Search Results for author:
Found 23 papers, 12 papers with code
TOOD: Task-aligned One-stage Object Detection
One-stage object detection is commonly implemented by optimizing two sub-tasks: object classification and localization, using heads with two parallel branches, which might lead to a certain level of spatial misalignment in predictions between the two tasks.
Ranked #3 on
2D Object Detection
on CeyMo
Mutually-aware Sub-Graphs Differentiable Architecture Search
In this paper, we propose a conceptually simple yet efficient method to bridge these two paradigms, referred as Mutually-aware Sub-Graphs Differentiable Architecture Search (MSG-DAS).
Brain Image Synthesis With Unsupervised Multivariate Canonical CSCl4Net
Recent advances in neuroscience have highlighted the effectiveness of multi-modal medical data for investigating certain pathologies and understanding human cognition.
Rethinking Deep Contrastive Learning with Embedding Memory
Pair-wise loss functions have been extensively studied and shown to continuously improve the performance of deep metric learning (DML).
Brain Image Synthesis with Unsupervised Multivariate Canonical CSC$\ell_4$Net
Recent advances in neuroscience have highlighted the effectiveness of multi-modal medical data for investigating certain pathologies and understanding human cognition.
Unchain the Search Space with Hierarchical Differentiable Architecture Search
To overcome this limitation, in this paper, we propose a Hierarchical Differentiable Architecture Search (H-DAS) that performs architecture search both at the cell level and at the stage level.
Representation Sharing for Fast Object Detector Search and Beyond
FAD consists of a designed search space and an efficient architecture search algorithm.
V4D: 4D Convolutional Neural Networks for Video-level Representation Learning
Most existing 3D CNN structures for video representation learning are clip-based methods, and do not consider video-level temporal evolution of spatio-temporal features.
Deformable Siamese Attention Networks for Visual Object Tracking
In this paper, we propose Deformable Siamese Attention Networks, referred to as SiamAttn, by introducing a new Siamese attention mechanism that computes deformable self-attention and cross-attention.
Channel Interaction Networks for Fine-Grained Image Categorization
Fine-grained image categorization is challenging due to the subtle inter-class differences. We posit that exploiting the rich relationships between channels can help capture such differences since different channels correspond to different semantics.
Ranked #23 on
Fine-Grained Image Classification
on FGVC Aircraft
iFAN: Image-Instance Full Alignment Networks for Adaptive Object Detection
We propose Image-Instance Full Alignment Networks (iFAN) to tackle this problem by precisely aligning feature distributions on both image and instance levels: 1) Image-level alignment: multi-scale features are roughly aligned by training adversarial domain classifiers in a hierarchically-nested fashion.
Knowledge Integration Networks for Action Recognition
We design a three-branch architecture consisting of a main branch for action recognition, and two auxiliary branches for human parsing and scene recognition which allow the model to encode the knowledge of human and scene for action recognition.
V4D:4D Convolutional Neural Networks for Video-level Representation Learning
Most existing 3D CNNs for video representation learning are clip-based methods, and thus do not consider video-level temporal evolution of spatio-temporal features.
Cross-Batch Memory for Embedding Learning
This suggests that the features of instances computed at preceding iterations can be used to considerably approximate their features extracted by the current model.
Ranked #2 on
Image Retrieval
on In-Shop
Convolutional Character Networks
We evaluate CharNet on three standard benchmarks, where it consistently outperforms the state-of-the-art approaches [25, 24] by a large margin, e. g., with improvements of 65. 33%->71. 08% (with generic lexicon) on ICDAR 2015, and 54. 0%->69. 23% on Total-Text, on end-to-end text recognition.
Ranked #2 on
Scene Text Detection
on ICDAR 2015
Label-PEnet: Sequential Label Propagation and Enhancement Networks for Weakly Supervised Instance Segmentation
Weakly-supervised instance segmentation aims to detect and segment object instances precisely, given imagelevel labels only.
Ranked #9 on
Image-level Supervised Instance Segmentation
on PASCAL VOC 2012 val
(using extra training data)
General Classification
Image-level Supervised Instance Segmentation
+6
Dual-Stream Pyramid Registration Network
We propose a Dual-Stream Pyramid Registration Network (referred as Dual-PRNet) for unsupervised 3D medical image registration.
The iMaterialist Fashion Attribute Dataset
The dataset is constructed from over one million fashion images with a label space that includes 8 groups of 228 fine-grained attributes in total.
Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning
A family of loss functions built on pair-based computation have been proposed in the literature which provide a myriad of solutions for deep metric learning.
Ranked #4 on
Image Retrieval
on In-Shop
Compatible and Diverse Fashion Image Inpainting
The latent representations are jointly optimized with the corresponding generation network to condition the synthesis process, encouraging a diverse set of generated results that are visually compatible with existing fashion garments.
Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge
This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i. e., 2012-2018.
Deep Metric Learning with Hierarchical Triplet Loss
(i) we construct a hierarchical class-level tree where neighboring classes are merged recursively.
Ranked #8 on
Image Retrieval
on CARS196
CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images
We present a simple yet efficient approach capable of training deep neural networks on large-scale weakly-supervised web images, which are crawled raw from the Internet by using text queries, without any human annotation.
Ranked #1 on
Image Classification
on Clothing1M (using clean data)
(using extra training data)
