Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks98 from public data
- HRank: Filter Pruning Using High-Rank Feature Map922
This paper proposes a novel filter pruning method by exploring the High Rank of feature maps (HRank), inspired by the discovery that the average rank of multiple feature maps generated by a single filter is always the same, regardless of the number of image batches CNNs receive.
- Channel Pruning via Automatic Structure Search293
This paper proposes a new channel pruning method based on artificial bee colony algorithm (ABC), dubbed as ABCPruner, which aims to efficiently find optimal pruned structure, i.e., channel number in each layer, rather than selecting "important" channels as previous works did.
- SeqTR: A Simple Yet Universal Network for Visual Grounding247
Experiments on five benchmark datasets demonstrate that the proposed SeqTR outperforms (or is on par with) the existing state-of-the-arts, proving that a simple yet universal approach for visual grounding is indeed feasible.
- CF-ViT: A General Coarse-to-Fine Method for Vision Transformer121
A coarse-to-fine vision transformer (CF-ViT) to relieve computational burden while retaining performance in this paper, motivated by two important observations in modern ViT models: The coarse-grained patch splitting can locate informative regions of an input image and network inference in a two-stage manner.
- DiffRate : Differentiable Compression Rate for Efficient Vision Transformers110
Differentiable Compression Rate (DiffRate), a novel token compression method that has several appealing properties prior arts do not have, is proposed and achieves state-of-the-art performance.
- ReCU: Reviving the Dead Weights in Binary Neural Networks109
It is proved that reviving the "dead weights" by ReCU can result in a smaller quantization error, and also takes into account the information entropy of the weights, and mathematically analyze why the weight standardization can benefit BNNs.
- Filter Sketch for Network Pruning106
FilterSketch encodes the second-order information of pretrained weights, which enables the representation capacity of pruned networks to be recovered with a simple fine-tuning procedure, leading to a several-orders-of-magnitude reduction of time cost in the optimization of pruning.
- IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization102
This paper proposes a novel zero-shot quantization method called IntraQ, which employs a local object reinforcement that locates the target objects at different scales and positions of the synthetic images and introduces a marginal distance constraint to form class-related features distributed in a coarse area.
- 95
- Pruning Networks With Cross-Layer Ranking & k-Reciprocal Nearest Filters79
A novel pruning method, termed CLR-RNF, is proposed that reveals a “long-tail” pruning problem in magnitude-based weight pruning methods and proposes a computation-aware measurement for individual weight importance, followed by a cross-layer ranking (CLR) of weights to identify and remove the bottom-ranked weights.
- Supervised Online Hashing via Hadamard Codebook Learning77
An online hashing scheme, termed Hadamard Codebook based Online Hashing (HCOH), which aims to solving the above problems towards robust and supervised online hashing and can be embedded with supervised labels and is not limited to a predefined category number.
- Distilling a Powerful Student Model via Online Knowledge Distillation76
A novel method for online knowledge distillation, termed feature fusion and self-distillation (FFSD), which comprises two key components: FFSD, toward solving the above problems in a unified framework.
- Network Pruning Using Adaptive Exemplar Filters74
Inspired by the face recognition community, a message-passing algorithm Affinity Propagation on the weight matrices is used to obtain an adaptive number of exemplars, which then act as the preserved filters, resulting in an automatic and efficient pruning approach called EPruner.
- 61
- Towards Optimal Discrete Online Hashing with Balanced Similarity61
A novel balanced similarity is further proposed, which uses two equilibrium factors to balance the similar and dissimilar weights and eventually enables the usage of discrete optimizations in online hashing.
- 60
- 1xN Pattern for Pruning Convolutional Neural Networks54
This paper proposes a novel 1×N pruning pattern that prunes consecutive N output kernels with the same input channel index into one block, which serves as a basic pruning granularity of thisPruning pattern.
- Hadamard Matrix Guided Online Hashing52
A novel supervised online hashing scheme termed Hadamard Matrix Guided Online Hashing (HMOH) is proposed, which is an orthogonal binary matrix built via Sylvester method, which is an orthogonal binary matrix built via Sylvester method.
- Q-DETR: An Efficient Low-Bit Quantized Detection Transformer51
This paper forms the DRD as a bi-level optimization problem, which can be derived by generalizing the information bottleneck (IB) principle to the learning of Q-DETR, and introduces a new foreground-aware query matching scheme to effectively transfer the teacher information to distillation-desired features to minimize the conditional information entropy.
- 43
- Training Compact CNNs for Image Classification Using Dynamic-Coded Filter Fusion41
This paper presents a novel filter pruning method, dubbed dynamic-coded filter fusion (DCFF), to derive compact CNNs in a computation-economical and regularization-free manner for efficient image classification.
- Dense Auto-Encoder Hashing for Robust Cross-Modality Retrieval40
This paper proposes a novel cross-modality hashing scheme, termed Dense Auto-encoder Hashing (DAH), which can explicitly impute the missed modality and produce robust binary codes by leveraging the relatedness among different modalities.
- Super Vision Transformer36
A novel training paradigm that trains only one ViT model at a time, but is capable of providing improved image recognition performance with various computational costs is presented, which significantly outperforms existing studies on efficient vision transformers.
- 33
- 31
- Learning Efficient GANs for Image Translation via Differentiable Masks and Co-Attention Distillation30
- 27
- 27
- 26
- 25
- 23
- 21
- 20
- 17
- 13
- 12
- Multi-Agent Sampling: Scaling Inference Compute for Data Synthesis with Tree Search-Based Agentic Collaboration11
This work introduces Tree Search-based Orchestrated Agents~(TOA), where the workflow evolves iteratively during the sequential sampling process, and leverages Monte Carlo Tree Search (MCTS), integrating a reward model to provide real-time feedback and accelerate exploration.
- 9
- 9
- Learning Efficient GANs using Differentiable Masks and co-Attention Distillation.9
A novel GAN compression method, termed DMAD, is introduced, by proposing a Differentiable Mask and a co-Attention Distillation that simultaneously distills informative attention maps from both the generator and discriminator of a pre-trained model to the searched generator, effectively stabilizing the adversarial training of the light-weight model.
- 8
- 8
- 8
- 7
- 6
- 6
- 6
- 5
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.