Search Results for author:
Found 29 papers, 25 papers with code
Goal-oriented Autonomous Driving
Modern autonomous driving system is characterized as modular tasks in sequential order, i. e., perception, prediction and planning.
BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision
The proposed method is verified with a wide spectrum of traditional and modern image backbones and achieves new SoTA results on the large-scale nuScenes dataset.
Ranked #1 on
3D Object Detection
on nuScenes Camera Only
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information
It has been proved that combining multiple pre-training strategies and data from various modalities/sources can greatly boost the training of large-scale models.
Ranked #1 on
Semantic Segmentation
on ADE20K
(using extra training data)
Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks
In this paper, we propose Uni-Perceiver v2, which is the first generalist model capable of handling major large-scale vision and vision-language tasks with competitive performance.
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
Compared to the great progress of large-scale vision transformers (ViTs) in recent years, large-scale models based on convolutional neural networks (CNNs) are still in an early state.
Ranked #1 on
Object Detection
on COCO test-dev
Demystify Transformers & Convolutions in Modern Image Deep Networks
Although the novel feature transformation designs are often claimed as the source of gain, some backbones may benefit from advanced engineering techniques, which makes it hard to identify the real gain from the key feature transformation operators.
Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe
As sensor configurations get more complex, integrating multi-source information from different sensors and representing features in a unified view come of vital importance.
Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs
To mitigate such interference, we introduce the Conditional Mixture-of-Experts (Conditional MoEs) to generalist models.
Siamese Image Modeling for Self-Supervised Vision Representation Learning
Driven by these analysis, we propose Siamese Image Modeling (SiameseIM), which predicts the dense representations of an augmented view, based on another masked view from the same image but with different augmentations.
DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation
This paper proposes a simple baseline framework for video-based 2D/3D human pose estimation that can achieve 10 times efficiency improvement over existing works without any performance degradation, named DeciWatch.
Ranked #1 on
2D Human Pose Estimation
on JHMDB (2D poses only)
Searching Parameterized AP Loss for Object Detection
In this paper, we propose Parameterized AP Loss, where parameterized functions are introduced to substitute the non-differentiable components in the AP calculation.
Exploring the Equivalence of Siamese Self-Supervised Learning via A Unified Gradient Framework
These methods appear to be quite different in the designed loss functions from various motivations.
Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks
The model is pre-trained on several uni-modal and multi-modal tasks, and evaluated on a variety of downstream tasks, including novel tasks that did not appear in the pre-training stage.
VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition
Deep learning-based models encounter challenges when processing long-tailed data in the real world.
Ranked #1 on
Long-tail Learning
on Places-LT
(using extra training data)
Collaborative Visual Navigation
As a fundamental problem for Artificial Intelligence, multi-agent system (MAS) is making rapid progress, mainly driven by multi-agent reinforcement learning (MARL) techniques.
AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks
However, the automatic design of loss functions for generic tasks with various evaluation metrics remains under-investigated.
Unsupervised Object Detection with LiDAR Clues
We further identify another major issue, seldom noticed by the community, that the long-tailed and open-ended (sub-)category distribution should be accommodated.
Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentation
In this paper, we propose to automate the design of metric-specific loss functions by searching differentiable surrogate losses for each metric.
Deformable DETR: Deformable Transformers for End-to-End Object Detection
DETR has been recently proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance.
Ranked #66 on
Object Detection
on COCO test-dev
Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation
In the feature maps of CNNs, there commonly exists considerable spatial redundancy that leads to much repetitive processing.
Deformable Kernels: Adapting Effective Receptive Fields for Object Deformation
This is typically done by augmenting static operators with learned free-form sampling grids in the image space, dynamically tuned to the data and task for adapting the receptive field.
Ranked #183 on
Object Detection
on COCO test-dev
VL-BERT: Pre-training of Generic Visual-Linguistic Representations
We introduce a new pre-trainable generic representation for visual-linguistic tasks, called Visual-Linguistic BERT (VL-BERT for short).
Ranked #1 on
Visual Question Answering
on VCR (Q-A) dev
An Empirical Study of Spatial Attention Mechanisms in Deep Networks
Attention mechanisms have become a popular component in deep neural networks, yet there has been little examination of how different influencing factors and methods for computing attention from these factors affect performance.
Integrated Object Detection and Tracking with Tracklet-Conditioned Detection
Accurate detection and tracking of objects is vital for effective video understanding.
Ranked #13 on
Video Object Detection
on ImageNet VID
Deformable ConvNets v2: More Deformable, Better Results
The superior performance of Deformable Convolutional Networks arises from its ability to adapt to the geometric variations of objects.
Ranked #119 on
Object Detection
on COCO minival
Towards High Performance Video Object Detection for Mobiles
In this paper, we present a light weight network architecture for video object detection on mobiles.
Towards High Performance Video Object Detection
There has been significant progresses for image object detection in recent years.
Flow-Guided Feature Aggregation for Video Object Detection
The accuracy of detection suffers from degenerated object appearances in videos, e. g., motion blur, video defocus, rare poses, etc.
Ranked #19 on
Video Object Detection
on ImageNet VID
Deep Feature Flow for Video Recognition
Yet, it is non-trivial to transfer the state-of-the-art image recognition networks to videos as per-frame evaluation is too slow and unaffordable.
Ranked #9 on
Video Semantic Segmentation
on Cityscapes val
