Search Results for author:
Found 33 papers, 17 papers with code
Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE
This technical report briefly describes our JDExplore d-team's Vega v2 submission on the SuperGLUE leaderboard.
Knowledge-Aware Federated Active Learning with Non-IID Data
In this paper, we propose a federated active learning paradigm to efficiently learn a global model with limited annotation budget while protecting data privacy in a decentralized learning way.
Responsible Active Learning via Human-in-the-loop Peer Study
To further enhance the active learner via large-scale unlabelled data, we introduce multiple peer students into the active learner which is trained by a novel learning paradigm, including the In-Class Peer Study on labelled data and the Out-of-Class Peer Study on unlabelled data.
Domain-Specific Risk Minimization for Out-of-Distribution Generalization
Our bound motivates two strategies to reduce the gap: the first one is ensembling multiple classifiers to enrich the hypothesis space, then we propose effective gap estimation methods for guiding the selection of a better hypothesis for the target.
Improving Fine-Grained Visual Recognition in Low Data Regimes via Self-Boosting Attention Mechanism
In low data regimes, a network often struggles to choose the correct regions for recognition and tends to overfit spurious correlated patterns from the training data.
MeshMAE: Masked Autoencoders for 3D Mesh Data Analysis
We first randomly mask some patches of the mesh and feed the corrupted mesh into Mesh Transformers.
Deep Dictionary Learning with An Intra-class Constraint
Specifically, we design the intra-class compactness constraint on the intermediate representation at different levels to encourage the intra-class representations to be closer to each other, and eventually the learned representation becomes more discriminative.~Unlike the traditional DDL methods, during the classification stage, our DDLIC performs a layer-wise greedy optimization in a similar way to the training stage.
GFNet: Geometric Flow Network for 3D Point Cloud Semantic Segmentation
However, recent projection-based methods for point cloud semantic segmentation usually utilize a vanilla late fusion strategy for the predictions of different views, failing to explore the complementary information from a geometric perspective during the representation learning.
Ranked #6 on
3D Semantic Segmentation
on SemanticKITTI
BatchFormerV2: Exploring Sample Relationships for Dense Representation Learning
Specifically, when applying the proposed module, it employs a two-stream pipeline during training, i. e., either with or without a BatchFormerV2 module, where the batchformer stream can be removed for testing.
Discovering Human-Object Interaction Concepts via Self-Compositional Learning
Therefore, the proposed method enables the learning on both known and unknown HOI concepts.
Affordance Recognition
Human-Object Interaction Concept Discovery
Exploring High-Order Structure for Robust Graph Structure Learning
In this paper, we analyze the adversarial attack on graphs from the perspective of feature smoothness which further contributes to an efficient new adversarial defensive algorithm for GNNs.
Contrastive Boundary Learning for Point Cloud Segmentation
Point cloud segmentation is fundamental in understanding 3D environments.
Ranked #4 on
Semantic Segmentation
on S3DIS Area5
Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers
Motivated by the inherent consistency between the self-attention in Transformers and the semantic affinity, we propose an Affinity from Attention (AFA) module to learn semantic affinity from the multi-head self-attention (MHSA) in Transformers.
Ranked #13 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning
We perform extensive experiments on over ten datasets and the proposed method achieves significant improvements on different data scarcity applications without any bells and whistles, including the tasks of long-tailed recognition, compositional zero-shot learning, domain generalization, and contrastive learning.
Ranked #10 on
Domain Generalization
on PACS
Hyper-relationship Learning Network for Scene Graph Generation
As a result, HLN significantly improves the performance of scene graph generation by integrating and reasoning from object interactions, relationship interactions, and transitive inference of hyper-relationships.
Resistance Training using Prior Bias: toward Unbiased Scene Graph Generation
To address this problem, we propose Resistance Training using Prior Bias (RTPB) for the scene graph generation.
SkipNode: On Alleviating Performance Degradation for Deep Graph Convolutional Networks
In this paper, we conduct theoretical and experimental analysis to explore the fundamental causes of performance degradation in deep GCNs: over-smoothing and gradient vanishing have a mutually reinforcing effect that causes the performance to deteriorate more quickly in deep GCNs.
Contrastive Graph Poisson Networks: Semi-Supervised Learning with Extremely Limited Labels
Essentially, our CGPN can enhance the learning performance of GNNs under extremely limited labels by contrastively propagating the limited labels to the entire graph.
On Exploring Node-feature and Graph-structure Diversities for Node Drop Graph Pooling
Graph pooling is essential in learning effective graph-level representations.
SynFace: Face Recognition with Synthetic Data
We then analyze the underlying causes behind the performance gap, e. g., the poor intra-class variations and the domain gap between synthetic and real face images.
TGRNet: A Table Graph Reconstruction Network for Table Structure Recognition
A table arranging data in rows and columns is a very effective data structure, which has been widely used in business and scientific research.
Learning Progressive Point Embeddings for 3D Point Cloud Generation
The proposed dual-generators framework thus is able to progressively learn effective point embeddings for accurate point cloud generation.
Affordance Transfer Learning for Human-Object Interaction Detection
The proposed method can thus be used to 1) improve the performance of HOI detection, especially for the HOIs with unseen objects; and 2) infer the affordances of novel objects.
Ranked #2 on
Affordance Recognition
on HICO-DET(Unknown Concepts)
Detecting Human-Object Interaction via Fabricated Compositional Learning
With the proposed object fabricator, we are able to generate large-scale HOI samples for rare and unseen categories to alleviate the open long-tailed issues in HOI detection.
Ranked #4 on
Affordance Recognition
on HICO-DET
Collaborative Teacher-Student Learning via Multiple Knowledge Transfer
However, most of the existing knowledge distillation methods consider only one type of knowledge learned from either instance features or instance relations via a specific distillation strategy in teacher-student learning.
Not All Operations Contribute Equally: Hierarchical Operation-Adaptive Predictor for Neural Architecture Search
Despite their efficiency, current graph-based predictors treat all operations equally, resulting in biased topological knowledge of cell architectures.
Heatmap Regression via Randomized Rounding
Previous methods to overcome the sub-pixel localization problem usually rely on high-resolution heatmaps.
Knowledge Distillation: A Survey
To this end, a variety of model compression and acceleration techniques have been developed.
Unsupervised Domain Adaptation on Reading Comprehension
On the other hand, it further reduces domain distribution discrepancy through conditional adversarial learning across domains.
Building Effective Large-Scale Traffic State Prediction System: Traffic4cast Challenge Solution
How to build an effective large-scale traffic state prediction system is a challenging but highly valuable problem.
Deep Metric Learning With Tuplet Margin Loss
Deep metric learning, in which the loss function plays a key role, has proven to be extremely useful in visual recognition tasks.
Correcting the Triplet Selection Bias for Triplet Loss
Considering that the number of triplets grows cubically with the size of training data, triplet mining is thus indispensable for efficiently training with triplet loss.
Anchor Cascade for Efficient Face Detection
Face detection is essential to facial analysis tasks such as facial reenactment and face recognition.
