Picture for Yi-Zhe Song

Yi-Zhe Song

Clue Me In: Semi-Supervised FGVC with Out-of-Distribution Data

Add code
Dec 06, 2021
Figure 1 for Clue Me In: Semi-Supervised FGVC with Out-of-Distribution Data
Figure 2 for Clue Me In: Semi-Supervised FGVC with Out-of-Distribution Data
Figure 3 for Clue Me In: Semi-Supervised FGVC with Out-of-Distribution Data
Figure 4 for Clue Me In: Semi-Supervised FGVC with Out-of-Distribution Data
Viaarxiv icon

Making a Bird AI Expert Work for You and Me

Add code
Dec 06, 2021
Figure 1 for Making a Bird AI Expert Work for You and Me
Figure 2 for Making a Bird AI Expert Work for You and Me
Figure 3 for Making a Bird AI Expert Work for You and Me
Figure 4 for Making a Bird AI Expert Work for You and Me
Viaarxiv icon

Fine-Grained Image Analysis with Deep Learning: A Survey

Add code
Nov 19, 2021
Figure 1 for Fine-Grained Image Analysis with Deep Learning: A Survey
Figure 2 for Fine-Grained Image Analysis with Deep Learning: A Survey
Figure 3 for Fine-Grained Image Analysis with Deep Learning: A Survey
Figure 4 for Fine-Grained Image Analysis with Deep Learning: A Survey
Viaarxiv icon

One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective

Add code
Sep 29, 2021
Figure 1 for One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective
Figure 2 for One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective
Figure 3 for One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective
Figure 4 for One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective
Viaarxiv icon

SketchLattice: Latticed Representation for Sketch Manipulation

Add code
Aug 26, 2021
Figure 1 for SketchLattice: Latticed Representation for Sketch Manipulation
Figure 2 for SketchLattice: Latticed Representation for Sketch Manipulation
Figure 3 for SketchLattice: Latticed Representation for Sketch Manipulation
Figure 4 for SketchLattice: Latticed Representation for Sketch Manipulation
Viaarxiv icon

Disentangled Lifespan Face Synthesis

Add code
Aug 13, 2021
Figure 1 for Disentangled Lifespan Face Synthesis
Figure 2 for Disentangled Lifespan Face Synthesis
Figure 3 for Disentangled Lifespan Face Synthesis
Figure 4 for Disentangled Lifespan Face Synthesis
Viaarxiv icon

Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer

Add code
Aug 12, 2021
Figure 1 for Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer
Figure 2 for Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer
Figure 3 for Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer
Figure 4 for Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer
Viaarxiv icon

Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillation

Add code
Jul 27, 2021
Figure 1 for Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillation
Figure 2 for Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillation
Figure 3 for Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillation
Figure 4 for Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillation
Viaarxiv icon

Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognition

Add code
Jul 27, 2021
Figure 1 for Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognition
Figure 2 for Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognition
Figure 3 for Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognition
Figure 4 for Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognition
Viaarxiv icon

Towards the Unseen: Iterative Text Recognition by Distilling from Errors

Add code
Jul 26, 2021
Figure 1 for Towards the Unseen: Iterative Text Recognition by Distilling from Errors
Figure 2 for Towards the Unseen: Iterative Text Recognition by Distilling from Errors
Figure 3 for Towards the Unseen: Iterative Text Recognition by Distilling from Errors
Figure 4 for Towards the Unseen: Iterative Text Recognition by Distilling from Errors
Viaarxiv icon