Search Results for author:
Found 34 papers, 20 papers with code
The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report
In sub-track 1, the practical runtime performance of the submissions was evaluated, and the corresponding score was used to determine the ranking.
Fusion-Mamba for Cross-modality Object Detection
In this paper, we investigate cross-modality fusion by associating cross-modal features in a hidden state space based on an improved Mamba with a gating mechanism.
LIPT: Latency-aware Image Processing Transformer
Extensive experiments on multiple image processing tasks (e. g., image super-resolution (SR), JPEG artifact reduction, and image denoising) demonstrate the superiority of LIPT on both latency and PSNR.
Knowledge Distillation with Multi-granularity Mixture of Priors for Image Super-Resolution
Knowledge distillation (KD) is a promising yet challenging model compression technique that transfers rich learning representations from a well-performing but cumbersome teacher model to a compact student model.
A General and Efficient Training for Transformer via Token Expansion
The remarkable performance of Vision Transformers (ViTs) typically requires an extremely large training cost.
Rethinking Centered Kernel Alignment in Knowledge Distillation
Knowledge distillation has emerged as a highly effective method for bridging the representation discrepancy between large-scale models and lightweight models.
Class-Imbalanced Semi-Supervised Learning for Large-Scale Point Cloud Semantic Segmentation via Decoupling Optimization
Semi-supervised learning (SSL), thanks to the significant reduction of data annotation costs, has been an active research topic for large-scale 3D scene understanding.
A Challenger to GPT-4V? Early Explorations of Gemini in Visual Expertise
They endow Large Language Models (LLMs) with powerful capabilities in visual understanding, enabling them to tackle diverse multi-modal tasks.
Weakly Supervised Open-Vocabulary Object Detection
Despite weakly supervised object detection (WSOD) being a promising step toward evading strong instance-level annotations, its capability is confined to closed-set categories within a single training dataset.
SPD-DDPM: Denoising Diffusion Probabilistic Models in the Symmetric Positive Definite Space
On the other hand, the model unconditionally learns the probability distribution of the data $p(X)$ and generates samples that conform to this distribution.
Aligning and Prompting Everything All at Once for Universal Visual Perception
However, predominant paradigms, driven by casting instance-level tasks as an object-word alignment, bring heavy cross-modality interaction, which is not effective in prompting object detection and visual grounding.
Data Upcycling Knowledge Distillation for Image Super-Resolution
Knowledge distillation (KD) compresses deep neural networks by transferring task-related knowledge from cumbersome pre-trained teacher models to compact student models.
Ranked #22 on
Image Super-Resolution
on Urban100 - 4x upscaling
Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler
In this paper, we propose a novel Knowledge-driven Differential Filter Sampler~(KDFS) with Masked Filter Modeling~(MFM) framework for filter pruning, which globally prunes the redundant filters based on the prior knowledge of a pre-trained model in a differential and non-alternative optimization.
AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning
Text consists of a category name and a fixed number of learnable parameters which are selected from our designed attribute word bank and serve as attributes.
DCS-RISR: Dynamic Channel Splitting for Efficient Real-world Image Super-Resolution
Real-world image super-resolution (RISR) has received increased focus for improving the quality of SR images under unknown complex degradation.
Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization
Open-vocabulary object detection (OVD) aims to scale up vocabulary size to detect objects of novel categories beyond the training vocabulary.
Ranked #12 on
Open Vocabulary Object Detection
on LVIS v1.0
MISSU: 3D Medical Image Segmentation via Self-distilling TransUNet
U-Nets have achieved tremendous success in medical image segmentation.
A Closer Look at Branch Classifiers of Multi-exit Architectures
Multi-exit architectures consist of a backbone and branch classifiers that offer shortened inference pathways to reduce the run-time of deep neural networks.
HybridCR: Weakly-Supervised 3D Point Cloud Semantic Segmentation via Hybrid Contrastive Regularization
To address the huge labeling cost in large-scale point cloud semantic segmentation, we propose a novel hybrid contrastive regularization (HybridCR) framework in weakly-supervised setting, which obtains competitive performance compared to its fully-supervised counterpart.
Self-supervised Models are Good Teaching Assistants for Vision Transformers
These findings motivate us to introduce an self-supervised teaching assistant (SSTA) besides the commonly used supervised teacher to improve the performance of transformers.
Novelty Detection via Contrastive Learning with Negative Data Augmentation
Moreover, our model is more stable for training in a non-adversarial manner, compared to other adversarial based novelty detection methods.
Towards Compact Single Image Super-Resolution via Contrastive Self-distillation
Convolutional neural networks (CNNs) are highly successful for super-resolution (SR) but often require sophisticated architectures with heavy memory cost and computational overhead, significantly restricts their practical deployments on resource-limited devices.
Towards Compact CNNs via Collaborative Compression
Channel pruning and tensor decomposition have received extensive attention in convolutional neural network compression.
DisCo: Remedy Self-supervised Learning on Lightweight Models with Distilled Contrastive Learning
Specifically, we find the final embedding obtained by the mainstream SSL methods contains the most fruitful information, and propose to distill the final embedding to maximally transmit a teacher's knowledge to a lightweight model by constraining the last embedding of the student to be consistent with that of the teacher.
Contrastive Learning for Compact Single Image Dehazing
In this paper, we propose a novel contrastive regularization (CR) built upon contrastive learning to exploit both the information of hazy images and clear images as negative and positive samples, respectively.
Ranked #5 on
Image Dehazing
on RS-Haze
Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identification
The Information Bottleneck (IB) provides an information theoretic principle for representation learning, by retaining all information relevant for predicting label while minimizing the redundancy.
Cross-Modality Person Re-identification
Cross-Modal Person Re-Identification
+3
Learn from Concepts: Towards the Purified Memory for Few-shot Learning
In this paper, we present a novel purified memory mechanism that simulates the recognition process of human beings.
PAMS: Quantized Super-Resolution via Parameterized Max Scale
Specifically, most state-of-the-art SR models without batch normalization have a large dynamic quantization range, which also serves as another cause of performance drop.
Neural network compression via learnable wavelet transforms
Linear layers still occupy a significant portion of the parameters in recurrent neural networks (RNNs).
Training convolutional neural networks with cheap convolutions and online distillation
The large memory and computation consumption in convolutional neural networks (CNNs) has been one of the main barriers for deploying them on resource-limited systems.
Interpretable Neural Network Decoupling
More specifically, we introduce a novel architecture controlling module in each layer to encode the network architecture by a vector.
Towards Optimal Structured CNN Pruning via Generative Adversarial Learning
In this paper, we propose an effective structured pruning approach that jointly prunes filters as well as other structures in an end-to-end manner.
Towards Compact ConvNets via Structure-Sparsity Regularized Filter Pruning
In this paper, we propose a novel filter pruning scheme, termed structured sparsity regularization (SSR), to simultaneously speedup the computation and reduce the memory overhead of CNNs, which can be well supported by various off-the-shelf deep learning libraries.
Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compression
The relationship between the input feature maps and 2D kernels is revealed in a theoretical framework, based on which a kernel sparsity and entropy (KSE) indicator is proposed to quantitate the feature map importance in a feature-agnostic manner to guide model compression.
