident predictions as the pseudo-ground-truths for each pixel, but it leads to a problem that most pixels may be left unused due to their unreliability.
Balancing Logit Variation for Long-tailed Semantic Segmentation
In this way, we manage to close the gap between the feature areas of different categories, resulting in a more balanced representation.
Pulling Target to Source: A New Perspective on Domain Adaptive Semantic Segmentation
To this end, we propose T2S-DA, which we interpret as a form of pulling Target to Source for Domain Adaptation, encouraging the model in learning similar cross-domain features.
PiClick: Picking the desired mask from multiple candidates in click-based interactive segmentation
Click-based interactive segmentation aims to generate target masks via human clicking, which facilitates efficient pixel-level annotation and image editing.
Hard Patches Mining for Masked Image Modeling
We observe that the reconstruction loss can naturally be the metric of the difficulty of the pre-training task.
Towards Open-Vocabulary Video Instance Segmentation
Video Instance Segmentation (VIS) aims at segmenting and categorizing objects in videos from a closed set of training categories, lacking the generalization ability to handle novel categories in real-world videos.
Few-shot Semantic Segmentation with Support-induced Graph Convolutional Network
However, the appearance variations between objects from the same category could be extremely large, leading to unreliable feature matching and query mask prediction.
Ranked #45 on
Few-Shot Semantic Segmentation
on PASCAL-5i (1-Shot)
LoopDraw: a Loop-Based Autoregressive Model for Shape Synthesis and Editing
There is no settled universal 3D representation for geometry with many alternatives such as point clouds, meshes, implicit functions, and voxels to name a few.
Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation
We propose to apply chain rule on the learned gradients, and back-propagate the score of a diffusion model through the Jacobian of a differentiable renderer, which we instantiate to be a voxel radiance field.
Ranked #6 on
Text to 3D
on T$^3$Bench
Learning from Future: A Novel Self-Training Framework for Semantic Segmentation
Self-training has shown great potential in semi-supervised learning.
NFormer: Robust Person Re-identification with Neighbor Transformer
To tackle this issue, we propose a Neighbor Transformer Network, or NFormer, which explicitly models interactions across all input images, thus suppressing outlier features and leading to more robust representations overall.
Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels
A common practice is to select the highly confident predictions as the pseudo ground-truth, but it leads to a problem that most pixels may be left unused due to their unreliability.
Decoupled IoU Regression for Object Detection
Prior works propose to predict Intersection-over-Union (IoU) between bounding boxes and corresponding ground-truths to improve NMS, while accurately predicting IoU is still a challenging problem.
Attentional Prototype Inference for Few-Shot Segmentation
We define a global latent variable to represent the prototype of each object category, which we model as a probabilistic distribution.
SwiftNet: Real-time Video Object Segmentation
In this work we present SwiftNet for real-time semisupervised video object segmentation (one-shot VOS), which reports 77. 8% J &F and 70 FPS on DAVIS 2017 validation dataset, leading all present solutions in overall accuracy and speed performance.
Pixel Consensus Voting for Panoptic Segmentation
The core of our approach, Pixel Consensus Voting, is a framework for instance segmentation based on the Generalized Hough transform.
Ranked #36 on
Panoptic Segmentation
on COCO test-dev
DIODE: A Dense Indoor and Outdoor DEpth Dataset
We introduce DIODE, a dataset that contains thousands of diverse high resolution color images with accurate, dense, long-range depth measurements.
