Search Results for author:
Found 64 papers, 34 papers with code
Efficient Pruning of Large Language Model with Adaptive Estimation Fusion
Large language models (LLMs) have become crucial for many generative downstream tasks, leading to an inevitable trend and significant challenge to deploy them efficiently on resource-constrained devices.
EffiBench: Benchmarking the Efficiency of Automatically Generated Code
This paper presents EffiBench, a benchmark with 1, 000 efficiency-critical coding problems for assessing the efficiency of code generated by code generation models.
Deep Clustering with Diffused Sampling and Hardness-aware Self-distillation
Deep clustering has gained significant attention due to its capability in learning clustering-friendly representations without labeled data.
Learning Representations for Clustering via Partial Information Discrimination and Cross-Level Interaction
In this paper, we present a novel deep image clustering approach termed PICI, which enforces the partial information discrimination and the cross-level interaction in a joint learning framework.
Towards Efficient and Effective Deep Clustering with Dynamic Grouping and Prototype Aggregation
To tackle these critical issues, we present a novel end-to-end deep clustering framework with dynamic grouping and prototype aggregation, termed as DigPro.
AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation
The advancement of natural language processing (NLP) has been significantly boosted by the development of transformer-based large language models (LLMs).
Ranked #1 on
Code Generation
on HumanEval
MAC: ModAlity Calibration for Object Detection
The flourishing success of Deep Neural Networks(DNNs) on RGB-input perception tasks has opened unbounded possibilities for non-RGB-input perception tasks, such as object detection from wireless signals, lidar scans, and infrared images.
Bias Testing and Mitigation in LLM-based Code Generation
To mitigate bias for code generation models, we evaluate five bias mitigation prompt strategies, i. e., utilizing bias testing results to refine the code (zero-shot), one-, few-shot, and two Chain-of-Thought (CoT) prompts.
Coordinate Transformer: Achieving Single-stage Multi-person Mesh Recovery from Videos
Multi-person 3D mesh recovery from videos is a critical first step towards automatic perception of group behavior in virtual reality, physical therapy and beyond.
CodeCoT: Tackling Code Syntax Errors in CoT Reasoning for Code Generation
However, its application in code generation faces a distinct challenge, i. e., although the code generated with CoT reasoning is logically correct, it faces the problem of syntax error (e. g., invalid syntax error report) during code execution, which causes the CoT result's pass@1 in HumanEval even lower than the zero-shot result.
Feature Map Testing for Deep Neural Networks
Current test metrics, however, are primarily concerned with the neurons, which means that test cases that are discovered either by guided fuzzing or selection with these metrics focus on detecting fault-inducing neurons while failing to detect fault-inducing feature maps.
Adversarial Feature Map Pruning for Backdoor
Unlike existing defense strategies, which focus on reproducing backdoor triggers, FMP attempts to prune backdoor feature maps, which are trained to extract backdoor information from inputs.
Neuron Sensitivity Guided Test Case Selection for Deep Learning Testing
To address the above-mentioned problem, we propose NSS, Neuron Sensitivity guided test case Selection, which can reduce the labeling time by selecting valuable test cases from unlabeled datasets.
Towards Building More Robust Models with Frequency Bias
The vulnerability of deep neural networks to adversarial samples has been a major impediment to their broad applications, despite their success in various fields.
Temporal Aware Mixed Attention-based Convolution and Transformer Network (MACTN) for EEG Emotion Recognition
In this study, we propose MACTN, a hierarchical hybrid model for jointly modeling local and global temporal information.
One-step Bipartite Graph Cut: A Normalized Formulation and Its Application to Scalable Subspace Clustering
The bipartite graph structure has shown its promising ability in facilitating the subspace clustering and spectral clustering algorithms for large-scale datasets.
Zero-shot Model Diagnosis
Extensive experiments demonstrate that our method is capable of producing counterfactual images and offering sensitivity analysis for model diagnosis without the need for a test set.
Semantic Image Attack for Visual Model Diagnosis
Rather than relying on a carefully designed test set to assess ML models' failures, fairness, or robustness, this paper proposes Semantic Image Attack (SIA), a method based on the adversarial attack that provides semantic adversarial images to allow model diagnosis, interpretability, and robustness.
Heterogeneous Tri-stream Clustering Network
Contrastive deep clustering has recently gained significant attention with its ability of joint contrastive learning and clustering via deep neural networks.
DensePose From WiFi
Advances in computer vision and machine learning techniques have led to significant development in 2D and 3D human pose estimation from RGB cameras, LiDAR, and radars.
Deep Temporal Contrastive Clustering
Recently the deep learning has shown its advantage in representation learning and clustering for time series data.
Efficient Multi-view Clustering via Unified and Discrete Bipartite Graph Learning
By simultaneously formulating the view-specific bipartite graph learning, the view-consensus bipartite graph learning, and the discrete cluster structure learning into a unified objective function, an efficient minimization algorithm is then designed to tackle this optimization problem and directly achieve a discrete clustering solution without requiring additional partitioning, which notably has linear time complexity in data size.
Adaptively-weighted Integral Space for Fast Multiview Clustering
In view of this, we propose an Adaptively-weighted Integral Space for Fast Multiview Clustering (AIMC) with nearly linear complexity.
Two Heads are Better than One: Robust Learning Meets Multi-branch Models
Compared to all methods that do not use additional data for training, our models achieve 67. 3% and 41. 5% robust accuracy on CIFAR-10 and CIFAR-100 (improving upon the state-of-the-art by +7. 23% and +9. 07%).
Deep Image Clustering with Contrastive Learning and Multi-scale Graph Convolutional Networks
Deep clustering has shown its promising capability in joint representation learning and clustering via deep neural networks.
Vision Transformer for Contrastive Clustering
Vision Transformer (ViT) has shown its advantages over the convolutional neural network (CNN) with its ability to capture global long-range dependencies for visual representation learning.
Strongly Augmented Contrastive Clustering
In this paper, we present an end-to-end deep clustering approach termed Strongly Augmented Contrastive Clustering (SACC), which extends the conventional two-augmentation-view paradigm to multiple views and jointly leverages strong and weak augmentations for strengthened deep clustering.
DeepCluE: Enhanced Image Clustering via Multi-layer Ensembles in Deep Neural Networks
In view of this, this paper presents a Deep Clustering via Ensembles (DeepCluE) approach, which bridges the gap between deep clustering and ensemble clustering by harnessing the power of multiple layers in deep neural networks.
Joint Multi-view Unsupervised Feature Selection and Graph Learning
Second, they often learn the similarity structure by either global structure learning or local structure learning, which lack the capability of graph learning with both global and local structural awareness.
The Two Dimensions of Worst-case Training and the Integrated Effect for Out-of-domain Generalization
Training with an emphasis on "hard-to-learn" components of the data has been proven as an effective method to improve the generalization of machine learning models, especially in the settings where robustness (e. g., generalization across distributions) is valued.
Fast Multi-view Clustering via Ensembles: Towards Scalability, Superiority, and Simplicity
Then, a set of diversified base clusterings for different view groups are obtained via fast graph partitioning, which are further formulated into a unified bipartite graph for final clustering in the late-stage fusion.
Seeking Commonness and Inconsistencies: A Jointly Smoothed Approach to Multi-view Subspace Clustering
Second, many of them overlook the local structures of multiple views and cannot jointly leverage multiple local structures to enhance the subspace representation learning.
The Two Dimensions of Worst-Case Training and Their Integrated Effect for Out-of-Domain Generalization
Training with an emphasis on "hard-to-learn" components of the data has been proven as an effective method to improve the generalization of machine learning models, especially in the settings where robustness (e. g., generalization across distributions) is valued.
You Can Wash Better: Daily Handwashing Assessment with Smartwatches
We propose UWash, an intelligent solution upon smartwatches, to assess handwashing for the purpose of raising users' awareness and cultivating habits in high-quality handwashing.
Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation
The nonuniform quantization strategy for compressing neural networks usually achieves better performance than its counterpart, i. e., uniform strategy, due to its superior representational capacity.
Elaborative Rehearsal for Zero-shot Action Recognition
However, due to the complexity and diversity of actions, it remains challenging to semantically represent action classes and transfer knowledge from seen data.
Ranked #3 on
Zero-Shot Action Recognition
on Olympics
Polarized Self-Attention: Towards High-quality Pixel-wise Regression
Pixel-wise regression is probably the most common problem in fine-grained computer vision tasks, such as estimating keypoint heatmaps and segmentation masks.
Ranked #2 on
Keypoint Detection
on MS COCO
(Validation AP metric)
How Do Adam and Training Strategies Help BNNs Optimization?
We show the regularization effect of second-order momentum in Adam is crucial to revitalize the weights that are dead due to the activation saturation in BNNs.
Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection
Moreover, the image-level category labels do not enforce consistent object detection across different transformations of the same images.
Ranked #1 on
Weakly Supervised Object Detection
on MSCOCO
Large Norms of CNN Layers Do Not Hurt Adversarial Robustness
Since the Lipschitz properties of convolutional neural networks (CNNs) are widely considered to be related to adversarial robustness, we theoretically characterize the $\ell_1$ norm and $\ell_\infty$ norm of 2D multi-channel convolutional layers and provide efficient methods to compute the exact $\ell_1$ norm and $\ell_\infty$ norm.
Multi-view Graph Learning by Joint Modeling of Consistency and Inconsistency
To overcome this limitation, we propose a new multi-view graph learning framework, which for the first time simultaneously and explicitly models multi-view consistency and multi-view inconsistency in a unified objective function, through which the consistent and inconsistent parts of each single-view graph as well as the unified graph that fuses the consistent parts can be iteratively learned.
Self-Challenging Improves Cross-Domain Generalization
We introduce a simple training heuristic, Representation Self-Challenging (RSC), that significantly improves the generalization of CNN to the out-of-domain data.
Ranked #27 on
Domain Generalization
on PACS
Multiple Object Tracking by Flowing and Fusing
Most of Multiple Object Tracking (MOT) approaches compute individual target features for two subtasks: estimating target-wise motions and conducting pair-wise Re-Identification (Re-ID).
Multiple Anchor Learning for Visual Object Detection
In this paper, we propose a Multiple Instance Learning (MIL) approach that selects anchors and jointly optimizes the two modules of a CNN-based object detector.
Ranked #105 on
Object Detection
on COCO test-dev
Frame-wise Motion and Appearance for Real-time Multiple Object Tracking
The main challenge of Multiple Object Tracking (MOT) is the efficiency in associating indefinite number of objects between video frames.
Cutting Down Training Memory by Re-fowarding
Our approach automatically finds a subset of vertices in a DNN computation graph, and stores tensors only at these vertices during the first forward.
Temporal Unet: Sample Level Human Action Recognition using WiFi
In this task, every WiFi distortion sample in the whole series should be categorized into one action, which is a critical technique in precise action localization, continuous action segmentation, and real-time action recognition.
Can WiFi Estimate Person Pose?
In this paper We try to answer this question by exploring the ability of WiFi on estimating single person pose.
Person-in-WiFi: Fine-grained Person Perception using WiFi
Fine-grained person perception such as body segmentation and pose estimation has been achieved with many 2D and 3D sensors such as RGB/depth cameras, radars (e. g., RF-Pose) and LiDARs.
SE2Net: Siamese Edge-Enhancement Network for Salient Object Detection
In this paper, we propose a simple yet effective Siamese Edge-Enhancement Network (SE2Net) to preserve the edge structure for salient object detection.
Improving Object Detection with Inverted Attention
Our approach (1) operates along both the spatial and channels dimensions of the feature maps; (2) requires no extra training on hard samples, no extra network parameters for attention estimation, and no testing overheads.
Ultra-Scalable Spectral Clustering and Ensemble Clustering
Experiments on various large-scale datasets have demonstrated the scalability and robustness of our algorithms.
Ranked #3 on
Image/Document Clustering
on pendigits
Enhanced Ensemble Clustering via Fast Propagation of Cluster-wise Similarities
Upon the constructed graph, a transition probability matrix is defined, based on which the random walk process is conducted to propagate the graph structural information.
CSI-Net: Unified Human Body Characterization and Pose Recognition
We build CSI-Net, a unified Deep Neural Network~(DNN), to learn the representation of WiFi signals.
Optimal Gradient Checkpoint Search for Arbitrary Computation Graphs
In this paper, we present theories and optimal algorithms on GC selection that, for the first time, are applicable to ACGs and achieve the maximal memory cut-offs.
PoseFlow: A Deep Motion Representation for Understanding Human Behaviors in Videos
This "noisy" motion representation makes it very challenging for pose estimation and action recognition in real scenarios.
Toward Multidiversified Ensemble Clustering of High-Dimensional Data: From Subspaces to Metrics and Beyond
The rapid emergence of high-dimensional data in various areas has brought new challenges to current ensemble clustering research.
Soft-Margin Mixture of Regressions
However, existing divide-and-conquer approaches fail to deal with discontinuities between partitions (e. g., Gaussian mixture of regressions) and they cannot guarantee that the partitioned input space will be homogeneously modeled by local regressors (e. g., ordinal regression).
Learning Category-Specific 3D Shape Models From Weakly Labeled 2D Images
Recently, researchers have made great processes to build category-specific 3D shape models from 2D images with manual annotations consisting of class labels, keypoints, and ground truth figure-ground segmentations.
Ensemble-driven support vector clustering: From ensemble learning to automatic parameter estimation
Support vector clustering (SVC) is a versatile clustering technique that is able to identify clusters of arbitrary shapes by exploiting the kernel trick.
Robust Ensemble Clustering Using Probability Trajectories
To address these two limitations, in this paper, we propose a novel ensemble clustering approach based on sparse graph representation and probability trajectory analysis.
Locally Weighted Ensemble Clustering
Although some efforts have been made to (globally) evaluate and weight the base clusterings, yet these methods tend to view each base clustering as an individual and neglect the local diversity of clusters inside the same base clustering.
Complex Non-Rigid Motion 3D Reconstruction by Union of Subspaces
The task of estimating complex non-rigid 3D motion through a monocular camera is of increasing interest to the wider scientific community.
Combining Multiple Clusterings via Crowd Agreement Estimation and Multi-Granularity Link Analysis
We present the normalized crowd agreement index (NCAI) to evaluate the quality of base clusterings in an unsupervised manner and thus weight the base clusterings in accordance with their clustering validity.
