Search Results for author:
Found 52 papers, 19 papers with code
PackDet: Packed Long-Head Object Detector
State-of-the-art object detectors exploit multi-branch structure and predict objects at several different scales, although substantially boosted accuracy is acquired, low efficiency is inevitable as fragmented structure is hardware unfriendly.
Weak Distribution Detectors Lead to Stronger Generalizability of Vision-Language Prompt Tuning
The idea is realized by exploiting out-of-distribution (OOD) detection to predict whether a sample belongs to a base distribution or a novel distribution and then using the score generated by a dedicated competition based scoring function to fuse the zero-shot and few-shot classifier.
SegICL: A Universal In-context Learning Framework for Enhanced Segmentation in Medical Imaging
Extensive experimental validation of SegICL demonstrates a positive correlation between the number of prompt samples and segmentation performance on OOD modalities and tasks.
Enhancing Visual Continual Learning with Language-Guided Supervision
Existing methods commonly utilize the one-hot labels and randomly initialize the classifier head.
Defying Imbalanced Forgetting in Class Incremental Learning
This intriguing phenomenon, discovered in replay-based Class Incremental Learning (CIL), highlights the imbalanced forgetting of learned classes, as their accuracy is similar before the occurrence of catastrophic forgetting.
Compositional Kronecker Context Optimization for Vision-Language Models
Context Optimization (CoOp) has emerged as a simple yet effective technique for adapting CLIP-like vision-language models to downstream image recognition tasks.
PAD: Self-Supervised Pre-Training with Patchwise-Scale Adapter for Infrared Images
Self-supervised learning (SSL) for RGB images has achieved significant success, yet there is still limited research on SSL for infrared images, primarily due to three prominent challenges: 1) the lack of a suitable large-scale infrared pre-training dataset, 2) the distinctiveness of non-iconic infrared images rendering common pre-training tasks like masked image modeling (MIM) less effective, and 3) the scarcity of fine-grained textures making it particularly challenging to learn general image features.
Cooperation Does Matter: Exploring Multi-Order Bilateral Relations for Audio-Visual Segmentation
For the first time, our framework explores three types of bilateral entanglements within AVS: pixel entanglement, modality entanglement, and temporal entanglement.
Change Detection Methods for Remote Sensing in the Last Decade: A Comprehensive Review
We first introduce some preliminary knowledge for the change detection task, such as problem definition, datasets, evaluation metrics, and transformer basics, as well as provide a detailed taxonomy of existing algorithms from three different perspectives: algorithm granularity, supervision modes, and learning frameworks in the methodology section.
Free Lunch for Generating Effective Outlier Supervision
Generally, existing approaches in dealing with out-of-distribution (OOD) detection mainly focus on the statistical difference between the features of OOD and in-distribution (ID) data extracted by the classifiers.
Bilateral Memory Consolidation for Continual Learning
Humans are proficient at continuously acquiring and integrating new knowledge.
Prompt Tuning with Soft Context Sharing for Vision-Language Models
Inspired by the fact that modeling task relationship by multi-task learning can usually boost performance, we propose a novel method SoftCPT (Soft Context Sharing for Prompt Tuning) to tune pre-trained vision-language models on multiple target few-shot tasks jointly.
Expanding Language-Image Pretrained Models for General Video Recognition
Extensive experiments demonstrate that our approach is effective and can be generalized to different video recognition scenarios.
Ranked #8 on
Zero-Shot Action Recognition
on Kinetics
Pro-tuning: Unified Prompt Tuning for Vision Tasks
To this end, we propose parameter-efficient Prompt tuning (Pro-tuning) to adapt frozen vision models to various downstream vision tasks.
Domain Decorrelation with Potential Energy Ranking
PoER helps the neural networks to capture label-related features which contain the domain information first in shallow layers and then distills the label-discriminative representations out progressively, enforcing the neural networks to be aware of the characteristic of objects and background which is vital to the generation of domain-invariant features.
AME: Attention and Memory Enhancement in Hyper-Parameter Optimization
Training Deep Neural Networks (DNNs) is inherently subject to sensitive hyper-parameters and untimely feedbacks of performance evaluation.
Adversarial Gradient Driven Exploration for Deep Click-Through Rate Prediction
We further show that such a process is equivalent to adding an adversarial perturbation to the model input, and thereby name our proposed approach as an the Adversarial Gradient Driven Exploration (AGE).
Alleviating Mode Collapse in GAN via Diversity Penalty Module
We compare the proposed method with Unrolled GAN (Metz et al. 2016), BourGAN (Xiao, Zhong, and Zheng 2018), PacGAN (Lin et al. 2018), VEEGAN (Srivastava et al. 2017) and ALI (Dumoulin et al. 2016) on 2D synthetic dataset, and results show that the diversity penalty module can help GAN capture much more modes of the data distribution.
HAN: An Efficient Hierarchical Self-Attention Network for Skeleton-Based Gesture Recognition
Previous methods for skeleton-based gesture recognition mostly arrange the skeleton sequence into a pseudo picture or spatial-temporal graph and apply deep Convolutional Neural Network (CNN) or Graph Convolutional Network (GCN) for feature extraction.
BoundarySqueeze: Image Segmentation as Boundary Squeezing
This module is used to squeeze the object boundary from both inner and outer directions, which contributes to precise mask representation.
Knowledge Mining and Transferring for Domain Adaptive Object Detection
Specifically, KTNet is constructed on a base detector with intrinsic knowledge mining and relational knowledge constraints.
CAN: Feature Co-Action for Click-Through Rate Prediction
For example, a simple attempt to learn the combination of feature A and feature B <A, B> as the explicit cartesian product representation of new features can outperform previous implicit feature interaction models including factorization machine (FM)-based models and their variations.
Spatio-Temporal Graph Structure Learning for Traffic Forecasting
To address these issues, we propose a novel framework named Structure Learning Convolution (SLC) that enables to extend the traditional convolutional neural network (CNN) to graph domains and learn the graph structure for traffic forecasting.
Ranked #3 on
Traffic Prediction
on METR-LA
AugFPN: Improving Multi-scale Feature Learning for Object Detection
In this paper, we begin by first analyzing the design defects of feature pyramid in FPN, and then introduce a new feature pyramid architecture named AugFPN to address these problems.
DATA: Differentiable ArchiTecture Approximation
Neural architecture search (NAS) is inherently subject to the gap of architectures during searching and validating.
Learning Where to Focus for Efficient Video Object Detection
Transferring existing image-based detectors to the video is non-trivial since the quality of frames is always deteriorated by part occlusion, rare pose, and motion blur.
Ranked #22 on
Video Object Detection
on ImageNet VID
FontGAN: A Unified Generative Framework for Chinese Character Stylization and De-stylization
In our model, we decouple character images into style representation and content representation, which facilitates more precise control of these two types of variables, thereby improving the quality of the generated results.
DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing
Point cloud processing is very challenging, as the diverse shapes formed by irregular points are often indistinguishable.
Ranked #22 on
3D Part Segmentation
on ShapeNet-Part
Differentiable Architecture Search with Ensemble Gumbel-Softmax
For network architecture search (NAS), it is crucial but challenging to simultaneously guarantee both effectiveness and efficiency.
Deep Discriminative Clustering Analysis
Traditional clustering methods often perform clustering with low-level indiscriminative representations and ignore relationships between patterns, resulting in slight achievements in the era of deep learning.
LFFD: A Light and Fast Face Detector for Edge Devices
Under the new schema, the proposed method can achieve superior accuracy (WIDER FACE Val/Test -- Easy: 0. 910/0. 896, Medium: 0. 881/0. 865, Hard: 0. 780/0. 770; FDDB -- discontinuous: 0. 973, continuous: 0. 724).
Ranked #6 on
Face Detection
on FDDB
Relation-Shape Convolutional Neural Network for Point Cloud Analysis
Specifically, the convolutional weight for local point set is forced to learn a high-level relation expression from predefined geometric priors, between a sampled point from this point set and the others.
Ranked #10 on
3D Point Cloud Classification
on ModelNet40-C
Progressive Sparse Local Attention for Video object detection
Instead of relying on optical flow, this paper proposes a novel module called Progressive Sparse Local Attention (PSLA), which establishes the spatial correspondence between features across frames in a local region with progressively sparser stride and uses the correspondence to propagate features.
Structure-Aware Convolutional Neural Networks
Convolutional neural networks (CNNs) are inherently subject to invariable filters that can only aggregate local inputs with the same topological structures.
Joint Neural Architecture Search and Quantization
Here our goal is to automatically find a compact neural network model with high performance that is suitable for mobile devices.
Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection
Specifically, given the image-level annotations, (1) we first develop a weakly-supervised detection (WSD) model, and then (2) construct an end-to-end multi-label image classification framework augmented by a knowledge distillation module that guides the classification model by the WSD model according to the class-level predictions for the whole image and the object-level visual features for object RoIs.
Ranked #9 on
Multi-Label Classification
on NUS-WIDE
Exploiting Vector Fields for Geometric Rectification of Distorted Document Images
This paper proposes a segment-free method for geometric rectification of a distorted document image captured by a hand-held camera.
Reinforced Evolutionary Neural Architecture Search
To address this issue, we propose the Reinforced Evolutionary Neural Architecture Search (RE- NAS), which is an evolutionary method with the reinforced mutation for NAS.
Semantic Labeling in Very High Resolution Images via a Self-Cascaded Convolutional Neural Network
Specifically, for confusing manmade objects, ScasNet improves the labeling coherence with sequential global-to-local contexts aggregation.
A Performance Evaluation of Local Features for Image Based 3D Reconstruction
To obtain a comprehensive evaluation, we choose to include both float type features and binary ones.
Deep Adaptive Image Clustering
The main challenge is that the ground-truth similarities are unknown in image clustering.
Ranked #8 on
Image Clustering
on Tiny-ImageNet
AMVH: Asymmetric Multi-Valued Hashing
(2) A multi-integer-embedding is employed for compressing the whole database, which is modeled by binary sparse representation with fixed sparsity.
Do We Need Binary Features for 3D Reconstruction?
Binary features have been incrementally popular in the past few years due to their low memory footprints and the efficient computation of Hamming distance between binary descriptors.
Extraction of Virtual Baselines From Distorted Document Images Using Curvilinear Projection
In this paper, we propose an efficient method for accurate extraction of these virtual visual cues from a curved document image.
Segment Graph Based Image Filtering: Fast Structure-Preserving Smoothing
In our SGF, we use the tree distance on the segment graph to define the internal weight function of the filtering kernel, which enables the filter to smooth out high-contrast details and textures while preserving major image structures very well.
Accurate Urban Road Centerline Extraction from VHR Imagery via Multiscale Segmentation and Tensor Voting
Finally, to overcome the ineffectiveness of current methods in the road intersection, a fitting based road centerline connection algorithm is proposed.
Cross-Modal Similarity Learning : A Low Rank Bilinear Formulation
A new approach to the problem has been raised which intends to match features of different modalities directly.
10,000+ Times Accelerated Robust Subset Selection (ARSS)
Subset selection from massive data with noised information is increasingly popular for various applications.
Active Flattening of Curved Document Images via Two Structured Beams
Document images captured by a digital camera often suffer from serious geometric distortions.
Structured Sparse Method for Hyperspectral Unmixing
With this constraint, our method can learn a compact space, where highly similar pixels are grouped to share correlated sparse representations.
Spectral Unmixing via Data-guided Sparsity
Hyperspectral unmixing, the process of estimating a common set of spectral bases and their corresponding composite percentages at each pixel, is an important task for hyperspectral analysis, visualization and understanding.
Robust Hyperspectral Unmixing with Correntropy based Metric
In addition, with sparsity constraints, our model can naturally generate sparse abundances.
