Search Results for author:
Found 38 papers, 18 papers with code
VLM-KD: Knowledge Distillation from VLM for Long-Tail Visual Recognition
To our knowledge, this work is the first to utilize knowledge distillation with text supervision generated by an off-the-shelf VLM and apply it to vanilla randomly initialized vision encoders.
SpikingSSMs: Learning Long Sequences with Sparse and Parallel Spiking State Space Models
Known as low energy consumption networks, spiking neural networks (SNNs) have gained a lot of attention within the past decades.
Design Principle Transfer in Neural Architecture Search via Large Language Models
In LAPT, LLM is applied to automatically reason the design principles from a set of given architectures, and then a principle adaptation method is applied to refine these principles progressively based on the new search results.
Understanding the Importance of Evolutionary Search in Automated Heuristic Design with Large Language Models
Automated heuristic design (AHD) has gained considerable attention for its potential to automate the development of effective heuristics.
Rethinking Unsupervised Outlier Detection via Multiple Thresholding
In the realm of unsupervised image outlier detection, assigning outlier scores holds greater significance than its subsequent task: thresholding for predicting labels.
Evolutionary Spiking Neural Networks: A Survey
Spiking neural networks (SNNs) are gaining increasing attention as potential computationally efficient alternatives to traditional artificial neural networks(ANNs).
AnomalyXFusion: Multi-modal Anomaly Synthesis with Diffusion
The AnomalyXFusion framework comprises two distinct yet synergistic modules: the Multi-modal In-Fusion (MIF) module and the Dynamic Dif-Fusion (DDF) module.
ShadowMaskFormer: Mask Augmented Patch Embeddings for Shadow Removal
Transformer recently emerged as the de facto model for computer vision tasks and has also been successfully applied to shadow removal.
Ranked #3 on
Shadow Removal
on ISTD+
A Multi-objective Optimization Benchmark Test Suite for Real-time Semantic Segmentation
To bridge the gap, we introduce a tailored streamline to transform the task of HW-NAS for real-time semantic segmentation into standard MOPs.
Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model
EoH represents the ideas of heuristics in natural language, termed thoughts.
Seed Feature Maps-based CNN Models for LEO Satellite Remote Sensing Services
However, the limited resources available on LEO satellites contrast with the demands of resource-intensive CNN models, necessitating the adoption of ground-station server assistance for training and updating these models.
Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitives
Our key idea is to employ non-learnable primitives to extract a diverse set of task-agnostic features and recombine them into a shared branch common to all tasks and explicit task-specific branches reserved for each task.
TFormer: A Transmission-Friendly ViT Model for IoT Devices
The high performance and small number of model parameters and FLOPs of TFormer are attributed to the proposed hybrid layer and the proposed partially connected feed-forward network (PCS-FFN).
Revisiting Residual Networks for Adversarial Robustness
Then we design a robust residual block, dubbed RobustResBlock, and a compound scaling rule, dubbed RobustScaling, to distribute depth and width at the desired FLOP count.
Revisiting Residual Networks for Adversarial Robustness: An Architectural Perspective
In contrast, little attention was devoted to analyzing the role of architectural elements (such as topology, depth, and width) on adversarial robustness.
Surrogate-assisted Multi-objective Neural Architecture Search for Real-time Semantic Segmentation
The main challenges of applying NAS to semantic segmentation arise from two aspects: (i) high-resolution images to be processed; (ii) additional requirement of real-time inference speed (i. e., real-time semantic segmentation) for applications such as autonomous driving.
Neural Architecture Search as Multiobjective Optimization Benchmarks: Problem Formulation and Performance Assessment
From an optimization point of view, the NAS tasks involving multiple design criteria are intrinsically multiobjective optimization problems; hence, it is reasonable to adopt evolutionary multiobjective optimization (EMO) algorithms for tackling them.
VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMix
Existing vision-language pre-training (VLP) methods primarily rely on paired image-text datasets, which are either annotated by enormous human labors, or crawled from the internet followed by elaborate data cleaning techniques.
Semantic-Aware Pretraining for Dense Video Captioning
This report describes the details of our approach for the event dense-captioning task in ActivityNet Challenge 2021.
GAMMA Challenge:Glaucoma grAding from Multi-Modality imAges
However, although numerous algorithms are proposed based on fundus images or OCT volumes in computer-aided diagnosis, there are still few methods leveraging both of the modalities for the glaucoma assessment.
Multiview Transformers for Video Recognition
Video understanding requires reasoning at multiple spatiotemporal resolutions -- from short fine-grained motions to events taking place over longer durations.
Ranked #5 on
Action Recognition
on EPIC-KITCHENS-100
(using extra training data)
Accelerating Multi-Objective Neural Architecture Search by Random-Weight Evaluation
For the goal of automated design of high-performance deep convolutional neural networks (CNNs), Neural Architecture Search (NAS) methodology is becoming increasingly important for both academia and industries. Due to the costly stochastic gradient descent (SGD) training of CNNs for performance evaluation, most existing NAS methods are computationally expensive for real-world deployments.
End-to-End Dense Video Captioning with Parallel Decoding
Dense video captioning aims to generate multiple associated captions with their temporal locations from the video.
Ranked #5 on
Dense Video Captioning
on YouCook2
FaPN: Feature-aligned Pyramid Network for Dense Image Prediction
Recent advancements in deep neural networks have made remarkable leap-forwards in dense image prediction.
Ranked #22 on
Semantic Segmentation
on ADE20K val
The surprising impact of mask-head architecture on novel class segmentation
Under this family, we study Mask R-CNN and discover that instead of its default strategy of training the mask-head with a combination of proposals and groundtruth boxes, training the mask-head with only groundtruth boxes dramatically improves its performance on novel classes.
Learning from Weakly-labeled Web Videos via Exploring Sub-Concepts
To address this issue, we introduce a new method for pre-training video action recognition models using queried web videos.
Multi-objective Neural Architecture Search with Almost No Training
In the recent past, neural architecture search (NAS) has attracted increasing attention from both academia and industries.
PERF-Net: Pose Empowered RGB-Flow Net
In recent years, many works in the video action recognition literature have shown that two stream models (combining spatial and temporal input streams) are necessary for achieving state of the art performance.
Ranked #5 on
Action Recognition
on UCF101
Learning Video Representations from Textual Web Supervision
Based on this observation, we propose to use text as a method for learning video representations.
NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search
In this paper, we propose an efficient NAS algorithm for generating task-specific models that are competitive under multiple competing objectives.
Ranked #17 on
Neural Architecture Search
on ImageNet
Neural Architecture Transfer
At the same time, the architecture search and transfer is orders of magnitude more efficient than existing NAS methods.
Ranked #1 on
Neural Architecture Search
on STL-10
Fine-Grained Image Classification
Neural Architecture Search
+1
DOPS: Learning to Detect 3D Objects and Predict their 3D Shapes
In contrast, we propose a general-purpose method that works on both indoor and outdoor scenes.
MUXConv: Information Multiplexing in Convolutional Neural Networks
To overcome this limitation, we present MUXConv, a layer that is designed to increase the flow of information by progressively multiplexing channel and spatial information in the network, while mitigating computational complexity.
Ranked #4 on
Pneumonia Detection
on ChestX-ray14
RetinaTrack: Online Single Stage Joint Detection and Tracking
Traditionally multi-object tracking and object detection are performed using separate systems with most prior works focusing exclusively on one of these aspects over the other.
Ranked #1 on
Multiple Object Tracking
on Waymo Open Dataset
Multi-Objective Evolutionary Design of Deep Convolutional Neural Networks for Image Classification
While existing approaches have achieved competitive performance in image classification, they are not well suited to problems where the computational budget is limited for two reasons: (1) the obtained architectures are either solely optimized for classification performance, or only for one deployment scenario; (2) the search process requires vast computational resources in most approaches.
Ranked #1 on
Pneumonia Detection
on ChestX-ray14
NSGA-Net: Neural Architecture Search using Multi-Objective Genetic Algorithm
This paper introduces NSGA-Net -- an evolutionary approach for neural architecture search (NAS).
NSGA-Net: A Multi-Objective Genetic Algorithm for Neural Architecture Search
This paper introduces NSGA-Net, an evolutionary approach for neural architecture search (NAS).
Similarity-Aware Patchwork Assembly for Depth Image Super-Resolution
This paper describes a patchwork assembly algorithm for depth image super-resolution.
