• Publications
  • Influence
ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression
TLDR
ThiNet is proposed, an efficient and unified framework to simultaneously accelerate and compress CNN models in both training and inference stages, and it is revealed that it needs to prune filters based on statistics information computed from its next layer, not the current layer, which differentiates ThiNet from existing methods. Expand
CENTRIST: A Visual Descriptor for Scene Categorization
  • Jianxin Wu, James M. Rehg
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine…
  • 1 August 2011
TLDR
CENsus TRansform hISTogram (CENTRIST), a new visual descriptor for recognizing topological places or scene categories, is introduced and is shown to be a holistic representation and has strong generalizability for category recognition. Expand
Ensembling neural networks: Many could be better than all
TLDR
The bias-variance decomposition of the error is provided in this paper, which shows that the success of GASEN may lie in that it can significantly reduce the bias as well as the variance. Expand
Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval
TLDR
The selective convolutional descriptor aggregation (SCDA) method is proposed, which is unsupervised, using no image label or bounding box annotation, and achieves comparable retrieval results with the state-of-the-art general image retrieval approaches. Expand
Beyond the Euclidean distance: Creating effective visual codebooks using the Histogram Intersection Kernel
  • Jianxin Wu, James M. Rehg
  • Mathematics, Computer Science
  • IEEE 12th International Conference on Computer…
  • 1 September 2009
TLDR
It is demonstrated that HIK can also be used in an unsupervised manner to significantly improve the generation of visual codebooks and the standard k-median clustering method can be used for visual codebook generation and can act as a compromise between HIK and k-means approaches. Expand
Fast Asymmetric Learning for Cascade Face Detection
TLDR
A linear asymmetric classifier (LAC) is presented, a classifier that explicitly handles the asymmetric learning goal as a well-defined constrained optimization problem and is demonstrated experimentally that LAC results in an improved ensemble classifier performance. Expand
Where am I: Place instance and category recognition using spatial PACT
  • Jianxin Wu, James M. Rehg
  • Mathematics, Computer Science
  • IEEE Conference on Computer Vision and Pattern…
  • 23 June 2008
TLDR
Spatial PACT is introduced, a new representation for recognizing instances and categories of places or scenes that outperforms the current state-of-the-art in several place and scene recognition, and shape matching datasets. Expand
Probabilistic End-To-End Noise Correction for Learning With Noisy Labels
  • Kun Yi, Jianxin Wu
  • Computer Science
  • IEEE/CVF Conference on Computer Vision and…
  • 19 March 2019
TLDR
An end-to-end framework called PENCIL, which can update both network parameters and label estimations as label distributions and is more general and robust than existing methods and is easy to apply. Expand
Exploratory Under-Sampling for Class-Imbalance Learning
TLDR
Experiments show that the proposed algorithms, BalanceCascade and EasyEnsemble, have better AUC scores than many existing class-imbalance learning methods and have approximately the same training time as that of under-sampling, which trains significantly faster than other methods. Expand
A Scalable Approach to Activity Recognition based on Object Use
TLDR
It is demonstrated that it is possible to automatically learn object models from video of household activities and employ these models for activity recognition, without requiring any explicit human labeling. Expand
...
1
2
3
4
5
...