Search Results for author:
Found 28 papers, 12 papers with code
Computational and Statistical Tradeoffs in Inferring Combinatorial Structures of Ising Model
We study the computational and statistical tradeoffs in inferring combinatorial structures of high dimensional simple zero-field ferromagnetic Ising model.
Confidence on the Focal: Conformal Prediction with Selection-Conditional Coverage
In such cases, marginally valid conformal prediction intervals may not provide valid coverage for the focal unit(s) due to selection bias.
SepRep-Net: Multi-source Free Domain Adaptation via Model Separation And Reparameterization
We consider multi-source free domain adaptation, the problem of adapting multiple existing models to a new domain without accessing the source data.
SeeDS: Semantic Separable Diffusion Synthesizer for Zero-shot Food Detection
To tackle this, we propose the Semantic Separable Diffusion Synthesizer (SeeDS) framework for Zero-Shot Food Detection (ZSFD).
Ranked #1 on
Generalized Zero-Shot Object Detection
on MS-COCO
Uncertainty Quantification over Graph with Conformalized Graph Neural Networks
We establish a permutation invariance condition that enables the validity of CP on graph data and provide an exact characterization of the test-time coverage.
Topological properties and organizing principles of semantic networks
We find that depending on the semantic relation type and the language, the link formation in semantic networks is guided by different principles.
UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers
Real-world data contains a vast amount of multimodal information, among which vision and language are the two most representative modalities.
Semi-Supervised Semantic Segmentation via Gentle Teaching Assistant
Semi-Supervised Semantic Segmentation aims at training the segmentation model with limited labeled data and a large amount of unlabeled data.
Multi-Level Logit Distillation
Through this framework, the prediction alignment is not only conducted at the instance level, but also at the batch and class level, through which the student model learns instance prediction, input correlation, and category correlation simultaneously.
Policy learning "without'' overlap: Pessimism and generalized empirical Bernstein's inequality
Existing policy learning methods rely on a uniform overlap assumption, i. e., the propensities of exploring all actions for all individual characteristics are lower bounded in the offline dataset.
Image-Text Retrieval with Binary and Continuous Label Supervision
Such a binary indicator covers only a limited subset of image-text semantic relations, which is insufficient to represent relevance degrees between images and texts described by continuous labels such as image captions.
Selection by Prediction with Conformal p-values
Decision making or scientific discovery pipelines such as job hiring and drug discovery often involve multiple stages: before any resource-intensive step, there is often an initial screening that uses predictions from a machine learning model to shortlist a few candidates from a large pool.
Upper bounds on the Natarajan dimensions of some function classes
The Natarajan dimension is a fundamental tool for characterizing multi-class PAC learnability, generalizing the Vapnik-Chervonenkis (VC) dimension from binary to multi-class classification problems.
The Overlooked Classifier in Human-Object Interaction Recognition
Human-Object Interaction (HOI) recognition is challenging due to two factors: (1) significant imbalance across classes and (2) requiring multiple labels per image.
The Overlooked Classifier in Human-Object Interaction Recognition
Human-Object Interaction (HOI) recognition is challenging due to two factors: (1) significant imbalance across classes and (2) requiring multiple labels per image.
Ranked #1 on
Human-Object Interaction Detection
on HICO
Improving Vision Transformers for Incremental Learning
This paper proposes a working recipe of using Vision Transformer (ViT) in class incremental learning.
Few-Shot Object Detection via Association and DIscrimination
1) In the association step, in contrast to implicitly leveraging multiple base classes, we construct a compact novel class feature space via explicitly imitating a specific base class feature space.
Single-DARTS: Towards Stable Architecture Search
Differentiable architecture search (DARTS) marks a milestone in Neural Architecture Search (NAS), boasting simplicity and small search costs.
Contemporary Symbolic Regression Methods and their Relative Performance
We assess 14 symbolic regression methods and 7 machine learning methods on a set of 252 diverse regression problems.
Is Object Detection Necessary for Human-Object Interaction Recognition?
This paper revisits human-object interaction (HOI) recognition at image level without using supervisions of object location and human pose.
Is Pessimism Provably Efficient for Offline RL?
We study offline reinforcement learning (RL), which aims to learn an optimal policy based on a dataset collected a priori.
Single-level Optimization For Differential Architecture Search
The bias causes the architecture parameters of non-learnable operations to surpass that of learnable operations.
Incorporating planning intelligence into deep learning: A planning support tool for street network design
Deep learning applications in shaping ad hoc planning proposals are limited by the difficulty in integrating professional knowledge about cities with artificial intelligence.
DeepStreet: A deep learning powered urban street network generation module
Specifically, the CNN is firstly trained to detect, recognize and capture the local features as well as the patterns of the existing street network sourced from the OpenStreetMap.
Learning Nonparametric Human Mesh Reconstruction from a Single Image without Ground Truth Meshes
Experimental results on multiple public datasets show that without using 3D ground truth meshes, the proposed approach outperforms the previous state-of-the-art approaches that require ground truth meshes for training.
Minimum Class Confusion for Versatile Domain Adaptation
It can be characterized as (1) a non-adversarial DA method without explicitly deploying domain alignment, enjoying faster convergence speed; (2) a versatile approach that can handle four existing scenarios: Closed-Set, Partial-Set, Multi-Source, and Multi-Target DA, outperforming the state-of-the-art methods in these scenarios, especially on one of the largest and hardest datasets to date (7. 3% on DomainNet).
Ranked #3 on
Multi-target Domain Adaptation
on DomainNet
Transferable Normalization: Towards Improving Transferability of Deep Neural Networks
Deep neural networks (DNNs) excel at learning representations when trained on large-scale datasets.
3D RoI-aware U-Net for Accurate and Efficient Colorectal Tumor Segmentation
With the region proposals from the encoder, we crop multi-level RoI in-region features from the encoder to form a GPU memory-efficient decoder for detailpreserving segmentation and therefore enlarged applicable volume size and effective receptive field.
