Search Results for author:
Found 26 papers, 18 papers with code
Underwater Acoustic Signal Recognition Based on Salient Feature
The proposed approach involves continual learning of features extracted from spectra for the classification of underwater acoustic signals.
TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training
As a result, we dissect the preservation of patch-wise spatial information in CLIP and proposed a local-to-global framework to obtain image tags.
SHAP-EDITOR: Instruction-guided Latent 3D Editing in Seconds
In particular, we hypothesise that editing can be greatly simplified by first encoding 3D objects in a suitable latent space.
A Study of Unsupervised Evaluation Metrics for Practical and Automatic Domain Adaptation
Unsupervised domain adaptation (UDA) methods facilitate the transfer of models to target domains without labels.
PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformer
The key to associating the two different representations is our introduced input-dependent Query Initialization module, which could efficiently generate reference points and content queries.
Training-Free Layout Control with Cross-Attention Guidance
We thoroughly evaluate our approach on three benchmarks and provide several qualitative examples and a comparative analysis of the two strategies that demonstrate the superiority of backward guidance compared to forward guidance, as well as prior work.
CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation
To efficiently generate high-quality segmentation masks from CLIP, we propose a novel WSSS framework called CLIP-ES.
Ranked #12 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
Self-supervised and Weakly Supervised Contrastive Learning for Frame-wise Action Representations
In this paper, we introduce a new framework of contrastive action representation learning (CARL) to learn frame-wise action representation in a self-supervised or weakly-supervised manner, especially for long videos.
Expanding Language-Image Pretrained Models for General Video Recognition
Extensive experiments demonstrate that our approach is effective and can be generalized to different video recognition scenarios.
Ranked #8 on
Zero-Shot Action Recognition
on Kinetics
Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning
In this paper, we introduce a novel contrastive action representation learning (CARL) framework to learn frame-wise action representations, especially for long videos, in a self-supervised manner.
Searching the Search Space of Vision Transformer
Vision Transformer has shown great visual representation power in substantial vision tasks such as recognition and detection, and thus been attracting fast-growing efforts on manually designing more effective architectures.
Rethinking and Improving Relative Position Encoding for Vision Transformer
We then propose new relative position encoding methods dedicated to 2D images, called image RPE (iRPE).
Ranked #140 on
Object Detection
on COCO minival
AutoFormer: Searching Transformers for Visual Recognition
Specifically, the performance of these subnets with weights inherited from the supernet is comparable to those retrained from scratch.
Ranked #1 on
Fine-Grained Image Classification
on Oxford 102 Flowers
(Top 1 Accuracy metric)
CRFL: Certifiably Robust Federated Learning against Backdoor Attacks
Our method exploits clipping and smoothing on model parameters to control the global model smoothness, which yields a sample-wise robustness certification on backdoors with limited magnitude.
Salient Object Ranking with Position-Preserved Attention
In this paper, we study the Salient Object Ranking (SOR) task, which manages to assign a ranking order of each detected object according to its visual saliency.
One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking
In this paper, we propose a one-shot neural ensemble architecture search (NEAS) solution that addresses the two challenges.
Suppress-and-Refine Framework for End-to-End 3D Object Detection
In this work, we propose a suppress-and-refine framework to remove these handcrafted components.
Complementary Pseudo Labels For Unsupervised Domain Adaptation On Person Re-identification
In this paper, to complement these low recall neighbor pseudo labels, we propose a joint learning framework to learn better feature embeddings via high precision neighbor pseudo labels and high recall group pseudo labels.
SHOT-VAE: Semi-supervised Deep Generative Models With Label-aware ELBO Approximations
Semi-supervised variational autoencoders (VAEs) have obtained strong results, but have also encountered the challenge that good ELBO values do not always imply accurate inference results.
KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation
(2) A dynamic weighting strategy named Consensus Focus to identify both the malicious and irrelevant domains.
Knowledge Distillation
Multi-Source Unsupervised Domain Adaptation
+2
Reducing the Teacher-Student Gap via Spherical Knowledge Disitllation
We investigate this problem by study the gap of confidence between teacher and student.
Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework
Specifically, it first casts the relationships between a certain model's accuracy and depth/width/resolution into a polynomial regression and then maximizes the polynomial to acquire the optimal values for the three dimensions.
Adversarial-Learned Loss for Domain Adaptation
In order to combine the strengths of these two methods, we propose a novel method called Adversarial-Learned Loss for Domain Adaptation (ALDA).
DBP: Discrimination Based Block-Level Pruning for Deep Model Acceleration
The dominant pruning methods, filter-level pruning methods, evaluate their performance through the reduction ratio of computations and deem that a higher reduction ratio of computations is equivalent to a higher acceleration ratio in terms of inference time.
Domain Adaptation for Semantic Segmentation with Maximum Squares Loss
However, when applying the entropy minimization to UDA for semantic segmentation, the gradient of the entropy is biased towards samples that are easy to transfer.
Learning color space adaptation from synthetic to real images of cirrus clouds
With our adapted synthetic data for training the semantic segmentation, we achieve an improvement of 6:59% when applied to real images, superior to alternative methods.
