• Publications
  • Influence
Discrimination-aware Channel Pruning for Deep Neural Networks
TLDR
This work investigates a simple-yet-effective method, called discrimination-aware channel pruning, to choose those channels that really contribute to discriminative power and proposes a greedy algorithm to conduct channel selection and parameter optimization in an iterative way.
Generative Low-bitwidth Data Free Quantization
TLDR
This paper proposes a knowledge matching generator to produce meaningful fake data by exploiting classification boundary knowledge and distribution information in the pre-trained model with much higher accuracy on 4-bit quantization than the existing data free quantization method.
Towards Context-Aware Interaction Recognition for Visual Relationship Detection
TLDR
This paper proposes an alternative, context-aware interaction recognition framework, and explicitly construct an interaction classifier which combines the context, and the interaction, to avoid the limitation of both approaches.
Towards Effective Low-Bitwidth Convolutional Neural Networks
TLDR
This paper tackles the problem of training a deep convolutional neural network with both low-precision weights and low-bitwidth activations by proposing a two-stage optimization strategy to progressively find good local minima and adopting a novel learning scheme to jointly train a full- Precision model alongside the low-Precision one.
Visual Tracking via Discriminative Sparse Similarity Map
TLDR
This paper casts the tracking problem as finding the candidate that scores highest in the evaluation model based upon a matrix called discriminative sparse similarity map (DSS map), and a pooling approach is proposed to extract the discrim inative information in the DSS map for easily yet effectively selecting good candidates from bad ones and finally get the optimum tracking results.
Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation
TLDR
This paper proposes a ``network decomposition'' strategy, named Group-Net, in which each full-precision group can be effectively reconstructed by aggregating a set of homogeneous binary branches, and shows strong generalization to other tasks.
Attend in Groups: A Weakly-Supervised Deep Learning Framework for Learning from Web Data
TLDR
This work proposes an end-to-end weakly-supervised deep learning framework which is robust to the label noise in Web images and relies on two unified strategies, random grouping and attention, to effectively reduce the negative impact of noisy web image annotations.
HCVRD: A Benchmark for Large-Scale Human-Centered Visual Relationship Detection
TLDR
A webly-supervised approach to these problems is proposed and it is demonstrated that the proposed model provides a strong baseline on the authors' HCVRD dataset.
Sequential Person Recognition in Photo Albums with a Recurrent Network
TLDR
This work proposes a novel recurrent network architecture, in which relational information between instances labels and appearance are modeled jointly, and demonstrates that this simple but elegant formulation achieves state-of-the-art performance on the newly released People In Photo Albums (PIPA) dataset.
Fast Training of Triplet-Based Deep Binary Embedding Networks
TLDR
This paper proposes to formulate high-order binary codes learning as a multi-label classification problem by explicitly separating learning into two interleaved stages and proposes to map the original image to compact binary codes via carefully designed deep convolutional neural networks and the hashing function fitting can be solved by training binary CNN classifiers.
...
...