Search Results for author:
Found 12 papers, 8 papers with code
Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object Detection
Thus, the optimum of the distillation loss does not necessarily lead to the optimal student classification scores for dense object detectors.
Language Adaptive Weight Generation for Multi-task Visual Grounding
The active perception can take expressions as priors to extract relevant visual features, which can effectively alleviate the mismatches.
Understanding and Unifying Fourteen Attribution Methods with Taylor Interactions
Various attribution methods have been developed to explain deep neural networks (DNNs) by inferring the attribution/importance/contribution score of each input variable to the final output.
Bit-Shrinking: Limiting Instantaneous Sharpness for Improving Post-Training Quantization
To this end, we detach a sharpness term from the loss which reflects the impact of quantization noise.
Learning Symmetry-Aware Geometry Correspondences for 6D Object Pose Estimation
Taking the symmetry properties of objects into consideration, we design a symmetry-aware matching loss to facilitate the learning of dense point-wise geometry features and improve the performance considerably.
SAViT: Structure-Aware Vision Transformer Pruning via Collaborative Optimization
In this paper, we introduce joint importance, which integrates essential structural-aware interactions between components for the first time, to perform collaborative pruning.
Unified Normalization for Accelerating and Stabilizing Transformers
To tackle these issues, we propose Unified Normalization (UN), which can speed up the inference by being fused with other linear operations and achieve comparable performance on par with LN.
Bidirectional Self-Training with Multiple Anisotropic Prototypes for Domain Adaptive Semantic Segmentation
A thriving trend for domain adaptive segmentation endeavors to generate the high-quality pseudo labels for target domain and retrain the segmentor on them.
UWC: Unit-wise Calibration Towards Rapid Network Compression
This paper introduces a post-training quantization~(PTQ) method achieving highly efficient Convolutional Neural Network~ (CNN) quantization with high performance.
Improving Ranking Correlation of Supernet with Candidates Enhancement and Progressive Training
One-shot neural architecture search (NAS) applies weight-sharing supernet to reduce the unaffordable computation overhead of automated architecture designing.
Cascade Bagging for Accuracy Prediction with Few Training Samples
To alleviate this problem, we propose a novel framework to train an accuracy predictor under few training samples.
Extreme Network Compression via Filter Group Approximation
In this paper we propose a novel decomposition method based on filter group approximation, which can significantly reduce the redundancy of deep convolutional neural networks (CNNs) while maintaining the majority of feature representation.
